commit
a50b149bb8
|
|
@ -130,3 +130,32 @@ dmypy.json
|
|||
.pyre/
|
||||
|
||||
*__pycache__*
|
||||
*.pdf
|
||||
*.zip
|
||||
*.png
|
||||
*.csv
|
||||
*.pkl
|
||||
*.dataframe
|
||||
|
||||
|
||||
# other projects
|
||||
LeQua2022
|
||||
MultiLabel
|
||||
NewMethods
|
||||
Ordinal
|
||||
Retrieval
|
||||
eDiscovery
|
||||
poster-cikm
|
||||
slides-cikm
|
||||
slides-short-cikm
|
||||
quick_experiment
|
||||
svm_perf_quantification/svm_struct
|
||||
svm_perf_quantification/svm_light
|
||||
TweetSentQuant
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
*.png
|
||||
|
|
|
|||
|
|
@ -1,3 +1,56 @@
|
|||
Change Log 0.1.8
|
||||
----------------
|
||||
|
||||
- Added Kernel Density Estimation methods (KDEyML, KDEyCS, KDEyHD) as proposed in the paper:
|
||||
Moreo, A., González, P., & del Coz, J. J. Kernel Density Estimation for Multiclass Quantification.
|
||||
arXiv preprint arXiv:2401.00490, 2024
|
||||
|
||||
- Substantial internal refactor: aggregative methods now inherit a pattern by which the fit method consists of:
|
||||
a) fitting the classifier and returning the representations of the training instances (typically the posterior
|
||||
probabilities, the label predictions, or the classifier scores, and typically obtained through kFCV).
|
||||
b) fitting an aggregation function
|
||||
The function implemented in step a) is inherited from the super class. Each new aggregative method now has to
|
||||
implement only the "aggregative_fit" of step b).
|
||||
This pattern was already implemented for the prediction (thus allowing evaluation functions to be performed
|
||||
very quicky), and is now available also for training. The main benefit is that model selection now can nestle
|
||||
the training of quantifiers in two levels: one for the classifier, and another for the aggregation function.
|
||||
As a result, a method with a param grid of 10 combinations for the classifier and 10 combinations for the
|
||||
quantifier, now implies 10 trainings of the classifier + 10*10 trainings of the aggregation function (this is
|
||||
typically much faster than the classifier training), whereas in versions <0.1.8 this amounted to training
|
||||
10*10 (classifiers+aggregations).
|
||||
|
||||
- Added different solvers for ACC and PACC quantifiers. In quapy < 0.1.8 these quantifiers try to solve the system
|
||||
of equations Ax=B exactly (by means of np.linalg.solve). As noted by Mirko Bunse (thanks!), such an exact solution
|
||||
does sometimes not exist. In cases like this, quapy < 0.1.8 resorted to CC for providing a plausible solution.
|
||||
ACC and PACC now resorts to an approximated solution in such cases (minimizing the L2-norm of the difference
|
||||
between Ax-B) as proposed by Mirko Bunse. A quick experiment reveals this heuristic greatly improves the results
|
||||
of ACC and PACC in T2A@LeQua.
|
||||
|
||||
- Fixed ThresholdOptimization methods (X, T50, MAX, MS and MS2). Thanks to Tobias Schumacher and colleagues for pointing
|
||||
this out in Appendix A of "Schumacher, T., Strohmaier, M., & Lemmerich, F. (2021). A comparative evaluation of
|
||||
quantification methods. arXiv:2103.03223v3 [cs.LG]"
|
||||
|
||||
- Added HDx and DistributionMatchingX to non-aggregative quantifiers (see also the new example "comparing_HDy_HDx.py")
|
||||
|
||||
- New UCI multiclass datasets added (thanks to Pablo González). The 5 UCI multiclass datasets are those corresponding
|
||||
to the following criteria:
|
||||
- >1000 instances
|
||||
- >2 classes
|
||||
- classification datasets
|
||||
- Python API available
|
||||
|
||||
- New IFCB (plankton) dataset added (thanks to Pablo González). See qp.datasets.fetch_IFCB.
|
||||
|
||||
- Added new evaluation measures NAE, NRAE (thanks to Andrea Esuli)
|
||||
|
||||
- Added new meta method "MedianEstimator"; an ensemble of binary base quantifiers that receives as input a dictionary
|
||||
of hyperparameters that will explore exhaustively, fitting and generating predictions for each combination of
|
||||
hyperparameters, and that returns, as the prevalence estimates, the median across all predictions.
|
||||
|
||||
- Added "custom_protocol.py" example.
|
||||
|
||||
- New API documentation template.
|
||||
|
||||
Change Log 0.1.7
|
||||
----------------
|
||||
|
||||
|
|
@ -13,7 +13,7 @@ for facilitating the analysis and interpretation of the experimental results.
|
|||
|
||||
### Last updates:
|
||||
|
||||
* Version 0.1.7 is released! major changes can be consulted [here](quapy/CHANGE_LOG.txt).
|
||||
* Version 0.1.8 is released! major changes can be consulted [here](CHANGE_LOG.txt).
|
||||
* A detailed documentation is now available [here](https://hlt-isti.github.io/QuaPy/)
|
||||
* The developer API documentation is available [here](https://hlt-isti.github.io/QuaPy/build/html/modules.html)
|
||||
|
||||
|
|
@ -76,7 +76,7 @@ See the [Wiki](https://github.com/HLT-ISTI/QuaPy/wiki) for detailed examples.
|
|||
* Implementation of many popular quantification methods (Classify-&-Count and its variants, Expectation Maximization,
|
||||
quantification methods based on structured output learning, HDy, QuaNet, quantification ensembles, among others).
|
||||
* Versatile functionality for performing evaluation based on sampling generation protocols (e.g., APP, NPP, etc.).
|
||||
* Implementation of most commonly used evaluation metrics (e.g., AE, RAE, SE, KLD, NKLD, etc.).
|
||||
* Implementation of most commonly used evaluation metrics (e.g., AE, RAE, NAE, NRAE, SE, KLD, NKLD, etc.).
|
||||
* Datasets frequently used in quantification (textual and numeric), including:
|
||||
* 32 UCI Machine Learning datasets.
|
||||
* 11 Twitter quantification-by-sentiment datasets.
|
||||
|
|
@ -96,6 +96,9 @@ quantification methods based on structured output learning, HDy, QuaNet, quantif
|
|||
* pandas, xlrd
|
||||
* matplotlib
|
||||
|
||||
## Contributing
|
||||
|
||||
In case you want to contribute improvements to quapy, please generate pull request to the "devel" branch.
|
||||
|
||||
## Documentation
|
||||
|
||||
|
|
|
|||
1
TODO.txt
1
TODO.txt
|
|
@ -33,7 +33,6 @@ Refactor protocols. APP and NPP related functionalities are duplicated in functi
|
|||
|
||||
New features:
|
||||
==========================================
|
||||
Add NAE, NRAE
|
||||
Add "measures for evaluating ordinal"?
|
||||
Add datasets for topic.
|
||||
Do we want to cover cross-lingual quantification natively in QuaPy, or does it make more sense as an application on top?
|
||||
|
|
|
|||
|
|
@ -1,831 +0,0 @@
|
|||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Datasets — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Evaluation" href="Evaluation.html" />
|
||||
<link rel="prev" title="Installation" href="Installation.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Evaluation.html" title="Evaluation"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Installation.html" title="Installation"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Datasets</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="datasets">
|
||||
<h1>Datasets<a class="headerlink" href="#datasets" title="Permalink to this heading">¶</a></h1>
|
||||
<p>QuaPy makes available several datasets that have been used in
|
||||
quantification literature, as well as an interface to allow
|
||||
anyone import their custom datasets.</p>
|
||||
<p>A <em>Dataset</em> object in QuaPy is roughly a pair of <em>LabelledCollection</em> objects,
|
||||
one playing the role of the training set, another the test set.
|
||||
<em>LabelledCollection</em> is a data class consisting of the (iterable)
|
||||
instances and labels. This class handles most of the sampling functionality in QuaPy.
|
||||
Take a look at the following code:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">import</span> <span class="nn">quapy.functional</span> <span class="k">as</span> <span class="nn">F</span>
|
||||
|
||||
<span class="n">instances</span> <span class="o">=</span> <span class="p">[</span>
|
||||
<span class="s1">'1st positive document'</span><span class="p">,</span> <span class="s1">'2nd positive document'</span><span class="p">,</span>
|
||||
<span class="s1">'the only negative document'</span><span class="p">,</span>
|
||||
<span class="s1">'1st neutral document'</span><span class="p">,</span> <span class="s1">'2nd neutral document'</span><span class="p">,</span> <span class="s1">'3rd neutral document'</span>
|
||||
<span class="p">]</span>
|
||||
<span class="n">labels</span> <span class="o">=</span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">]</span>
|
||||
|
||||
<span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">LabelledCollection</span><span class="p">(</span><span class="n">instances</span><span class="p">,</span> <span class="n">labels</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">strprev</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">prevalence</span><span class="p">(),</span> <span class="n">prec</span><span class="o">=</span><span class="mi">2</span><span class="p">))</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Output the class prevalences (showing 2 digit precision):</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">[</span><span class="mf">0.17</span><span class="p">,</span> <span class="mf">0.50</span><span class="p">,</span> <span class="mf">0.33</span><span class="p">]</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>One can easily produce new samples at desired class prevalence values:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">sample_size</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="n">prev</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.4</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">]</span>
|
||||
<span class="n">sample</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">sampling</span><span class="p">(</span><span class="n">sample_size</span><span class="p">,</span> <span class="o">*</span><span class="n">prev</span><span class="p">)</span>
|
||||
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s1">'instances:'</span><span class="p">,</span> <span class="n">sample</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s1">'labels:'</span><span class="p">,</span> <span class="n">sample</span><span class="o">.</span><span class="n">labels</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s1">'prevalence:'</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">strprev</span><span class="p">(</span><span class="n">sample</span><span class="o">.</span><span class="n">prevalence</span><span class="p">(),</span> <span class="n">prec</span><span class="o">=</span><span class="mi">2</span><span class="p">))</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Which outputs:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">instances</span><span class="p">:</span> <span class="p">[</span><span class="s1">'the only negative document'</span> <span class="s1">'2nd positive document'</span>
|
||||
<span class="s1">'2nd positive document'</span> <span class="s1">'2nd neutral document'</span> <span class="s1">'1st positive document'</span>
|
||||
<span class="s1">'the only negative document'</span> <span class="s1">'the only negative document'</span>
|
||||
<span class="s1">'the only negative document'</span> <span class="s1">'2nd positive document'</span>
|
||||
<span class="s1">'1st positive document'</span><span class="p">]</span>
|
||||
<span class="n">labels</span><span class="p">:</span> <span class="p">[</span><span class="mi">0</span> <span class="mi">2</span> <span class="mi">2</span> <span class="mi">1</span> <span class="mi">2</span> <span class="mi">0</span> <span class="mi">0</span> <span class="mi">0</span> <span class="mi">2</span> <span class="mi">2</span><span class="p">]</span>
|
||||
<span class="n">prevalence</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.40</span><span class="p">,</span> <span class="mf">0.10</span><span class="p">,</span> <span class="mf">0.50</span><span class="p">]</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Samples can be made consistent across different runs (e.g., to test
|
||||
different methods on the same exact samples) by sampling and retaining
|
||||
the indexes, that can then be used to generate the sample:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">index</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">sampling_index</span><span class="p">(</span><span class="n">sample_size</span><span class="p">,</span> <span class="o">*</span><span class="n">prev</span><span class="p">)</span>
|
||||
<span class="k">for</span> <span class="n">method</span> <span class="ow">in</span> <span class="n">methods</span><span class="p">:</span>
|
||||
<span class="n">sample</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">sampling_from_index</span><span class="p">(</span><span class="n">index</span><span class="p">)</span>
|
||||
<span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>However, generating samples for evaluation purposes is tackled in QuaPy
|
||||
by means of the evaluation protocols (see the dedicated entries in the Wiki
|
||||
for <a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Evaluation">evaluation</a> and
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Protocols">protocols</a>).</p>
|
||||
<section id="reviews-datasets">
|
||||
<h2>Reviews Datasets<a class="headerlink" href="#reviews-datasets" title="Permalink to this heading">¶</a></h2>
|
||||
<p>Three datasets of reviews about Kindle devices, Harry Potter’s series, and
|
||||
the well-known IMDb movie reviews can be fetched using a unified interface.
|
||||
For example:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'kindle'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>These datasets have been used in:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">Esuli</span><span class="p">,</span> <span class="n">A</span><span class="o">.</span><span class="p">,</span> <span class="n">Moreo</span><span class="p">,</span> <span class="n">A</span><span class="o">.</span><span class="p">,</span> <span class="o">&</span> <span class="n">Sebastiani</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span> <span class="p">(</span><span class="mi">2018</span><span class="p">,</span> <span class="n">October</span><span class="p">)</span><span class="o">.</span>
|
||||
<span class="n">A</span> <span class="n">recurrent</span> <span class="n">neural</span> <span class="n">network</span> <span class="k">for</span> <span class="n">sentiment</span> <span class="n">quantification</span><span class="o">.</span>
|
||||
<span class="n">In</span> <span class="n">Proceedings</span> <span class="n">of</span> <span class="n">the</span> <span class="mi">27</span><span class="n">th</span> <span class="n">ACM</span> <span class="n">International</span> <span class="n">Conference</span> <span class="n">on</span>
|
||||
<span class="n">Information</span> <span class="ow">and</span> <span class="n">Knowledge</span> <span class="n">Management</span> <span class="p">(</span><span class="n">pp</span><span class="o">.</span> <span class="mi">1775</span><span class="o">-</span><span class="mi">1778</span><span class="p">)</span><span class="o">.</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The list of reviews ids is available in:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">REVIEWS_SENTIMENT_DATASETS</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Some statistics of the fhe available datasets are summarized below:</p>
|
||||
<table class="docutils align-default">
|
||||
<thead>
|
||||
<tr class="row-odd"><th class="head"><p>Dataset</p></th>
|
||||
<th class="head text-center"><p>classes</p></th>
|
||||
<th class="head text-center"><p>train size</p></th>
|
||||
<th class="head text-center"><p>test size</p></th>
|
||||
<th class="head text-center"><p>train prev</p></th>
|
||||
<th class="head text-center"><p>test prev</p></th>
|
||||
<th class="head"><p>type</p></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>hp</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>9533</p></td>
|
||||
<td class="text-center"><p>18399</p></td>
|
||||
<td class="text-center"><p>[0.018, 0.982]</p></td>
|
||||
<td class="text-center"><p>[0.065, 0.935]</p></td>
|
||||
<td><p>text</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>kindle</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>3821</p></td>
|
||||
<td class="text-center"><p>21591</p></td>
|
||||
<td class="text-center"><p>[0.081, 0.919]</p></td>
|
||||
<td class="text-center"><p>[0.063, 0.937]</p></td>
|
||||
<td><p>text</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>imdb</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>25000</p></td>
|
||||
<td class="text-center"><p>25000</p></td>
|
||||
<td class="text-center"><p>[0.500, 0.500]</p></td>
|
||||
<td class="text-center"><p>[0.500, 0.500]</p></td>
|
||||
<td><p>text</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</section>
|
||||
<section id="twitter-sentiment-datasets">
|
||||
<h2>Twitter Sentiment Datasets<a class="headerlink" href="#twitter-sentiment-datasets" title="Permalink to this heading">¶</a></h2>
|
||||
<p>11 Twitter datasets for sentiment analysis.
|
||||
Text is not accessible, and the documents were made available
|
||||
in tf-idf format. Each dataset presents two splits: a train/val
|
||||
split for model selection purposes, and a train+val/test split
|
||||
for model evaluation. The following code exemplifies how to load
|
||||
a twitter dataset for model selection.</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_twitter</span><span class="p">(</span><span class="s1">'gasp'</span><span class="p">,</span> <span class="n">for_model_selection</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The datasets were used in:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">Gao</span><span class="p">,</span> <span class="n">W</span><span class="o">.</span><span class="p">,</span> <span class="o">&</span> <span class="n">Sebastiani</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span> <span class="p">(</span><span class="mi">2015</span><span class="p">,</span> <span class="n">August</span><span class="p">)</span><span class="o">.</span>
|
||||
<span class="n">Tweet</span> <span class="n">sentiment</span><span class="p">:</span> <span class="n">From</span> <span class="n">classification</span> <span class="n">to</span> <span class="n">quantification</span><span class="o">.</span>
|
||||
<span class="n">In</span> <span class="mi">2015</span> <span class="n">IEEE</span><span class="o">/</span><span class="n">ACM</span> <span class="n">International</span> <span class="n">Conference</span> <span class="n">on</span> <span class="n">Advances</span> <span class="ow">in</span>
|
||||
<span class="n">Social</span> <span class="n">Networks</span> <span class="n">Analysis</span> <span class="ow">and</span> <span class="n">Mining</span> <span class="p">(</span><span class="n">ASONAM</span><span class="p">)</span> <span class="p">(</span><span class="n">pp</span><span class="o">.</span> <span class="mi">97</span><span class="o">-</span><span class="mi">104</span><span class="p">)</span><span class="o">.</span> <span class="n">IEEE</span><span class="o">.</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Three of the datasets (semeval13, semeval14, and semeval15) share the
|
||||
same training set (semeval), meaning that the training split one would get
|
||||
when requesting any of them is the same. The dataset “semeval” can only
|
||||
be requested with “for_model_selection=True”.
|
||||
The lists of the Twitter dataset’s ids can be consulted in:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># a list of 11 dataset ids that can be used for model selection or model evaluation</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">TWITTER_SENTIMENT_DATASETS_TEST</span>
|
||||
|
||||
<span class="c1"># 9 dataset ids in which "semeval13", "semeval14", and "semeval15" are replaced with "semeval"</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">TWITTER_SENTIMENT_DATASETS_TRAIN</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Some details can be found below:</p>
|
||||
<table class="docutils align-default">
|
||||
<thead>
|
||||
<tr class="row-odd"><th class="head"><p>Dataset</p></th>
|
||||
<th class="head text-center"><p>classes</p></th>
|
||||
<th class="head text-center"><p>train size</p></th>
|
||||
<th class="head text-center"><p>test size</p></th>
|
||||
<th class="head text-center"><p>features</p></th>
|
||||
<th class="head text-center"><p>train prev</p></th>
|
||||
<th class="head text-center"><p>test prev</p></th>
|
||||
<th class="head"><p>type</p></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>gasp</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>8788</p></td>
|
||||
<td class="text-center"><p>3765</p></td>
|
||||
<td class="text-center"><p>694582</p></td>
|
||||
<td class="text-center"><p>[0.421, 0.496, 0.082]</p></td>
|
||||
<td class="text-center"><p>[0.407, 0.507, 0.086]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>hcr</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>1594</p></td>
|
||||
<td class="text-center"><p>798</p></td>
|
||||
<td class="text-center"><p>222046</p></td>
|
||||
<td class="text-center"><p>[0.546, 0.211, 0.243]</p></td>
|
||||
<td class="text-center"><p>[0.640, 0.167, 0.193]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>omd</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>1839</p></td>
|
||||
<td class="text-center"><p>787</p></td>
|
||||
<td class="text-center"><p>199151</p></td>
|
||||
<td class="text-center"><p>[0.463, 0.271, 0.266]</p></td>
|
||||
<td class="text-center"><p>[0.437, 0.283, 0.280]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>sanders</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>2155</p></td>
|
||||
<td class="text-center"><p>923</p></td>
|
||||
<td class="text-center"><p>229399</p></td>
|
||||
<td class="text-center"><p>[0.161, 0.691, 0.148]</p></td>
|
||||
<td class="text-center"><p>[0.164, 0.688, 0.148]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>semeval13</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>11338</p></td>
|
||||
<td class="text-center"><p>3813</p></td>
|
||||
<td class="text-center"><p>1215742</p></td>
|
||||
<td class="text-center"><p>[0.159, 0.470, 0.372]</p></td>
|
||||
<td class="text-center"><p>[0.158, 0.430, 0.412]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>semeval14</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>11338</p></td>
|
||||
<td class="text-center"><p>1853</p></td>
|
||||
<td class="text-center"><p>1215742</p></td>
|
||||
<td class="text-center"><p>[0.159, 0.470, 0.372]</p></td>
|
||||
<td class="text-center"><p>[0.109, 0.361, 0.530]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>semeval15</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>11338</p></td>
|
||||
<td class="text-center"><p>2390</p></td>
|
||||
<td class="text-center"><p>1215742</p></td>
|
||||
<td class="text-center"><p>[0.159, 0.470, 0.372]</p></td>
|
||||
<td class="text-center"><p>[0.153, 0.413, 0.434]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>semeval16</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>8000</p></td>
|
||||
<td class="text-center"><p>2000</p></td>
|
||||
<td class="text-center"><p>889504</p></td>
|
||||
<td class="text-center"><p>[0.157, 0.351, 0.492]</p></td>
|
||||
<td class="text-center"><p>[0.163, 0.341, 0.497]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>sst</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>2971</p></td>
|
||||
<td class="text-center"><p>1271</p></td>
|
||||
<td class="text-center"><p>376132</p></td>
|
||||
<td class="text-center"><p>[0.261, 0.452, 0.288]</p></td>
|
||||
<td class="text-center"><p>[0.207, 0.481, 0.312]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>wa</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>2184</p></td>
|
||||
<td class="text-center"><p>936</p></td>
|
||||
<td class="text-center"><p>248563</p></td>
|
||||
<td class="text-center"><p>[0.305, 0.414, 0.281]</p></td>
|
||||
<td class="text-center"><p>[0.282, 0.446, 0.272]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>wb</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>4259</p></td>
|
||||
<td class="text-center"><p>1823</p></td>
|
||||
<td class="text-center"><p>404333</p></td>
|
||||
<td class="text-center"><p>[0.270, 0.392, 0.337]</p></td>
|
||||
<td class="text-center"><p>[0.274, 0.392, 0.335]</p></td>
|
||||
<td><p>sparse</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</section>
|
||||
<section id="uci-machine-learning">
|
||||
<h2>UCI Machine Learning<a class="headerlink" href="#uci-machine-learning" title="Permalink to this heading">¶</a></h2>
|
||||
<p>A set of 32 datasets from the <a class="reference external" href="https://archive.ics.uci.edu/ml/datasets.php">UCI Machine Learning repository</a>
|
||||
used in:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">Pérez</span><span class="o">-</span><span class="n">Gállego</span><span class="p">,</span> <span class="n">P</span><span class="o">.</span><span class="p">,</span> <span class="n">Quevedo</span><span class="p">,</span> <span class="n">J</span><span class="o">.</span> <span class="n">R</span><span class="o">.</span><span class="p">,</span> <span class="o">&</span> <span class="k">del</span> <span class="n">Coz</span><span class="p">,</span> <span class="n">J</span><span class="o">.</span> <span class="n">J</span><span class="o">.</span> <span class="p">(</span><span class="mi">2017</span><span class="p">)</span><span class="o">.</span>
|
||||
<span class="n">Using</span> <span class="n">ensembles</span> <span class="k">for</span> <span class="n">problems</span> <span class="k">with</span> <span class="n">characterizable</span> <span class="n">changes</span>
|
||||
<span class="ow">in</span> <span class="n">data</span> <span class="n">distribution</span><span class="p">:</span> <span class="n">A</span> <span class="n">case</span> <span class="n">study</span> <span class="n">on</span> <span class="n">quantification</span><span class="o">.</span>
|
||||
<span class="n">Information</span> <span class="n">Fusion</span><span class="p">,</span> <span class="mi">34</span><span class="p">,</span> <span class="mi">87</span><span class="o">-</span><span class="mf">100.</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The list does not exactly coincide with that used in Pérez-Gállego et al. 2017
|
||||
since we were unable to find the datasets with ids “diabetes” and “phoneme”.</p>
|
||||
<p>These dataset can be loaded by calling, e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCIDataset</span><span class="p">(</span><span class="s1">'yeast'</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>This call will return a <em>Dataset</em> object in which the training and
|
||||
test splits are randomly drawn, in a stratified manner, from the whole
|
||||
collection at 70% and 30%, respectively. The <em>verbose=True</em> option indicates
|
||||
that the dataset description should be printed in standard output.
|
||||
The original data is not split,
|
||||
and some papers submit the entire collection to a kFCV validation.
|
||||
In order to accommodate with these practices, one could first instantiate
|
||||
the entire collection, and then creating a generator that will return one
|
||||
training+test dataset at a time, following a kFCV protocol:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="n">collection</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCILabelledCollection</span><span class="p">(</span><span class="s2">"yeast"</span><span class="p">)</span>
|
||||
<span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">Dataset</span><span class="o">.</span><span class="n">kFCV</span><span class="p">(</span><span class="n">collection</span><span class="p">,</span> <span class="n">nfolds</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">nrepeats</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
|
||||
<span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Above code will allow to conduct a 2x5FCV evaluation on the “yeast” dataset.</p>
|
||||
<p>All datasets come in numerical form (dense matrices); some statistics
|
||||
are summarized below.</p>
|
||||
<table class="docutils align-default">
|
||||
<thead>
|
||||
<tr class="row-odd"><th class="head"><p>Dataset</p></th>
|
||||
<th class="head text-center"><p>classes</p></th>
|
||||
<th class="head text-center"><p>instances</p></th>
|
||||
<th class="head text-center"><p>features</p></th>
|
||||
<th class="head text-center"><p>prev</p></th>
|
||||
<th class="head"><p>type</p></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>acute.a</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>120</p></td>
|
||||
<td class="text-center"><p>6</p></td>
|
||||
<td class="text-center"><p>[0.508, 0.492]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>acute.b</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>120</p></td>
|
||||
<td class="text-center"><p>6</p></td>
|
||||
<td class="text-center"><p>[0.583, 0.417]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>balance.1</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>625</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.539, 0.461]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>balance.2</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>625</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.922, 0.078]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>balance.3</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>625</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.539, 0.461]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>breast-cancer</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>683</p></td>
|
||||
<td class="text-center"><p>9</p></td>
|
||||
<td class="text-center"><p>[0.350, 0.650]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>cmc.1</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1473</p></td>
|
||||
<td class="text-center"><p>9</p></td>
|
||||
<td class="text-center"><p>[0.573, 0.427]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>cmc.2</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1473</p></td>
|
||||
<td class="text-center"><p>9</p></td>
|
||||
<td class="text-center"><p>[0.774, 0.226]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>cmc.3</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1473</p></td>
|
||||
<td class="text-center"><p>9</p></td>
|
||||
<td class="text-center"><p>[0.653, 0.347]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>ctg.1</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>2126</p></td>
|
||||
<td class="text-center"><p>22</p></td>
|
||||
<td class="text-center"><p>[0.222, 0.778]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>ctg.2</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>2126</p></td>
|
||||
<td class="text-center"><p>22</p></td>
|
||||
<td class="text-center"><p>[0.861, 0.139]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>ctg.3</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>2126</p></td>
|
||||
<td class="text-center"><p>22</p></td>
|
||||
<td class="text-center"><p>[0.917, 0.083]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>german</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>24</p></td>
|
||||
<td class="text-center"><p>[0.300, 0.700]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>haberman</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>306</p></td>
|
||||
<td class="text-center"><p>3</p></td>
|
||||
<td class="text-center"><p>[0.735, 0.265]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>ionosphere</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>351</p></td>
|
||||
<td class="text-center"><p>34</p></td>
|
||||
<td class="text-center"><p>[0.641, 0.359]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>iris.1</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>150</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.667, 0.333]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>iris.2</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>150</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.667, 0.333]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>iris.3</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>150</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.667, 0.333]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>mammographic</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>830</p></td>
|
||||
<td class="text-center"><p>5</p></td>
|
||||
<td class="text-center"><p>[0.514, 0.486]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>pageblocks.5</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>5473</p></td>
|
||||
<td class="text-center"><p>10</p></td>
|
||||
<td class="text-center"><p>[0.979, 0.021]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>semeion</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1593</p></td>
|
||||
<td class="text-center"><p>256</p></td>
|
||||
<td class="text-center"><p>[0.901, 0.099]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>sonar</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>208</p></td>
|
||||
<td class="text-center"><p>60</p></td>
|
||||
<td class="text-center"><p>[0.534, 0.466]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>spambase</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>4601</p></td>
|
||||
<td class="text-center"><p>57</p></td>
|
||||
<td class="text-center"><p>[0.606, 0.394]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>spectf</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>267</p></td>
|
||||
<td class="text-center"><p>44</p></td>
|
||||
<td class="text-center"><p>[0.794, 0.206]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>tictactoe</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>958</p></td>
|
||||
<td class="text-center"><p>9</p></td>
|
||||
<td class="text-center"><p>[0.653, 0.347]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>transfusion</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>748</p></td>
|
||||
<td class="text-center"><p>4</p></td>
|
||||
<td class="text-center"><p>[0.762, 0.238]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>wdbc</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>569</p></td>
|
||||
<td class="text-center"><p>30</p></td>
|
||||
<td class="text-center"><p>[0.627, 0.373]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>wine.1</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>178</p></td>
|
||||
<td class="text-center"><p>13</p></td>
|
||||
<td class="text-center"><p>[0.669, 0.331]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>wine.2</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>178</p></td>
|
||||
<td class="text-center"><p>13</p></td>
|
||||
<td class="text-center"><p>[0.601, 0.399]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>wine.3</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>178</p></td>
|
||||
<td class="text-center"><p>13</p></td>
|
||||
<td class="text-center"><p>[0.730, 0.270]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>wine-q-red</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1599</p></td>
|
||||
<td class="text-center"><p>11</p></td>
|
||||
<td class="text-center"><p>[0.465, 0.535]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>wine-q-white</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>4898</p></td>
|
||||
<td class="text-center"><p>11</p></td>
|
||||
<td class="text-center"><p>[0.335, 0.665]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>yeast</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>1484</p></td>
|
||||
<td class="text-center"><p>8</p></td>
|
||||
<td class="text-center"><p>[0.711, 0.289]</p></td>
|
||||
<td><p>dense</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<section id="issues">
|
||||
<h3>Issues:<a class="headerlink" href="#issues" title="Permalink to this heading">¶</a></h3>
|
||||
<p>All datasets will be downloaded automatically the first time they are requested, and
|
||||
stored in the <em>quapy_data</em> folder for faster further reuse.
|
||||
However, some datasets require special actions that at the moment are not fully
|
||||
automated.</p>
|
||||
<ul class="simple">
|
||||
<li><p>Datasets with ids “ctg.1”, “ctg.2”, and “ctg.3” (<em>Cardiotocography Data Set</em>) load
|
||||
an Excel file, which requires the user to install the <em>xlrd</em> Python module in order
|
||||
to open it.</p></li>
|
||||
<li><p>The dataset with id “pageblocks.5” (<em>Page Blocks Classification (5)</em>) needs to
|
||||
open a “unix compressed file” (extension .Z), which is not directly doable with
|
||||
standard Pythons packages like gzip or zip. This file would need to be uncompressed using
|
||||
OS-dependent software manually. Information on how to do it will be printed the first
|
||||
time the dataset is invoked.</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
</section>
|
||||
<section id="lequa-datasets">
|
||||
<h2>LeQua Datasets<a class="headerlink" href="#lequa-datasets" title="Permalink to this heading">¶</a></h2>
|
||||
<p>QuaPy also provides the datasets used for the LeQua competition.
|
||||
In brief, there are 4 tasks (T1A, T1B, T2A, T2B) having to do with text quantification
|
||||
problems. Tasks T1A and T1B provide documents in vector form, while T2A and T2B provide
|
||||
raw documents instead.
|
||||
Tasks T1A and T2A are binary sentiment quantification problems, while T2A and T2B
|
||||
are multiclass quantification problems consisting of estimating the class prevalence
|
||||
values of 28 different merchandise products.</p>
|
||||
<p>Every task consists of a training set, a set of validation samples (for model selection)
|
||||
and a set of test samples (for evaluation). QuaPy returns this data as a LabelledCollection
|
||||
(training) and two generation protocols (for validation and test samples), as follows:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">training</span><span class="p">,</span> <span class="n">val_generator</span><span class="p">,</span> <span class="n">test_generator</span> <span class="o">=</span> <span class="n">fetch_lequa2022</span><span class="p">(</span><span class="n">task</span><span class="o">=</span><span class="n">task</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>See the <code class="docutils literal notranslate"><span class="pre">lequa2022_experiments.py</span></code> in the examples folder for further details on how to
|
||||
carry out experiments using these datasets.</p>
|
||||
<p>The datasets are downloaded only once, and stored for fast reuse.</p>
|
||||
<p>Some statistics are summarized below:</p>
|
||||
<table class="docutils align-default">
|
||||
<thead>
|
||||
<tr class="row-odd"><th class="head"><p>Dataset</p></th>
|
||||
<th class="head text-center"><p>classes</p></th>
|
||||
<th class="head text-center"><p>train size</p></th>
|
||||
<th class="head text-center"><p>validation samples</p></th>
|
||||
<th class="head text-center"><p>test samples</p></th>
|
||||
<th class="head text-center"><p>docs by sample</p></th>
|
||||
<th class="head text-center"><p>type</p></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>T1A</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>5000</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>5000</p></td>
|
||||
<td class="text-center"><p>250</p></td>
|
||||
<td class="text-center"><p>vector</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>T1B</p></td>
|
||||
<td class="text-center"><p>28</p></td>
|
||||
<td class="text-center"><p>20000</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>5000</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>vector</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>T2A</p></td>
|
||||
<td class="text-center"><p>2</p></td>
|
||||
<td class="text-center"><p>5000</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>5000</p></td>
|
||||
<td class="text-center"><p>250</p></td>
|
||||
<td class="text-center"><p>text</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>T2B</p></td>
|
||||
<td class="text-center"><p>28</p></td>
|
||||
<td class="text-center"><p>20000</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>5000</p></td>
|
||||
<td class="text-center"><p>1000</p></td>
|
||||
<td class="text-center"><p>text</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p>For further details on the datasets, we refer to the original
|
||||
<a class="reference external" href="https://ceur-ws.org/Vol-3180/paper-146.pdf">paper</a>:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">Esuli</span><span class="p">,</span> <span class="n">A</span><span class="o">.</span><span class="p">,</span> <span class="n">Moreo</span><span class="p">,</span> <span class="n">A</span><span class="o">.</span><span class="p">,</span> <span class="n">Sebastiani</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="p">,</span> <span class="o">&</span> <span class="n">Sperduti</span><span class="p">,</span> <span class="n">G</span><span class="o">.</span> <span class="p">(</span><span class="mi">2022</span><span class="p">)</span><span class="o">.</span>
|
||||
<span class="n">A</span> <span class="n">Detailed</span> <span class="n">Overview</span> <span class="n">of</span> <span class="n">LeQua</span><span class="o">@</span> <span class="n">CLEF</span> <span class="mi">2022</span><span class="p">:</span> <span class="n">Learning</span> <span class="n">to</span> <span class="n">Quantify</span><span class="o">.</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="adding-custom-datasets">
|
||||
<h2>Adding Custom Datasets<a class="headerlink" href="#adding-custom-datasets" title="Permalink to this heading">¶</a></h2>
|
||||
<p>QuaPy provides data loaders for simple formats dealing with
|
||||
text, following the format:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">class</span><span class="o">-</span><span class="nb">id</span> \<span class="n">t</span> <span class="n">first</span> <span class="n">document</span><span class="s1">'s pre-processed text </span><span class="se">\n</span>
|
||||
<span class="n">class</span><span class="o">-</span><span class="nb">id</span> \<span class="n">t</span> <span class="n">second</span> <span class="n">document</span><span class="s1">'s pre-processed text </span><span class="se">\n</span>
|
||||
<span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>and sparse representations of the form:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">{</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="ow">or</span> <span class="o">+</span><span class="mi">1</span><span class="p">}</span> <span class="n">col</span><span class="p">(</span><span class="nb">int</span><span class="p">):</span><span class="n">val</span><span class="p">(</span><span class="nb">float</span><span class="p">)</span> <span class="n">col</span><span class="p">(</span><span class="nb">int</span><span class="p">):</span><span class="n">val</span><span class="p">(</span><span class="nb">float</span><span class="p">)</span> <span class="o">...</span> \<span class="n">n</span>
|
||||
<span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The code in charge in loading a LabelledCollection is:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="nd">@classmethod</span>
|
||||
<span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span><span class="nb">str</span><span class="p">,</span> <span class="n">loader_func</span><span class="p">:</span><span class="n">callable</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="n">LabelledCollection</span><span class="p">(</span><span class="o">*</span><span class="n">loader_func</span><span class="p">(</span><span class="n">path</span><span class="p">))</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>indicating that any <em>loader_func</em> (e.g., a user-defined one) which
|
||||
returns valid arguments for initializing a <em>LabelledCollection</em> object will allow
|
||||
to load any collection. In particular, the <em>LabelledCollection</em> receives as
|
||||
arguments the instances (as an iterable) and the labels (as an iterable) and,
|
||||
additionally, the number of classes can be specified (it would otherwise be
|
||||
inferred from the labels, but that requires at least one positive example for
|
||||
all classes to be present in the collection).</p>
|
||||
<p>The same <em>loader_func</em> can be passed to a Dataset, along with two
|
||||
paths, in order to create a training and test pair of <em>LabelledCollection</em>,
|
||||
e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
|
||||
<span class="n">train_path</span> <span class="o">=</span> <span class="s1">'../my_data/train.dat'</span>
|
||||
<span class="n">test_path</span> <span class="o">=</span> <span class="s1">'../my_data/test.dat'</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">my_custom_loader</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fin</span><span class="p">:</span>
|
||||
<span class="o">...</span>
|
||||
<span class="k">return</span> <span class="n">instances</span><span class="p">,</span> <span class="n">labels</span>
|
||||
|
||||
<span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">Dataset</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">train_path</span><span class="p">,</span> <span class="n">test_path</span><span class="p">,</span> <span class="n">my_custom_loader</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<section id="data-processing">
|
||||
<h3>Data Processing<a class="headerlink" href="#data-processing" title="Permalink to this heading">¶</a></h3>
|
||||
<p>QuaPy implements a number of preprocessing functions in the package <em>qp.data.preprocessing</em>, including:</p>
|
||||
<ul class="simple">
|
||||
<li><p><em>text2tfidf</em>: tfidf vectorization</p></li>
|
||||
<li><p><em>reduce_columns</em>: reducing the number of columns based on term frequency</p></li>
|
||||
<li><p><em>standardize</em>: transforms the column values into z-scores (i.e., subtract the mean and normalizes by the standard deviation, so
|
||||
that the column values have zero mean and unit variance).</p></li>
|
||||
<li><p><em>index</em>: transforms textual tokens into lists of numeric ids)</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Datasets</a><ul>
|
||||
<li><a class="reference internal" href="#reviews-datasets">Reviews Datasets</a></li>
|
||||
<li><a class="reference internal" href="#twitter-sentiment-datasets">Twitter Sentiment Datasets</a></li>
|
||||
<li><a class="reference internal" href="#uci-machine-learning">UCI Machine Learning</a><ul>
|
||||
<li><a class="reference internal" href="#issues">Issues:</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><a class="reference internal" href="#lequa-datasets">LeQua Datasets</a></li>
|
||||
<li><a class="reference internal" href="#adding-custom-datasets">Adding Custom Datasets</a><ul>
|
||||
<li><a class="reference internal" href="#data-processing">Data Processing</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="Installation.html"
|
||||
title="previous chapter">Installation</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="Evaluation.html"
|
||||
title="next chapter">Evaluation</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/Datasets.md.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Evaluation.html" title="Evaluation"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Installation.html" title="Installation"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Datasets</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,281 +0,0 @@
|
|||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Evaluation — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Protocols" href="Protocols.html" />
|
||||
<link rel="prev" title="Datasets" href="Datasets.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Protocols.html" title="Protocols"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Datasets.html" title="Datasets"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Evaluation</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="evaluation">
|
||||
<h1>Evaluation<a class="headerlink" href="#evaluation" title="Permalink to this heading">¶</a></h1>
|
||||
<p>Quantification is an appealing tool in scenarios of dataset shift,
|
||||
and particularly in scenarios of prior-probability shift.
|
||||
That is, the interest in estimating the class prevalences arises
|
||||
under the belief that those class prevalences might have changed
|
||||
with respect to the ones observed during training.
|
||||
In other words, one could simply return the training prevalence
|
||||
as a predictor of the test prevalence if this change is assumed
|
||||
to be unlikely (as is the case in general scenarios of
|
||||
machine learning governed by the iid assumption).
|
||||
In brief, quantification requires dedicated evaluation protocols,
|
||||
which are implemented in QuaPy and explained here.</p>
|
||||
<section id="error-measures">
|
||||
<h2>Error Measures<a class="headerlink" href="#error-measures" title="Permalink to this heading">¶</a></h2>
|
||||
<p>The module quapy.error implements the following error measures for quantification:</p>
|
||||
<ul class="simple">
|
||||
<li><p><em>mae</em>: mean absolute error</p></li>
|
||||
<li><p><em>mrae</em>: mean relative absolute error</p></li>
|
||||
<li><p><em>mse</em>: mean squared error</p></li>
|
||||
<li><p><em>mkld</em>: mean Kullback-Leibler Divergence</p></li>
|
||||
<li><p><em>mnkld</em>: mean normalized Kullback-Leibler Divergence</p></li>
|
||||
</ul>
|
||||
<p>Functions <em>ae</em>, <em>rae</em>, <em>se</em>, <em>kld</em>, and <em>nkld</em> are also available,
|
||||
which return the individual errors (i.e., without averaging the whole).</p>
|
||||
<p>Some errors of classification are also available:</p>
|
||||
<ul class="simple">
|
||||
<li><p><em>acce</em>: accuracy error (1-accuracy)</p></li>
|
||||
<li><p><em>f1e</em>: F-1 score error (1-F1 score)</p></li>
|
||||
</ul>
|
||||
<p>The error functions implement the following interface, e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">mae</span><span class="p">(</span><span class="n">true_prevs</span><span class="p">,</span> <span class="n">prevs_hat</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>in which the first argument is a ndarray containing the true
|
||||
prevalences, and the second argument is another ndarray with
|
||||
the estimations produced by some method.</p>
|
||||
<p>Some error functions, e.g., <em>mrae</em>, <em>mkld</em>, and <em>mnkld</em>, are
|
||||
smoothed for numerical stability. In those cases, there is a
|
||||
third argument, e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">mrae</span><span class="p">(</span><span class="n">true_prevs</span><span class="p">,</span> <span class="n">prevs_hat</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> <span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>indicating the value for the smoothing parameter epsilon.
|
||||
Traditionally, this value is set to 1/(2T) in past literature,
|
||||
with T the sampling size. One could either pass this value
|
||||
to the function each time, or to set a QuaPy’s environment
|
||||
variable <em>SAMPLE_SIZE</em> once, and omit this argument
|
||||
thereafter (recommended);
|
||||
e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'SAMPLE_SIZE'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">100</span> <span class="c1"># once for all</span>
|
||||
<span class="n">true_prev</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">([</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">,</span> <span class="mf">0.2</span><span class="p">])</span> <span class="c1"># let's assume 3 classes</span>
|
||||
<span class="n">estim_prev</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">([</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">])</span>
|
||||
<span class="n">error</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">error</span><span class="o">.</span><span class="n">mrae</span><span class="p">(</span><span class="n">true_prev</span><span class="p">,</span> <span class="n">estim_prev</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'mrae(</span><span class="si">{</span><span class="n">true_prev</span><span class="si">}</span><span class="s1">, </span><span class="si">{</span><span class="n">estim_prev</span><span class="si">}</span><span class="s1">) = </span><span class="si">{</span><span class="n">error</span><span class="si">:</span><span class="s1">.3f</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>will print:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">mrae</span><span class="p">([</span><span class="mf">0.500</span><span class="p">,</span> <span class="mf">0.300</span><span class="p">,</span> <span class="mf">0.200</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.100</span><span class="p">,</span> <span class="mf">0.300</span><span class="p">,</span> <span class="mf">0.600</span><span class="p">])</span> <span class="o">=</span> <span class="mf">0.914</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Finally, it is possible to instantiate QuaPy’s quantification
|
||||
error functions from strings using, e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">error_function</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">error</span><span class="o">.</span><span class="n">from_name</span><span class="p">(</span><span class="s1">'mse'</span><span class="p">)</span>
|
||||
<span class="n">error</span> <span class="o">=</span> <span class="n">error_function</span><span class="p">(</span><span class="n">true_prev</span><span class="p">,</span> <span class="n">estim_prev</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="evaluation-protocols">
|
||||
<h2>Evaluation Protocols<a class="headerlink" href="#evaluation-protocols" title="Permalink to this heading">¶</a></h2>
|
||||
<p>An <em>evaluation protocol</em> is an evaluation procedure that uses
|
||||
one specific <em>sample generation procotol</em> to genereate many
|
||||
samples, typically characterized by widely varying amounts of
|
||||
<em>shift</em> with respect to the original distribution, that are then
|
||||
used to evaluate the performance of a (trained) quantifier.
|
||||
These protocols are explained in more detail in a dedicated <a class="reference internal" href="Protocols.html"><span class="doc std std-doc">entry
|
||||
in the wiki</span></a>. For the moment being, let us assume we already have
|
||||
chosen and instantiated one specific such protocol, that we here
|
||||
simply call <em>prot</em>. Let also assume our model is called
|
||||
<em>quantifier</em> and that our evaluatio measure of choice is
|
||||
<em>mae</em>. The evaluation comes down to:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">mae</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">quantifier</span><span class="p">,</span> <span class="n">protocol</span><span class="o">=</span><span class="n">prot</span><span class="p">,</span> <span class="n">error_metric</span><span class="o">=</span><span class="s1">'mae'</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'MAE = </span><span class="si">{</span><span class="n">mae</span><span class="si">:</span><span class="s1">.4f</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>It is often desirable to evaluate our system using more than one
|
||||
single evaluatio measure. In this case, it is convenient to generate
|
||||
a <em>report</em>. A report in QuaPy is a dataframe accounting for all the
|
||||
true prevalence values with their corresponding prevalence values
|
||||
as estimated by the quantifier, along with the error each has given
|
||||
rise.</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">report</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">evaluation_report</span><span class="p">(</span><span class="n">quantifier</span><span class="p">,</span> <span class="n">protocol</span><span class="o">=</span><span class="n">prot</span><span class="p">,</span> <span class="n">error_metrics</span><span class="o">=</span><span class="p">[</span><span class="s1">'mae'</span><span class="p">,</span> <span class="s1">'mrae'</span><span class="p">,</span> <span class="s1">'mkld'</span><span class="p">])</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>From a pandas’ dataframe, it is straightforward to visualize all the results,
|
||||
and compute the averaged values, e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">pd</span><span class="o">.</span><span class="n">set_option</span><span class="p">(</span><span class="s1">'display.expand_frame_repr'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
|
||||
<span class="n">report</span><span class="p">[</span><span class="s1">'estim-prev'</span><span class="p">]</span> <span class="o">=</span> <span class="n">report</span><span class="p">[</span><span class="s1">'estim-prev'</span><span class="p">]</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">strprev</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="n">report</span><span class="p">)</span>
|
||||
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s1">'Averaged values:'</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="n">report</span><span class="o">.</span><span class="n">mean</span><span class="p">())</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>This will produce an output like:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span> <span class="n">true</span><span class="o">-</span><span class="n">prev</span> <span class="n">estim</span><span class="o">-</span><span class="n">prev</span> <span class="n">mae</span> <span class="n">mrae</span> <span class="n">mkld</span>
|
||||
<span class="mi">0</span> <span class="p">[</span><span class="mf">0.308</span><span class="p">,</span> <span class="mf">0.692</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.314</span><span class="p">,</span> <span class="mf">0.686</span><span class="p">]</span> <span class="mf">0.005649</span> <span class="mf">0.013182</span> <span class="mf">0.000074</span>
|
||||
<span class="mi">1</span> <span class="p">[</span><span class="mf">0.896</span><span class="p">,</span> <span class="mf">0.104</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.909</span><span class="p">,</span> <span class="mf">0.091</span><span class="p">]</span> <span class="mf">0.013145</span> <span class="mf">0.069323</span> <span class="mf">0.000985</span>
|
||||
<span class="mi">2</span> <span class="p">[</span><span class="mf">0.848</span><span class="p">,</span> <span class="mf">0.152</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.809</span><span class="p">,</span> <span class="mf">0.191</span><span class="p">]</span> <span class="mf">0.039063</span> <span class="mf">0.149806</span> <span class="mf">0.005175</span>
|
||||
<span class="mi">3</span> <span class="p">[</span><span class="mf">0.016</span><span class="p">,</span> <span class="mf">0.984</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.033</span><span class="p">,</span> <span class="mf">0.967</span><span class="p">]</span> <span class="mf">0.017236</span> <span class="mf">0.487529</span> <span class="mf">0.005298</span>
|
||||
<span class="mi">4</span> <span class="p">[</span><span class="mf">0.728</span><span class="p">,</span> <span class="mf">0.272</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.751</span><span class="p">,</span> <span class="mf">0.249</span><span class="p">]</span> <span class="mf">0.022769</span> <span class="mf">0.057146</span> <span class="mf">0.001350</span>
|
||||
<span class="o">...</span> <span class="o">...</span> <span class="o">...</span> <span class="o">...</span> <span class="o">...</span> <span class="o">...</span>
|
||||
<span class="mi">4995</span> <span class="p">[</span><span class="mf">0.72</span><span class="p">,</span> <span class="mf">0.28</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.698</span><span class="p">,</span> <span class="mf">0.302</span><span class="p">]</span> <span class="mf">0.021752</span> <span class="mf">0.053631</span> <span class="mf">0.001133</span>
|
||||
<span class="mi">4996</span> <span class="p">[</span><span class="mf">0.868</span><span class="p">,</span> <span class="mf">0.132</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.888</span><span class="p">,</span> <span class="mf">0.112</span><span class="p">]</span> <span class="mf">0.020490</span> <span class="mf">0.088230</span> <span class="mf">0.001985</span>
|
||||
<span class="mi">4997</span> <span class="p">[</span><span class="mf">0.292</span><span class="p">,</span> <span class="mf">0.708</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.298</span><span class="p">,</span> <span class="mf">0.702</span><span class="p">]</span> <span class="mf">0.006149</span> <span class="mf">0.014788</span> <span class="mf">0.000090</span>
|
||||
<span class="mi">4998</span> <span class="p">[</span><span class="mf">0.24</span><span class="p">,</span> <span class="mf">0.76</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.220</span><span class="p">,</span> <span class="mf">0.780</span><span class="p">]</span> <span class="mf">0.019950</span> <span class="mf">0.054309</span> <span class="mf">0.001127</span>
|
||||
<span class="mi">4999</span> <span class="p">[</span><span class="mf">0.948</span><span class="p">,</span> <span class="mf">0.052</span><span class="p">]</span> <span class="p">[</span><span class="mf">0.965</span><span class="p">,</span> <span class="mf">0.035</span><span class="p">]</span> <span class="mf">0.016941</span> <span class="mf">0.165776</span> <span class="mf">0.003538</span>
|
||||
|
||||
<span class="p">[</span><span class="mi">5000</span> <span class="n">rows</span> <span class="n">x</span> <span class="mi">5</span> <span class="n">columns</span><span class="p">]</span>
|
||||
<span class="n">Averaged</span> <span class="n">values</span><span class="p">:</span>
|
||||
<span class="n">mae</span> <span class="mf">0.023588</span>
|
||||
<span class="n">mrae</span> <span class="mf">0.108779</span>
|
||||
<span class="n">mkld</span> <span class="mf">0.003631</span>
|
||||
<span class="n">dtype</span><span class="p">:</span> <span class="n">float64</span>
|
||||
|
||||
<span class="n">Process</span> <span class="n">finished</span> <span class="k">with</span> <span class="n">exit</span> <span class="n">code</span> <span class="mi">0</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Alternatively, we can simply generate all the predictions by:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">prediction</span><span class="p">(</span><span class="n">quantifier</span><span class="p">,</span> <span class="n">protocol</span><span class="o">=</span><span class="n">prot</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>All the evaluation functions implement specific optimizations for speeding-up
|
||||
the evaluation of aggregative quantifiers (i.e., of instances of <em>AggregativeQuantifier</em>).
|
||||
The optimization comes down to generating classification predictions (either crisp or soft)
|
||||
only once for the entire test set, and then applying the sampling procedure to the
|
||||
predictions, instead of generating samples of instances and then computing the
|
||||
classification predictions every time. This is only possible when the protocol
|
||||
is an instance of <em>OnLabelledCollectionProtocol</em>. The optimization is only
|
||||
carried out when the number of classification predictions thus generated would be
|
||||
smaller than the number of predictions required for the entire protocol; e.g.,
|
||||
if the original dataset contains 1M instances, but the protocol is such that it would
|
||||
at most generate 20 samples of 100 instances, then it would be preferable to postpone the
|
||||
classification for each sample. This behaviour is indicated by setting
|
||||
<em>aggr_speedup=”auto”</em>. Conversely, when indicating <em>aggr_speedup=”force”</em> QuaPy will
|
||||
precompute all the predictions irrespectively of the number of instances and number of samples.
|
||||
Finally, this can be deactivated by setting <em>aggr_speedup=False</em>. Note that this optimization
|
||||
is not only applied for the final evaluation, but also for the internal evaluations carried
|
||||
out during <em>model selection</em>. Since these are typically many, the heuristic can help reduce the
|
||||
execution time a lot.</p>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Evaluation</a><ul>
|
||||
<li><a class="reference internal" href="#error-measures">Error Measures</a></li>
|
||||
<li><a class="reference internal" href="#evaluation-protocols">Evaluation Protocols</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="Datasets.html"
|
||||
title="previous chapter">Datasets</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="Protocols.html"
|
||||
title="next chapter">Protocols</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/Evaluation.md.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Protocols.html" title="Protocols"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Datasets.html" title="Datasets"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Evaluation</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,178 +0,0 @@
|
|||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Installation — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Datasets" href="Datasets.html" />
|
||||
<link rel="prev" title="Welcome to QuaPy’s documentation!" href="index.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Datasets.html" title="Datasets"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="index.html" title="Welcome to QuaPy’s documentation!"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Installation</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="installation">
|
||||
<h1>Installation<a class="headerlink" href="#installation" title="Permalink to this heading">¶</a></h1>
|
||||
<p>QuaPy can be easily installed via <cite>pip</cite></p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pip</span> <span class="n">install</span> <span class="n">quapy</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>See <a class="reference external" href="https://pypi.org/project/QuaPy/">pip page</a> for older versions.</p>
|
||||
<section id="requirements">
|
||||
<h2>Requirements<a class="headerlink" href="#requirements" title="Permalink to this heading">¶</a></h2>
|
||||
<ul class="simple">
|
||||
<li><p>scikit-learn, numpy, scipy</p></li>
|
||||
<li><p>pytorch (for QuaNet)</p></li>
|
||||
<li><p>svmperf patched for quantification (see below)</p></li>
|
||||
<li><p>joblib</p></li>
|
||||
<li><p>tqdm</p></li>
|
||||
<li><p>pandas, xlrd</p></li>
|
||||
<li><p>matplotlib</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="svm-perf-with-quantification-oriented-losses">
|
||||
<h2>SVM-perf with quantification-oriented losses<a class="headerlink" href="#svm-perf-with-quantification-oriented-losses" title="Permalink to this heading">¶</a></h2>
|
||||
<p>In order to run experiments involving SVM(Q), SVM(KLD), SVM(NKLD),
|
||||
SVM(AE), or SVM(RAE), you have to first download the
|
||||
<a class="reference external" href="http://www.cs.cornell.edu/people/tj/svm_light/svm_perf.html">svmperf</a>
|
||||
package, apply the patch
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/blob/master/svm-perf-quantification-ext.patch">svm-perf-quantification-ext.patch</a>,
|
||||
and compile the sources.
|
||||
The script
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/blob/master/prepare_svmperf.sh">prepare_svmperf.sh</a>,
|
||||
does all the job. Simply run:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="o">./</span><span class="n">prepare_svmperf</span><span class="o">.</span><span class="n">sh</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The resulting directory <cite>./svm_perf_quantification</cite> contains the
|
||||
patched version of <cite>svmperf</cite> with quantification-oriented losses.</p>
|
||||
<p>The
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/blob/master/svm-perf-quantification-ext.patch">svm-perf-quantification-ext.patch</a>
|
||||
is an extension of the patch made available by
|
||||
<a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/2700406?casa_token=8D2fHsGCVn0AAAAA:ZfThYOvrzWxMGfZYlQW_y8Cagg-o_l6X_PcF09mdETQ4Tu7jK98mxFbGSXp9ZSO14JkUIYuDGFG0">Esuli et al. 2015</a>
|
||||
that allows SVMperf to optimize for
|
||||
the <cite>Q</cite> measure as proposed by
|
||||
<a class="reference external" href="https://www.sciencedirect.com/science/article/abs/pii/S003132031400291X">Barranquero et al. 2015</a>
|
||||
and for the <cite>KLD</cite> and <cite>NKLD</cite> as proposed by
|
||||
<a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/2700406?casa_token=8D2fHsGCVn0AAAAA:ZfThYOvrzWxMGfZYlQW_y8Cagg-o_l6X_PcF09mdETQ4Tu7jK98mxFbGSXp9ZSO14JkUIYuDGFG0">Esuli et al. 2015</a>
|
||||
for quantification.
|
||||
This patch extends the former by also allowing SVMperf to optimize for
|
||||
<cite>AE</cite> and <cite>RAE</cite>.</p>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Installation</a><ul>
|
||||
<li><a class="reference internal" href="#requirements">Requirements</a></li>
|
||||
<li><a class="reference internal" href="#svm-perf-with-quantification-oriented-losses">SVM-perf with quantification-oriented losses</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="index.html"
|
||||
title="previous chapter">Welcome to QuaPy’s documentation!</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="Datasets.html"
|
||||
title="next chapter">Datasets</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/Installation.rst.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Datasets.html" title="Datasets"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="index.html" title="Welcome to QuaPy’s documentation!"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Installation</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,539 +0,0 @@
|
|||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Quantification Methods — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Model Selection" href="Model-Selection.html" />
|
||||
<link rel="prev" title="Protocols" href="Protocols.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Model-Selection.html" title="Model Selection"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Protocols.html" title="Protocols"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Quantification Methods</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="quantification-methods">
|
||||
<h1>Quantification Methods<a class="headerlink" href="#quantification-methods" title="Permalink to this heading">¶</a></h1>
|
||||
<p>Quantification methods can be categorized as belonging to
|
||||
<em>aggregative</em> and <em>non-aggregative</em> groups.
|
||||
Most methods included in QuaPy at the moment are of type <em>aggregative</em>
|
||||
(though we plan to add many more methods in the near future), i.e.,
|
||||
are methods characterized by the fact that
|
||||
quantification is performed as an aggregation function of the individual
|
||||
products of classification.</p>
|
||||
<p>Any quantifier in QuaPy shoud extend the class <em>BaseQuantifier</em>,
|
||||
and implement some abstract methods:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span> <span class="nd">@abstractmethod</span>
|
||||
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">:</span> <span class="n">LabelledCollection</span><span class="p">):</span> <span class="o">...</span>
|
||||
|
||||
<span class="nd">@abstractmethod</span>
|
||||
<span class="k">def</span> <span class="nf">quantify</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">instances</span><span class="p">):</span> <span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The meaning of those functions should be familiar to those
|
||||
used to work with scikit-learn since the class structure of QuaPy
|
||||
is directly inspired by scikit-learn’s <em>Estimators</em>. Functions
|
||||
<em>fit</em> and <em>quantify</em> are used to train the model and to provide
|
||||
class estimations (the reason why
|
||||
scikit-learn’ structure has not been adopted <em>as is</em> in QuaPy responds to
|
||||
the fact that scikit-learn’s <em>predict</em> function is expected to return
|
||||
one output for each input element –e.g., a predicted label for each
|
||||
instance in a sample– while in quantification the output for a sample
|
||||
is one single array of class prevalences).
|
||||
Quantifiers also extend from scikit-learn’s <code class="docutils literal notranslate"><span class="pre">BaseEstimator</span></code>, in order
|
||||
to simplify the use of <em>set_params</em> and <em>get_params</em> used in
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Model-Selection">model selector</a>.</p>
|
||||
<section id="aggregative-methods">
|
||||
<h2>Aggregative Methods<a class="headerlink" href="#aggregative-methods" title="Permalink to this heading">¶</a></h2>
|
||||
<p>All quantification methods are implemented as part of the
|
||||
<em>qp.method</em> package. In particular, <em>aggregative</em> methods are defined in
|
||||
<em>qp.method.aggregative</em>, and extend <em>AggregativeQuantifier(BaseQuantifier)</em>.
|
||||
The methods that any <em>aggregative</em> quantifier must implement are:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span> <span class="nd">@abstractmethod</span>
|
||||
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">:</span> <span class="n">LabelledCollection</span><span class="p">,</span> <span class="n">fit_learner</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> <span class="o">...</span>
|
||||
|
||||
<span class="nd">@abstractmethod</span>
|
||||
<span class="k">def</span> <span class="nf">aggregate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">classif_predictions</span><span class="p">:</span><span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span> <span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>since, as mentioned before, aggregative methods base their prediction on the
|
||||
individual predictions of a classifier. Indeed, a default implementation
|
||||
of <em>BaseQuantifier.quantify</em> is already provided, which looks like:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span> <span class="k">def</span> <span class="nf">quantify</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">instances</span><span class="p">):</span>
|
||||
<span class="n">classif_predictions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">classify</span><span class="p">(</span><span class="n">instances</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">aggregate</span><span class="p">(</span><span class="n">classif_predictions</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Aggregative quantifiers are expected to maintain a classifier (which is
|
||||
accessed through the <em>@property</em> <em>classifier</em>). This classifier is
|
||||
given as input to the quantifier, and can be already fit
|
||||
on external data (in which case, the <em>fit_learner</em> argument should
|
||||
be set to False), or be fit by the quantifier’s fit (default).</p>
|
||||
<p>Another class of <em>aggregative</em> methods are the <em>probabilistic</em>
|
||||
aggregative methods, that should inherit from the abstract class
|
||||
<em>AggregativeProbabilisticQuantifier(AggregativeQuantifier)</em>.
|
||||
The particularity of <em>probabilistic</em> aggregative methods (w.r.t.
|
||||
non-probabilistic ones), is that the default quantifier is defined
|
||||
in terms of the posterior probabilities returned by a probabilistic
|
||||
classifier, and not by the crisp decisions of a hard classifier.
|
||||
In any case, the interface <em>classify(instances)</em> remains unchanged.</p>
|
||||
<p>One advantage of <em>aggregative</em> methods (either probabilistic or not)
|
||||
is that the evaluation according to any sampling procedure (e.g.,
|
||||
the <a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Evaluation">artificial sampling protocol</a>)
|
||||
can be achieved very efficiently, since the entire set can be pre-classified
|
||||
once, and the quantification estimations for different samples can directly
|
||||
reuse these predictions, without requiring to classify each element every time.
|
||||
QuaPy leverages this property to speed-up any procedure having to do with
|
||||
quantification over samples, as is customarily done in model selection or
|
||||
in evaluation.</p>
|
||||
<section id="the-classify-count-variants">
|
||||
<h3>The Classify & Count variants<a class="headerlink" href="#the-classify-count-variants" title="Permalink to this heading">¶</a></h3>
|
||||
<p>QuaPy implements the four CC variants, i.e.:</p>
|
||||
<ul class="simple">
|
||||
<li><p><em>CC</em> (Classify & Count), the simplest aggregative quantifier; one that
|
||||
simply relies on the label predictions of a classifier to deliver class estimates.</p></li>
|
||||
<li><p><em>ACC</em> (Adjusted Classify & Count), the adjusted variant of CC.</p></li>
|
||||
<li><p><em>PCC</em> (Probabilistic Classify & Count), the probabilistic variant of CC that
|
||||
relies on the soft estimations (or posterior probabilities) returned by a (probabilistic) classifier.</p></li>
|
||||
<li><p><em>PACC</em> (Probabilistic Adjusted Classify & Count), the adjusted variant of PCC.</p></li>
|
||||
</ul>
|
||||
<p>The following code serves as a complete example using CC equipped
|
||||
with a SVM as the classifier:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">import</span> <span class="nn">quapy.functional</span> <span class="k">as</span> <span class="nn">F</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.svm</span> <span class="kn">import</span> <span class="n">LinearSVC</span>
|
||||
|
||||
<span class="n">training</span><span class="p">,</span> <span class="n">test</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_twitter</span><span class="p">(</span><span class="s1">'hcr'</span><span class="p">,</span> <span class="n">pickle</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span><span class="o">.</span><span class="n">train_test</span>
|
||||
|
||||
<span class="c1"># instantiate a classifier learner, in this case a SVM</span>
|
||||
<span class="n">svm</span> <span class="o">=</span> <span class="n">LinearSVC</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># instantiate a Classify & Count with the SVM</span>
|
||||
<span class="c1"># (an alias is available in qp.method.aggregative.ClassifyAndCount)</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">CC</span><span class="p">(</span><span class="n">svm</span><span class="p">)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The same code could be used to instantiate an ACC, by simply replacing
|
||||
the instantiation of the model with:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">ACC</span><span class="p">(</span><span class="n">svm</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Note that the adjusted variants (ACC and PACC) need to estimate
|
||||
some parameters for performing the adjustment (e.g., the
|
||||
<em>true positive rate</em> and the <em>false positive rate</em> in case of
|
||||
binary classification) that are estimated on a validation split
|
||||
of the labelled set. In this case, the <strong>init</strong> method of
|
||||
ACC defines an additional parameter, <em>val_split</em> which, by
|
||||
default, is set to 0.4 and so, the 40% of the labelled data
|
||||
will be used for estimating the parameters for adjusting the
|
||||
predictions. This parameters can also be set with an integer,
|
||||
indicating that the parameters should be estimated by means of
|
||||
<em>k</em>-fold cross-validation, for which the integer indicates the
|
||||
number <em>k</em> of folds. Finally, <em>val_split</em> can be set to a
|
||||
specific held-out validation set (i.e., an instance of <em>LabelledCollection</em>).</p>
|
||||
<p>The specification of <em>val_split</em> can be
|
||||
postponed to the invokation of the fit method (if <em>val_split</em> was also
|
||||
set in the constructor, the one specified at fit time would prevail),
|
||||
e.g.:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">ACC</span><span class="p">(</span><span class="n">svm</span><span class="p">)</span>
|
||||
<span class="c1"># perform 5-fold cross validation for estimating ACC's parameters</span>
|
||||
<span class="c1"># (overrides the default val_split=0.4 in the constructor)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">training</span><span class="p">,</span> <span class="n">val_split</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The following code illustrates the case in which PCC is used:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">PCC</span><span class="p">(</span><span class="n">svm</span><span class="p">)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s1">'classifier:'</span><span class="p">,</span> <span class="n">model</span><span class="o">.</span><span class="n">classifier</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>In this case, QuaPy will print:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">The</span> <span class="n">learner</span> <span class="n">LinearSVC</span> <span class="n">does</span> <span class="ow">not</span> <span class="n">seem</span> <span class="n">to</span> <span class="n">be</span> <span class="n">probabilistic</span><span class="o">.</span> <span class="n">The</span> <span class="n">learner</span> <span class="n">will</span> <span class="n">be</span> <span class="n">calibrated</span><span class="o">.</span>
|
||||
<span class="n">classifier</span><span class="p">:</span> <span class="n">CalibratedClassifierCV</span><span class="p">(</span><span class="n">base_estimator</span><span class="o">=</span><span class="n">LinearSVC</span><span class="p">(),</span> <span class="n">cv</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The first output indicates that the learner (<em>LinearSVC</em> in this case)
|
||||
is not a probabilistic classifier (i.e., it does not implement the
|
||||
<em>predict_proba</em> method) and so, the classifier will be converted to
|
||||
a probabilistic one through <a class="reference external" href="https://scikit-learn.org/stable/modules/calibration.html">calibration</a>.
|
||||
As a result, the classifier that is printed in the second line points
|
||||
to a <em>CalibratedClassifier</em> instance. Note that calibration can only
|
||||
be applied to hard classifiers when <em>fit_learner=True</em>; an exception
|
||||
will be raised otherwise.</p>
|
||||
<p>Lastly, everything we said aboud ACC and PCC
|
||||
applies to PACC as well.</p>
|
||||
</section>
|
||||
<section id="expectation-maximization-emq">
|
||||
<h3>Expectation Maximization (EMQ)<a class="headerlink" href="#expectation-maximization-emq" title="Permalink to this heading">¶</a></h3>
|
||||
<p>The Expectation Maximization Quantifier (EMQ), also known as
|
||||
the SLD, is available at <em>qp.method.aggregative.EMQ</em> or via the
|
||||
alias <em>qp.method.aggregative.ExpectationMaximizationQuantifier</em>.
|
||||
The method is described in:</p>
|
||||
<p><em>Saerens, M., Latinne, P., and Decaestecker, C. (2002). Adjusting the outputs of a classifier
|
||||
to new a priori probabilities: A simple procedure. Neural Computation, 14(1):21–41.</em></p>
|
||||
<p>EMQ works with a probabilistic classifier (if the classifier
|
||||
given as input is a hard one, a calibration will be attempted).
|
||||
Although this method was originally proposed for improving the
|
||||
posterior probabilities of a probabilistic classifier, and not
|
||||
for improving the estimation of prior probabilities, EMQ ranks
|
||||
almost always among the most effective quantifiers in the
|
||||
experiments we have carried out.</p>
|
||||
<p>An example of use can be found below:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
|
||||
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_twitter</span><span class="p">(</span><span class="s1">'hcr'</span><span class="p">,</span> <span class="n">pickle</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">EMQ</span><span class="p">(</span><span class="n">LogisticRegression</span><span class="p">())</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p><em>New in v0.1.7</em>: EMQ now accepts two new parameters in the construction method, namely
|
||||
<em>exact_train_prev</em> which allows to use the true training prevalence as the departing
|
||||
prevalence estimation (default behaviour), or instead an approximation of it as
|
||||
suggested by <a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. (2020)</a>
|
||||
(by setting <em>exact_train_prev=False</em>).
|
||||
The other parameter is <em>recalib</em> which allows to indicate a calibration method, among those
|
||||
proposed by <a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. (2020)</a>,
|
||||
including the Bias-Corrected Temperature Scaling, Vector Scaling, etc.
|
||||
See the API documentation for further details.</p>
|
||||
</section>
|
||||
<section id="hellinger-distance-y-hdy">
|
||||
<h3>Hellinger Distance y (HDy)<a class="headerlink" href="#hellinger-distance-y-hdy" title="Permalink to this heading">¶</a></h3>
|
||||
<p>Implementation of the method based on the Hellinger Distance y (HDy) proposed by
|
||||
<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S0020025512004069">González-Castro, V., Alaiz-Rodrı́guez, R., and Alegre, E. (2013). Class distribution
|
||||
estimation based on the Hellinger distance. Information Sciences, 218:146–164.</a></p>
|
||||
<p>It is implemented in <em>qp.method.aggregative.HDy</em> (also accessible
|
||||
through the allias <em>qp.method.aggregative.HellingerDistanceY</em>).
|
||||
This method works with a probabilistic classifier (hard classifiers
|
||||
can be used as well and will be calibrated) and requires a validation
|
||||
set to estimate parameter for the mixture model. Just like
|
||||
ACC and PACC, this quantifier receives a <em>val_split</em> argument
|
||||
in the constructor (or in the fit method, in which case the previous
|
||||
value is overridden) that can either be a float indicating the proportion
|
||||
of training data to be taken as the validation set (in a random
|
||||
stratified split), or a validation set (i.e., an instance of
|
||||
<em>LabelledCollection</em>) itself.</p>
|
||||
<p>HDy was proposed as a binary classifier and the implementation
|
||||
provided in QuaPy accepts only binary datasets.</p>
|
||||
<p>The following code shows an example of use:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
|
||||
|
||||
<span class="c1"># load a binary dataset</span>
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'hp'</span><span class="p">,</span> <span class="n">pickle</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">preprocessing</span><span class="o">.</span><span class="n">text2tfidf</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">HDy</span><span class="p">(</span><span class="n">LogisticRegression</span><span class="p">())</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p><em>New in v0.1.7:</em> QuaPy now provides an implementation of the generalized
|
||||
“Distribution Matching” approaches for multiclass, inspired by the framework
|
||||
of <a class="reference external" href="https://arxiv.org/abs/1606.00868">Firat (2016)</a>. One can instantiate
|
||||
a variant of HDy for multiclass quantification as follows:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">mutliclassHDy</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">DistributionMatching</span><span class="p">(</span><span class="n">classifier</span><span class="o">=</span><span class="n">LogisticRegression</span><span class="p">(),</span> <span class="n">divergence</span><span class="o">=</span><span class="s1">'HD'</span><span class="p">,</span> <span class="n">cdf</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p><em>New in v0.1.7:</em> QuaPy now provides an implementation of the “DyS”
|
||||
framework proposed by <a class="reference external" href="https://ojs.aaai.org/index.php/AAAI/article/view/4376">Maletzke et al (2020)</a>
|
||||
and the “SMM” method proposed by <a class="reference external" href="https://ieeexplore.ieee.org/document/9260028">Hassan et al (2019)</a>
|
||||
(thanks to <em>Pablo González</em> for the contributions!)</p>
|
||||
</section>
|
||||
<section id="threshold-optimization-methods">
|
||||
<h3>Threshold Optimization methods<a class="headerlink" href="#threshold-optimization-methods" title="Permalink to this heading">¶</a></h3>
|
||||
<p><em>New in v0.1.7:</em> QuaPy now implements Forman’s threshold optimization methods;
|
||||
see, e.g., <a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/1150402.1150423">(Forman 2006)</a>
|
||||
and <a class="reference external" href="https://link.springer.com/article/10.1007/s10618-008-0097-y">(Forman 2008)</a>.
|
||||
These include: T50, MAX, X, Median Sweep (MS), and its variant MS2.</p>
|
||||
</section>
|
||||
<section id="explicit-loss-minimization">
|
||||
<h3>Explicit Loss Minimization<a class="headerlink" href="#explicit-loss-minimization" title="Permalink to this heading">¶</a></h3>
|
||||
<p>The Explicit Loss Minimization (ELM) represent a family of methods
|
||||
based on structured output learning, i.e., quantifiers relying on
|
||||
classifiers that have been optimized targeting a
|
||||
quantification-oriented evaluation measure.
|
||||
The original methods are implemented in QuaPy as classify & count (CC)
|
||||
quantifiers that use Joachim’s <a class="reference external" href="https://www.cs.cornell.edu/people/tj/svm_light/svm_perf.html">SVMperf</a>
|
||||
as the underlying classifier, properly set to optimize for the desired loss.</p>
|
||||
<p>In QuaPy, this can be more achieved by calling the functions:</p>
|
||||
<ul class="simple">
|
||||
<li><p><em>newSVMQ</em>: returns the quantification method called SVM(Q) that optimizes for the metric <em>Q</em> defined
|
||||
in <a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S003132031400291X"><em>Barranquero, J., Díez, J., and del Coz, J. J. (2015). Quantification-oriented learning based
|
||||
on reliable classifiers. Pattern Recognition, 48(2):591–604.</em></a></p></li>
|
||||
<li><p><em>newSVMKLD</em> and <em>newSVMNKLD</em>: returns the quantification method called SVM(KLD) and SVM(nKLD), standing for
|
||||
Kullback-Leibler Divergence and Normalized Kullback-Leibler Divergence, as proposed in <a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/2700406"><em>Esuli, A. and Sebastiani, F. (2015).
|
||||
Optimizing text quantifiers for multivariate loss functions.
|
||||
ACM Transactions on Knowledge Discovery and Data, 9(4):Article 27.</em></a></p></li>
|
||||
<li><p><em>newSVMAE</em> and <em>newSVMRAE</em>: returns a quantification method called SVM(AE) and SVM(RAE) that optimizes for the (Mean) Absolute Error and for the
|
||||
(Mean) Relative Absolute Error, as first used by
|
||||
<a class="reference external" href="https://arxiv.org/abs/2011.02552"><em>Moreo, A. and Sebastiani, F. (2021). Tweet sentiment quantification: An experimental re-evaluation. PLOS ONE 17 (9), 1-23.</em></a></p></li>
|
||||
</ul>
|
||||
<p>the last two methods (SVM(AE) and SVM(RAE)) have been implemented in
|
||||
QuaPy in order to make available ELM variants for what nowadays
|
||||
are considered the most well-behaved evaluation metrics in quantification.</p>
|
||||
<p>In order to make these models work, you would need to run the script
|
||||
<em>prepare_svmperf.sh</em> (distributed along with QuaPy) that
|
||||
downloads <em>SVMperf</em>’ source code, applies a patch that
|
||||
implements the quantification oriented losses, and compiles the
|
||||
sources.</p>
|
||||
<p>If you want to add any custom loss, you would need to modify
|
||||
the source code of <em>SVMperf</em> in order to implement it, and
|
||||
assign a valid loss code to it. Then you must re-compile
|
||||
the whole thing and instantiate the quantifier in QuaPy
|
||||
as follows:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># you can either set the path to your custom svm_perf_quantification implementation</span>
|
||||
<span class="c1"># in the environment variable, or as an argument to the constructor of ELM</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'SVMPERF_HOME'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'./path/to/svm_perf_quantification'</span>
|
||||
|
||||
<span class="c1"># assign an alias to your custom loss and the id you have assigned to it</span>
|
||||
<span class="n">svmperf</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">classification</span><span class="o">.</span><span class="n">svmperf</span><span class="o">.</span><span class="n">SVMperf</span>
|
||||
<span class="n">svmperf</span><span class="o">.</span><span class="n">valid_losses</span><span class="p">[</span><span class="s1">'mycustomloss'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">28</span>
|
||||
|
||||
<span class="c1"># instantiate the ELM method indicating the loss</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">ELM</span><span class="p">(</span><span class="n">loss</span><span class="o">=</span><span class="s1">'mycustomloss'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>All ELM are binary quantifiers since they rely on <em>SVMperf</em>, that
|
||||
currently supports only binary classification.
|
||||
ELM variants (any binary quantifier in general) can be extended
|
||||
to operate in single-label scenarios trivially by adopting a
|
||||
“one-vs-all” strategy (as, e.g., in
|
||||
<a class="reference external" href="https://link.springer.com/article/10.1007/s13278-016-0327-z"><em>Gao, W. and Sebastiani, F. (2016). From classification to quantification in tweet sentiment
|
||||
analysis. Social Network Analysis and Mining, 6(19):1–22</em></a>).
|
||||
In QuaPy this is possible by using the <em>OneVsAll</em> class.</p>
|
||||
<p>There are two ways for instantiating this class, <em>OneVsAllGeneric</em> that works for
|
||||
any quantifier, and <em>OneVsAllAggregative</em> that is optimized for aggregative quantifiers.
|
||||
In general, you can simply use the <em>getOneVsAll</em> function and QuaPy will choose
|
||||
the more convenient of the two.</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.method.aggregative</span> <span class="kn">import</span> <span class="n">SVMQ</span>
|
||||
|
||||
<span class="c1"># load a single-label dataset (this one contains 3 classes)</span>
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_twitter</span><span class="p">(</span><span class="s1">'hcr'</span><span class="p">,</span> <span class="n">pickle</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># let qp know where svmperf is</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'SVMPERF_HOME'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'../svm_perf_quantification'</span>
|
||||
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">getOneVsAll</span><span class="p">(</span><span class="n">SVMQ</span><span class="p">(),</span> <span class="n">n_jobs</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># run them on parallel</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Check the examples <em><span class="xref myst">explicit_loss_minimization.py</span></em>
|
||||
and <span class="xref myst">one_vs_all.py</span> for more details.</p>
|
||||
</section>
|
||||
</section>
|
||||
<section id="meta-models">
|
||||
<h2>Meta Models<a class="headerlink" href="#meta-models" title="Permalink to this heading">¶</a></h2>
|
||||
<p>By <em>meta</em> models we mean quantification methods that are defined on top of other
|
||||
quantification methods, and that thus do not squarely belong to the aggregative nor
|
||||
the non-aggregative group (indeed, <em>meta</em> models could use quantifiers from any of those
|
||||
groups).
|
||||
<em>Meta</em> models are implemented in the <em>qp.method.meta</em> module.</p>
|
||||
<section id="ensembles">
|
||||
<h3>Ensembles<a class="headerlink" href="#ensembles" title="Permalink to this heading">¶</a></h3>
|
||||
<p>QuaPy implements (some of) the variants proposed in:</p>
|
||||
<ul class="simple">
|
||||
<li><p><a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253516300628"><em>Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
|
||||
Information Fusion, 34, 87-100.</em></a></p></li>
|
||||
<li><p><a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253517303652"><em>Pérez-Gállego, P., Castano, A., Quevedo, J. R., & del Coz, J. J. (2019).
|
||||
Dynamic ensemble selection for quantification tasks.
|
||||
Information Fusion, 45, 1-15.</em></a></p></li>
|
||||
</ul>
|
||||
<p>The following code shows how to instantiate an Ensemble of 30 <em>Adjusted Classify & Count</em> (ACC)
|
||||
quantifiers operating with a <em>Logistic Regressor</em> (LR) as the base classifier, and using the
|
||||
<em>average</em> as the aggregation policy (see the original article for further details).
|
||||
The last parameter indicates to use all processors for parallelization.</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.method.aggregative</span> <span class="kn">import</span> <span class="n">ACC</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.method.meta</span> <span class="kn">import</span> <span class="n">Ensemble</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
|
||||
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCIDataset</span><span class="p">(</span><span class="s1">'haberman'</span><span class="p">)</span>
|
||||
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">Ensemble</span><span class="p">(</span><span class="n">quantifier</span><span class="o">=</span><span class="n">ACC</span><span class="p">(</span><span class="n">LogisticRegression</span><span class="p">()),</span> <span class="n">size</span><span class="o">=</span><span class="mi">30</span><span class="p">,</span> <span class="n">policy</span><span class="o">=</span><span class="s1">'ave'</span><span class="p">,</span> <span class="n">n_jobs</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Other aggregation policies implemented in QuaPy include:</p>
|
||||
<ul class="simple">
|
||||
<li><p>‘ptr’ for applying a dynamic selection based on the training prevalence of the ensemble’s members</p></li>
|
||||
<li><p>‘ds’ for applying a dynamic selection based on the Hellinger Distance</p></li>
|
||||
<li><p><em>any valid quantification measure</em> (e.g., ‘mse’) for performing a static selection based on
|
||||
the performance estimated for each member of the ensemble in terms of that evaluation metric.</p></li>
|
||||
</ul>
|
||||
<p>When using any of the above options, it is important to set the <em>red_size</em> parameter, which
|
||||
informs of the number of members to retain.</p>
|
||||
<p>Please, check the <a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Model-Selection">model selection</a>
|
||||
wiki if you want to optimize the hyperparameters of ensemble for classification or quantification.</p>
|
||||
</section>
|
||||
<section id="the-quanet-neural-network">
|
||||
<h3>The QuaNet neural network<a class="headerlink" href="#the-quanet-neural-network" title="Permalink to this heading">¶</a></h3>
|
||||
<p>QuaPy offers an implementation of QuaNet, a deep learning model presented in:</p>
|
||||
<p><a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/3269206.3269287"><em>Esuli, A., Moreo, A., & Sebastiani, F. (2018, October).
|
||||
A recurrent neural network for sentiment quantification.
|
||||
In Proceedings of the 27th ACM International Conference on
|
||||
Information and Knowledge Management (pp. 1775-1778).</em></a></p>
|
||||
<p>This model requires <em>torch</em> to be installed.
|
||||
QuaNet also requires a classifier that can provide embedded representations
|
||||
of the inputs.
|
||||
In the original paper, QuaNet was tested using an LSTM as the base classifier.
|
||||
In the following example, we show an instantiation of QuaNet that instead uses CNN as a probabilistic classifier, taking its last layer representation as the document embedding:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.method.meta</span> <span class="kn">import</span> <span class="n">QuaNet</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.classification.neural</span> <span class="kn">import</span> <span class="n">NeuralClassifierTrainer</span><span class="p">,</span> <span class="n">CNNnet</span>
|
||||
|
||||
<span class="c1"># use samples of 100 elements</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'SAMPLE_SIZE'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">100</span>
|
||||
|
||||
<span class="c1"># load the kindle dataset as text, and convert words to numerical indexes</span>
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'kindle'</span><span class="p">,</span> <span class="n">pickle</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">preprocessing</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># the text classifier is a CNN trained by NeuralClassifierTrainer</span>
|
||||
<span class="n">cnn</span> <span class="o">=</span> <span class="n">CNNnet</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">vocabulary_size</span><span class="p">,</span> <span class="n">dataset</span><span class="o">.</span><span class="n">n_classes</span><span class="p">)</span>
|
||||
<span class="n">learner</span> <span class="o">=</span> <span class="n">NeuralClassifierTrainer</span><span class="p">(</span><span class="n">cnn</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">'cuda'</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># train QuaNet</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">QuaNet</span><span class="p">(</span><span class="n">learner</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">'cuda'</span><span class="p">)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
<span class="n">estim_prevalence</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Quantification Methods</a><ul>
|
||||
<li><a class="reference internal" href="#aggregative-methods">Aggregative Methods</a><ul>
|
||||
<li><a class="reference internal" href="#the-classify-count-variants">The Classify & Count variants</a></li>
|
||||
<li><a class="reference internal" href="#expectation-maximization-emq">Expectation Maximization (EMQ)</a></li>
|
||||
<li><a class="reference internal" href="#hellinger-distance-y-hdy">Hellinger Distance y (HDy)</a></li>
|
||||
<li><a class="reference internal" href="#threshold-optimization-methods">Threshold Optimization methods</a></li>
|
||||
<li><a class="reference internal" href="#explicit-loss-minimization">Explicit Loss Minimization</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><a class="reference internal" href="#meta-models">Meta Models</a><ul>
|
||||
<li><a class="reference internal" href="#ensembles">Ensembles</a></li>
|
||||
<li><a class="reference internal" href="#the-quanet-neural-network">The QuaNet neural network</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="Protocols.html"
|
||||
title="previous chapter">Protocols</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="Model-Selection.html"
|
||||
title="next chapter">Model Selection</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/Methods.md.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Model-Selection.html" title="Model Selection"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Protocols.html" title="Protocols"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Quantification Methods</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,268 +0,0 @@
|
|||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Model Selection — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Plotting" href="Plotting.html" />
|
||||
<link rel="prev" title="Quantification Methods" href="Methods.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Plotting.html" title="Plotting"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Methods.html" title="Quantification Methods"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Model Selection</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="model-selection">
|
||||
<h1>Model Selection<a class="headerlink" href="#model-selection" title="Permalink to this heading">¶</a></h1>
|
||||
<p>As a supervised machine learning task, quantification methods
|
||||
can strongly depend on a good choice of model hyper-parameters.
|
||||
The process whereby those hyper-parameters are chosen is
|
||||
typically known as <em>Model Selection</em>, and typically consists of
|
||||
testing different settings and picking the one that performed
|
||||
best in a held-out validation set in terms of any given
|
||||
evaluation measure.</p>
|
||||
<section id="targeting-a-quantification-oriented-loss">
|
||||
<h2>Targeting a Quantification-oriented loss<a class="headerlink" href="#targeting-a-quantification-oriented-loss" title="Permalink to this heading">¶</a></h2>
|
||||
<p>The task being optimized determines the evaluation protocol,
|
||||
i.e., the criteria according to which the performance of
|
||||
any given method for solving is to be assessed.
|
||||
As a task on its own right, quantification should impose
|
||||
its own model selection strategies, i.e., strategies
|
||||
aimed at finding appropriate configurations
|
||||
specifically designed for the task of quantification.</p>
|
||||
<p>Quantification has long been regarded as an add-on of
|
||||
classification, and thus the model selection strategies
|
||||
customarily adopted in classification have simply been
|
||||
applied to quantification (see the next section).
|
||||
It has been argued in <a class="reference external" href="https://link.springer.com/chapter/10.1007/978-3-030-72240-1_6">Moreo, Alejandro, and Fabrizio Sebastiani.
|
||||
Re-Assessing the “Classify and Count” Quantification Method.
|
||||
ECIR 2021: Advances in Information Retrieval pp 75–91.</a>
|
||||
that specific model selection strategies should
|
||||
be adopted for quantification. That is, model selection
|
||||
strategies for quantification should target
|
||||
quantification-oriented losses and be tested in a variety
|
||||
of scenarios exhibiting different degrees of prior
|
||||
probability shift.</p>
|
||||
<p>The class <em>qp.model_selection.GridSearchQ</em> implements a grid-search exploration over the space of
|
||||
hyper-parameter combinations that <a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Evaluation">evaluates</a>
|
||||
each combination of hyper-parameters by means of a given quantification-oriented
|
||||
error metric (e.g., any of the error functions implemented
|
||||
in <em>qp.error</em>) and according to a
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Protocols">sampling generation protocol</a>.</p>
|
||||
<p>The following is an example (also included in the examples folder) of model selection for quantification:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.protocol</span> <span class="kn">import</span> <span class="n">APP</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.method.aggregative</span> <span class="kn">import</span> <span class="n">DistributionMatching</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd">In this example, we show how to perform model selection on a DistributionMatching quantifier.</span>
|
||||
<span class="sd">"""</span>
|
||||
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">DistributionMatching</span><span class="p">(</span><span class="n">LogisticRegression</span><span class="p">())</span>
|
||||
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'SAMPLE_SIZE'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">100</span>
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'N_JOBS'</span><span class="p">]</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> <span class="c1"># explore hyper-parameters in parallel</span>
|
||||
|
||||
<span class="n">training</span><span class="p">,</span> <span class="n">test</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'imdb'</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span><span class="o">.</span><span class="n">train_test</span>
|
||||
|
||||
<span class="c1"># The model will be returned by the fit method of GridSearchQ.</span>
|
||||
<span class="c1"># Every combination of hyper-parameters will be evaluated by confronting the</span>
|
||||
<span class="c1"># quantifier thus configured against a series of samples generated by means</span>
|
||||
<span class="c1"># of a sample generation protocol. For this example, we will use the</span>
|
||||
<span class="c1"># artificial-prevalence protocol (APP), that generates samples with prevalence</span>
|
||||
<span class="c1"># values in the entire range of values from a grid (e.g., [0, 0.1, 0.2, ..., 1]).</span>
|
||||
<span class="c1"># We devote 30% of the dataset for this exploration.</span>
|
||||
<span class="n">training</span><span class="p">,</span> <span class="n">validation</span> <span class="o">=</span> <span class="n">training</span><span class="o">.</span><span class="n">split_stratified</span><span class="p">(</span><span class="n">train_prop</span><span class="o">=</span><span class="mf">0.7</span><span class="p">)</span>
|
||||
<span class="n">protocol</span> <span class="o">=</span> <span class="n">APP</span><span class="p">(</span><span class="n">validation</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># We will explore a classification-dependent hyper-parameter (e.g., the 'C'</span>
|
||||
<span class="c1"># hyper-parameter of LogisticRegression) and a quantification-dependent hyper-parameter</span>
|
||||
<span class="c1"># (e.g., the number of bins in a DistributionMatching quantifier.</span>
|
||||
<span class="c1"># Classifier-dependent hyper-parameters have to be marked with a prefix "classifier__"</span>
|
||||
<span class="c1"># in order to let the quantifier know this hyper-parameter belongs to its underlying</span>
|
||||
<span class="c1"># classifier.</span>
|
||||
<span class="n">param_grid</span> <span class="o">=</span> <span class="p">{</span>
|
||||
<span class="s1">'classifier__C'</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">logspace</span><span class="p">(</span><span class="o">-</span><span class="mi">3</span><span class="p">,</span><span class="mi">3</span><span class="p">,</span><span class="mi">7</span><span class="p">),</span>
|
||||
<span class="s1">'nbins'</span><span class="p">:</span> <span class="p">[</span><span class="mi">8</span><span class="p">,</span> <span class="mi">16</span><span class="p">,</span> <span class="mi">32</span><span class="p">,</span> <span class="mi">64</span><span class="p">],</span>
|
||||
<span class="p">}</span>
|
||||
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">model_selection</span><span class="o">.</span><span class="n">GridSearchQ</span><span class="p">(</span>
|
||||
<span class="n">model</span><span class="o">=</span><span class="n">model</span><span class="p">,</span>
|
||||
<span class="n">param_grid</span><span class="o">=</span><span class="n">param_grid</span><span class="p">,</span>
|
||||
<span class="n">protocol</span><span class="o">=</span><span class="n">protocol</span><span class="p">,</span>
|
||||
<span class="n">error</span><span class="o">=</span><span class="s1">'mae'</span><span class="p">,</span> <span class="c1"># the error to optimize is the MAE (a quantification-oriented loss)</span>
|
||||
<span class="n">refit</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="c1"># retrain on the whole labelled set once done</span>
|
||||
<span class="n">verbose</span><span class="o">=</span><span class="kc">True</span> <span class="c1"># show information as the process goes on</span>
|
||||
<span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">training</span><span class="p">)</span>
|
||||
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'model selection ended: best hyper-parameters=</span><span class="si">{</span><span class="n">model</span><span class="o">.</span><span class="n">best_params_</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">best_model_</span>
|
||||
|
||||
<span class="c1"># evaluation in terms of MAE</span>
|
||||
<span class="c1"># we use the same evaluation protocol (APP) on the test set</span>
|
||||
<span class="n">mae_score</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">protocol</span><span class="o">=</span><span class="n">APP</span><span class="p">(</span><span class="n">test</span><span class="p">),</span> <span class="n">error_metric</span><span class="o">=</span><span class="s1">'mae'</span><span class="p">)</span>
|
||||
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'MAE=</span><span class="si">{</span><span class="n">mae_score</span><span class="si">:</span><span class="s1">.5f</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>In this example, the system outputs:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">starting</span> <span class="n">model</span> <span class="n">selection</span> <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_jobs</span> <span class="o">=-</span><span class="mi">1</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">hyperparams</span><span class="o">=</span><span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">0.01</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">64</span><span class="p">}</span> <span class="n">got</span> <span class="n">mae</span> <span class="n">score</span> <span class="mf">0.04021</span> <span class="p">[</span><span class="n">took</span> <span class="mf">1.1356</span><span class="n">s</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">hyperparams</span><span class="o">=</span><span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">0.01</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">32</span><span class="p">}</span> <span class="n">got</span> <span class="n">mae</span> <span class="n">score</span> <span class="mf">0.04286</span> <span class="p">[</span><span class="n">took</span> <span class="mf">1.2139</span><span class="n">s</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">hyperparams</span><span class="o">=</span><span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">0.01</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">16</span><span class="p">}</span> <span class="n">got</span> <span class="n">mae</span> <span class="n">score</span> <span class="mf">0.04888</span> <span class="p">[</span><span class="n">took</span> <span class="mf">1.2491</span><span class="n">s</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">hyperparams</span><span class="o">=</span><span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">0.001</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">8</span><span class="p">}</span> <span class="n">got</span> <span class="n">mae</span> <span class="n">score</span> <span class="mf">0.05163</span> <span class="p">[</span><span class="n">took</span> <span class="mf">1.5372</span><span class="n">s</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="o">...</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">hyperparams</span><span class="o">=</span><span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">1000.0</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">32</span><span class="p">}</span> <span class="n">got</span> <span class="n">mae</span> <span class="n">score</span> <span class="mf">0.02445</span> <span class="p">[</span><span class="n">took</span> <span class="mf">2.9056</span><span class="n">s</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">optimization</span> <span class="n">finished</span><span class="p">:</span> <span class="n">best</span> <span class="n">params</span> <span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">100.0</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">32</span><span class="p">}</span> <span class="p">(</span><span class="n">score</span><span class="o">=</span><span class="mf">0.02234</span><span class="p">)</span> <span class="p">[</span><span class="n">took</span> <span class="mf">7.3114</span><span class="n">s</span><span class="p">]</span>
|
||||
<span class="p">[</span><span class="n">GridSearchQ</span><span class="p">]:</span> <span class="n">refitting</span> <span class="n">on</span> <span class="n">the</span> <span class="n">whole</span> <span class="n">development</span> <span class="nb">set</span>
|
||||
<span class="n">model</span> <span class="n">selection</span> <span class="n">ended</span><span class="p">:</span> <span class="n">best</span> <span class="n">hyper</span><span class="o">-</span><span class="n">parameters</span><span class="o">=</span><span class="p">{</span><span class="s1">'classifier__C'</span><span class="p">:</span> <span class="mf">100.0</span><span class="p">,</span> <span class="s1">'nbins'</span><span class="p">:</span> <span class="mi">32</span><span class="p">}</span>
|
||||
<span class="n">MAE</span><span class="o">=</span><span class="mf">0.03102</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The parameter <em>val_split</em> can alternatively be used to indicate
|
||||
a validation set (i.e., an instance of <em>LabelledCollection</em>) instead
|
||||
of a proportion. This could be useful if one wants to have control
|
||||
on the specific data split to be used across different model selection
|
||||
experiments.</p>
|
||||
</section>
|
||||
<section id="targeting-a-classification-oriented-loss">
|
||||
<h2>Targeting a Classification-oriented loss<a class="headerlink" href="#targeting-a-classification-oriented-loss" title="Permalink to this heading">¶</a></h2>
|
||||
<p>Optimizing a model for quantification could rather be
|
||||
computationally costly.
|
||||
In aggregative methods, one could alternatively try to optimize
|
||||
the classifier’s hyper-parameters for classification.
|
||||
Although this is theoretically suboptimal, many articles in
|
||||
quantification literature have opted for this strategy.</p>
|
||||
<p>In QuaPy, this is achieved by simply instantiating the
|
||||
classifier learner as a GridSearchCV from scikit-learn.
|
||||
The following code illustrates how to do that:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">learner</span> <span class="o">=</span> <span class="n">GridSearchCV</span><span class="p">(</span>
|
||||
<span class="n">LogisticRegression</span><span class="p">(),</span>
|
||||
<span class="n">param_grid</span><span class="o">=</span><span class="p">{</span><span class="s1">'C'</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">logspace</span><span class="p">(</span><span class="o">-</span><span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">10</span><span class="p">),</span> <span class="s1">'class_weight'</span><span class="p">:</span> <span class="p">[</span><span class="s1">'balanced'</span><span class="p">,</span> <span class="kc">None</span><span class="p">]},</span>
|
||||
<span class="n">cv</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">DistributionMatching</span><span class="p">(</span><span class="n">learner</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>However, this is conceptually flawed, since the model should be
|
||||
optimized for the task at hand (quantification), and not for a surrogate task (classification),
|
||||
i.e., the model should be requested to deliver low quantification errors, rather
|
||||
than low classification errors.</p>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Model Selection</a><ul>
|
||||
<li><a class="reference internal" href="#targeting-a-quantification-oriented-loss">Targeting a Quantification-oriented loss</a></li>
|
||||
<li><a class="reference internal" href="#targeting-a-classification-oriented-loss">Targeting a Classification-oriented loss</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="Methods.html"
|
||||
title="previous chapter">Quantification Methods</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="Plotting.html"
|
||||
title="next chapter">Plotting</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/Model-Selection.md.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Plotting.html" title="Plotting"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Methods.html" title="Quantification Methods"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Model Selection</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,350 +0,0 @@
|
|||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Plotting — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="quapy" href="modules.html" />
|
||||
<link rel="prev" title="Model Selection" href="Model-Selection.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="modules.html" title="quapy"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Model-Selection.html" title="Model Selection"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Plotting</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="plotting">
|
||||
<h1>Plotting<a class="headerlink" href="#plotting" title="Permalink to this heading">¶</a></h1>
|
||||
<p>The module <em>qp.plot</em> implements some basic plotting functions
|
||||
that can help analyse the performance of a quantification method.</p>
|
||||
<p>All plotting functions receive as inputs the outcomes of
|
||||
some experiments and include, for each experiment,
|
||||
the following three main arguments:</p>
|
||||
<ul class="simple">
|
||||
<li><p><em>method_names</em> a list containing the names of the quantification methods</p></li>
|
||||
<li><p><em>true_prevs</em> a list containing matrices of true prevalences</p></li>
|
||||
<li><p><em>estim_prevs</em> a list containing matrices of estimated prevalences
|
||||
(should be of the same shape as the corresponding matrix in <em>true_prevs</em>)</p></li>
|
||||
</ul>
|
||||
<p>Note that a method (as indicated by a name in <em>method_names</em>) can
|
||||
appear more than once. This could occur when various datasets are
|
||||
involved in the experiments. In this case, all experiments for the
|
||||
method will be merged and the plot will represent the method’s
|
||||
performance across various datasets.</p>
|
||||
<p>This is a very simple example of a valid input for the plotting functions:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">method_names</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'classify & count'</span><span class="p">,</span> <span class="s1">'EMQ'</span><span class="p">,</span> <span class="s1">'classify & count'</span><span class="p">]</span>
|
||||
<span class="n">true_prevs</span> <span class="o">=</span> <span class="p">[</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.25</span><span class="p">,</span> <span class="mf">0.75</span><span class="p">]]),</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.25</span><span class="p">,</span> <span class="mf">0.75</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">]]),</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.25</span><span class="p">,</span> <span class="mf">0.75</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">]]),</span>
|
||||
<span class="p">]</span>
|
||||
<span class="n">estim_prevs</span> <span class="o">=</span> <span class="p">[</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="mf">0.45</span><span class="p">,</span> <span class="mf">0.55</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.6</span><span class="p">,</span> <span class="mf">0.4</span><span class="p">]]),</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">0.8</span><span class="p">]]),</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.3</span><span class="p">,</span> <span class="mf">0.7</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">]]),</span>
|
||||
<span class="p">]</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>in which the <em>classify & count</em> has been tested in two datasets and
|
||||
the <em>EMQ</em> method has been tested only in one dataset. For the first
|
||||
experiment, only two (binary) quantifications have been tested,
|
||||
while for the second and third experiments three instances have
|
||||
been tested.</p>
|
||||
<p>In general, we would like to test the performance of the
|
||||
quantification methods across different scenarios showcasing
|
||||
the accuracy of the quantifier in predicting class prevalences
|
||||
for a wide range of prior distributions. This can easily be
|
||||
achieved by means of the
|
||||
<a class="reference external" href="https://github.com/HLT-ISTI/QuaPy/wiki/Protocols">artificial sampling protocol</a>
|
||||
that is implemented in QuaPy.</p>
|
||||
<p>The following code shows how to perform one simple experiment
|
||||
in which the 4 <em>CC-variants</em>, all equipped with a linear SVM, are
|
||||
applied to one binary dataset of reviews about <em>Kindle</em> devices and
|
||||
tested across the entire spectrum of class priors (taking 21 splits
|
||||
of the interval [0,1], i.e., using prevalence steps of 0.05, and
|
||||
generating 100 random samples at each prevalence).</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">protocol</span> <span class="kn">import</span> <span class="n">APP</span>
|
||||
<span class="kn">from</span> <span class="nn">quapy.method.aggregative</span> <span class="kn">import</span> <span class="n">CC</span><span class="p">,</span> <span class="n">ACC</span><span class="p">,</span> <span class="n">PCC</span><span class="p">,</span> <span class="n">PACC</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.svm</span> <span class="kn">import</span> <span class="n">LinearSVC</span>
|
||||
|
||||
<span class="n">qp</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'SAMPLE_SIZE'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">500</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">gen_data</span><span class="p">():</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">base_classifier</span><span class="p">():</span>
|
||||
<span class="k">return</span> <span class="n">LinearSVC</span><span class="p">(</span><span class="n">class_weight</span><span class="o">=</span><span class="s1">'balanced'</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">models</span><span class="p">():</span>
|
||||
<span class="k">yield</span> <span class="s1">'CC'</span><span class="p">,</span> <span class="n">CC</span><span class="p">(</span><span class="n">base_classifier</span><span class="p">())</span>
|
||||
<span class="k">yield</span> <span class="s1">'ACC'</span><span class="p">,</span> <span class="n">ACC</span><span class="p">(</span><span class="n">base_classifier</span><span class="p">())</span>
|
||||
<span class="k">yield</span> <span class="s1">'PCC'</span><span class="p">,</span> <span class="n">PCC</span><span class="p">(</span><span class="n">base_classifier</span><span class="p">())</span>
|
||||
<span class="k">yield</span> <span class="s1">'PACC'</span><span class="p">,</span> <span class="n">PACC</span><span class="p">(</span><span class="n">base_classifier</span><span class="p">())</span>
|
||||
|
||||
<span class="n">train</span><span class="p">,</span> <span class="n">test</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'kindle'</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span><span class="o">.</span><span class="n">train_test</span>
|
||||
|
||||
<span class="n">method_names</span><span class="p">,</span> <span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span><span class="p">,</span> <span class="n">tr_prevs</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[],</span> <span class="p">[],</span> <span class="p">[]</span>
|
||||
|
||||
<span class="k">for</span> <span class="n">method_name</span><span class="p">,</span> <span class="n">model</span> <span class="ow">in</span> <span class="n">models</span><span class="p">():</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">train</span><span class="p">)</span>
|
||||
<span class="n">true_prev</span><span class="p">,</span> <span class="n">estim_prev</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">prediction</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">APP</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">repeats</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">))</span>
|
||||
|
||||
<span class="n">method_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">method_name</span><span class="p">)</span>
|
||||
<span class="n">true_prevs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">true_prev</span><span class="p">)</span>
|
||||
<span class="n">estim_prevs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">estim_prev</span><span class="p">)</span>
|
||||
<span class="n">tr_prevs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">train</span><span class="o">.</span><span class="n">prevalence</span><span class="p">())</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">method_names</span><span class="p">,</span> <span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span><span class="p">,</span> <span class="n">tr_prevs</span>
|
||||
|
||||
<span class="n">method_names</span><span class="p">,</span> <span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span><span class="p">,</span> <span class="n">tr_prevs</span> <span class="o">=</span> <span class="n">gen_data</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>the plots that can be generated are explained below.</p>
|
||||
<section id="diagonal-plot">
|
||||
<h2>Diagonal Plot<a class="headerlink" href="#diagonal-plot" title="Permalink to this heading">¶</a></h2>
|
||||
<p>The <em>diagonal</em> plot shows a very insightful view of the
|
||||
quantifier’s performance. It plots the predicted class
|
||||
prevalence (in the y-axis) against the true class prevalence
|
||||
(in the x-axis). Unfortunately, it is limited to binary quantification,
|
||||
although one can simply generate as many <em>diagonal</em> plots as
|
||||
classes there are by indicating which class should be considered
|
||||
the target of the plot.</p>
|
||||
<p>The following call will produce the plot:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">qp</span><span class="o">.</span><span class="n">plot</span><span class="o">.</span><span class="n">binary_diagonal</span><span class="p">(</span><span class="n">method_names</span><span class="p">,</span> <span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span><span class="p">,</span> <span class="n">train_prev</span><span class="o">=</span><span class="n">tr_prevs</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">savepath</span><span class="o">=</span><span class="s1">'./plots/bin_diag.png'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>the last argument is optional, and indicates the path where to save
|
||||
the plot (the file extension will determine the format – typical extensions
|
||||
are ‘.png’ or ‘.pdf’). If this path is not provided, then the plot
|
||||
will be shown but not saved.
|
||||
The resulting plot should look like:</p>
|
||||
<p><img alt="diagonal plot on Kindle" src="_images/bin_diag.png" /></p>
|
||||
<p>Note that in this case, we are also indicating the training
|
||||
prevalence, which is plotted in the diagonal a as cyan dot.
|
||||
The color bands indicate the standard deviations of the predictions,
|
||||
and can be hidden by setting the argument <em>show_std=False</em> (see
|
||||
the complete list of arguments in the documentation).</p>
|
||||
<p>Finally, note how most quantifiers, and specially the “unadjusted”
|
||||
variants CC and PCC, are strongly biased towards the
|
||||
prevalence seen during training.</p>
|
||||
</section>
|
||||
<section id="quantification-bias">
|
||||
<h2>Quantification bias<a class="headerlink" href="#quantification-bias" title="Permalink to this heading">¶</a></h2>
|
||||
<p>This plot aims at evincing the bias that any quantifier
|
||||
displays with respect to the training prevalences by
|
||||
means of <a class="reference external" href="https://en.wikipedia.org/wiki/Box_plot">box plots</a>.
|
||||
This plot can be generated by:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">qp</span><span class="o">.</span><span class="n">plot</span><span class="o">.</span><span class="n">binary_bias_global</span><span class="p">(</span><span class="n">method_names</span><span class="p">,</span> <span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span><span class="p">,</span> <span class="n">savepath</span><span class="o">=</span><span class="s1">'./plots/bin_bias.png'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>and should look like:</p>
|
||||
<p><img alt="bias plot on Kindle" src="_images/bin_bias.png" /></p>
|
||||
<p>The box plots show some interesting facts:</p>
|
||||
<ul class="simple">
|
||||
<li><p>all methods are biased towards the training prevalence but specially
|
||||
so CC and PCC (an unbiased quantifier would have a box centered at 0)</p></li>
|
||||
<li><p>the bias is always positive, indicating that all methods tend to
|
||||
overestimate the positive class prevalence</p></li>
|
||||
<li><p>CC and PCC have high variability while ACC and specially PACC exhibit
|
||||
lower variability.</p></li>
|
||||
</ul>
|
||||
<p>Again, these plots could be generated for experiments ranging across
|
||||
different datasets, and the plot will merge all data accordingly.</p>
|
||||
<p>Another illustrative example can be shown that consists of
|
||||
training different CC quantifiers trained at different
|
||||
(artificially sampled) training prevalences.
|
||||
For this example, we generate training samples of 5000
|
||||
documents containing 10%, 20%, …, 90% of positives from the
|
||||
IMDb dataset, and generate the bias plot again.
|
||||
This example can be run by rewritting the <em>gen_data()</em> function
|
||||
like this:</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">gen_data</span><span class="p">():</span>
|
||||
|
||||
<span class="n">train</span><span class="p">,</span> <span class="n">test</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'imdb'</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span><span class="o">.</span><span class="n">train_test</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">CC</span><span class="p">(</span><span class="n">LinearSVC</span><span class="p">())</span>
|
||||
|
||||
<span class="n">method_data</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="k">for</span> <span class="n">training_prevalence</span> <span class="ow">in</span> <span class="n">np</span><span class="o">.</span><span class="n">linspace</span><span class="p">(</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">,</span> <span class="mi">9</span><span class="p">):</span>
|
||||
<span class="n">training_size</span> <span class="o">=</span> <span class="mi">5000</span>
|
||||
<span class="c1"># since the problem is binary, it suffices to specify the negative prevalence, since the positive is constrained</span>
|
||||
<span class="n">train_sample</span> <span class="o">=</span> <span class="n">train</span><span class="o">.</span><span class="n">sampling</span><span class="p">(</span><span class="n">training_size</span><span class="p">,</span> <span class="mi">1</span><span class="o">-</span><span class="n">training_prevalence</span><span class="p">)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">train_sample</span><span class="p">)</span>
|
||||
<span class="n">true_prev</span><span class="p">,</span> <span class="n">estim_prev</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">prediction</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">APP</span><span class="p">(</span><span class="n">test</span><span class="p">,</span> <span class="n">repeats</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">))</span>
|
||||
<span class="n">method_name</span> <span class="o">=</span> <span class="s1">'CC$_{'</span><span class="o">+</span><span class="sa">f</span><span class="s1">'</span><span class="si">{</span><span class="nb">int</span><span class="p">(</span><span class="mi">100</span><span class="o">*</span><span class="n">training_prevalence</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span> <span class="o">+</span> <span class="s1">'\%}$'</span>
|
||||
<span class="n">method_data</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">method_name</span><span class="p">,</span> <span class="n">true_prev</span><span class="p">,</span> <span class="n">estim_prev</span><span class="p">,</span> <span class="n">train_sample</span><span class="o">.</span><span class="n">prevalence</span><span class="p">()))</span>
|
||||
|
||||
<span class="k">return</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">method_data</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>and the plot should now look like:</p>
|
||||
<p><img alt="bias plot on IMDb" src="_images/bin_bias_cc.png" /></p>
|
||||
<p>which clearly shows a negative bias for CC variants trained on
|
||||
data containing more negatives (i.e., < 50%) and positive biases
|
||||
in cases containing more positives (i.e., >50%). The CC trained
|
||||
at 50% behaves as an unbiased estimator of the positive class
|
||||
prevalence.</p>
|
||||
<p>The function <em>qp.plot.binary_bias_bins</em> allows the user to
|
||||
generate box plots broken down by bins of true test prevalence.
|
||||
To this aim, an argument <em>nbins</em> is passed which indicates
|
||||
how many isometric subintervals to take. For example
|
||||
the following plot is produced for <em>nbins=3</em>:</p>
|
||||
<p><img alt="bias plot on IMDb" src="_images/bin_bias_bin_cc.png" /></p>
|
||||
<p>Interestingly enough, the seemingly unbiased estimator (CC at 50%) happens to display
|
||||
a positive bias (or a tendency to overestimate) in cases of low prevalence
|
||||
(i.e., when the true prevalence of the positive class is below 33%),
|
||||
and a negative bias (or a tendency to underestimate) in cases of high prevalence
|
||||
(i.e., when the true prevalence is beyond 67%).</p>
|
||||
<p>Out of curiosity, the diagonal plot for this experiment looks like:</p>
|
||||
<p><img alt="diag plot on IMDb" src="_images/bin_diag_cc.png" /></p>
|
||||
<p>showing pretty clearly the dependency of CC on the prior probabilities
|
||||
of the labeled set it was trained on.</p>
|
||||
</section>
|
||||
<section id="error-by-drift">
|
||||
<h2>Error by Drift<a class="headerlink" href="#error-by-drift" title="Permalink to this heading">¶</a></h2>
|
||||
<p>Above discussed plots are useful for analyzing and comparing
|
||||
the performance of different quantification methods, but are
|
||||
limited to the binary case. The “error by drift” is a plot
|
||||
that shows the error in predictions as a function of the
|
||||
(prior probability) drift between each test sample and the
|
||||
training set. Interestingly, the error and drift can both be measured
|
||||
in terms of any evaluation measure for quantification (like the
|
||||
ones available in <em>qp.error</em>) and can thus be computed
|
||||
irrespectively of the number of classes.</p>
|
||||
<p>The following shows how to generate the plot for the 4 CC variants,
|
||||
using 10 bins for the drift
|
||||
and <em>absolute error</em> as the measure of the error (the
|
||||
drift in the x-axis is always computed in terms of <em>absolute error</em> since
|
||||
other errors are harder to interpret):</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">qp</span><span class="o">.</span><span class="n">plot</span><span class="o">.</span><span class="n">error_by_drift</span><span class="p">(</span><span class="n">method_names</span><span class="p">,</span> <span class="n">true_prevs</span><span class="p">,</span> <span class="n">estim_prevs</span><span class="p">,</span> <span class="n">tr_prevs</span><span class="p">,</span>
|
||||
<span class="n">error_name</span><span class="o">=</span><span class="s1">'ae'</span><span class="p">,</span> <span class="n">n_bins</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">savepath</span><span class="o">=</span><span class="s1">'./plots/err_drift.png'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p><img alt="diag plot on IMDb" src="_images/err_drift.png" /></p>
|
||||
<p>Note that all methods work reasonably well in cases of low prevalence
|
||||
drift (i.e., any CC-variant is a good quantifier whenever the IID
|
||||
assumption is approximately preserved). The higher the drift, the worse
|
||||
those quantifiers tend to perform, although it is clear that PACC
|
||||
yields the lowest error for the most difficult cases.</p>
|
||||
<p>Remember that any plot can be generated <em>across many datasets</em>, and
|
||||
that this would probably result in a more solid comparison.
|
||||
In those cases, however, it is likely that the variances of each
|
||||
method get higher, to the detriment of the visualization.
|
||||
We recommend to set <em>show_std=False</em> in those cases
|
||||
in order to hide the color bands.</p>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Plotting</a><ul>
|
||||
<li><a class="reference internal" href="#diagonal-plot">Diagonal Plot</a></li>
|
||||
<li><a class="reference internal" href="#quantification-bias">Quantification bias</a></li>
|
||||
<li><a class="reference internal" href="#error-by-drift">Error by Drift</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="Model-Selection.html"
|
||||
title="previous chapter">Model Selection</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="modules.html"
|
||||
title="next chapter">quapy</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/Plotting.md.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="modules.html" title="quapy"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Model-Selection.html" title="Model Selection"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Plotting</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 62 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 108 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 71 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 185 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 337 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 243 KiB |
|
|
@ -1,356 +0,0 @@
|
|||
# Datasets
|
||||
|
||||
QuaPy makes available several datasets that have been used in
|
||||
quantification literature, as well as an interface to allow
|
||||
anyone import their custom datasets.
|
||||
|
||||
A _Dataset_ object in QuaPy is roughly a pair of _LabelledCollection_ objects,
|
||||
one playing the role of the training set, another the test set.
|
||||
_LabelledCollection_ is a data class consisting of the (iterable)
|
||||
instances and labels. This class handles most of the sampling functionality in QuaPy.
|
||||
Take a look at the following code:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
import quapy.functional as F
|
||||
|
||||
instances = [
|
||||
'1st positive document', '2nd positive document',
|
||||
'the only negative document',
|
||||
'1st neutral document', '2nd neutral document', '3rd neutral document'
|
||||
]
|
||||
labels = [2, 2, 0, 1, 1, 1]
|
||||
|
||||
data = qp.data.LabelledCollection(instances, labels)
|
||||
print(F.strprev(data.prevalence(), prec=2))
|
||||
```
|
||||
|
||||
Output the class prevalences (showing 2 digit precision):
|
||||
```
|
||||
[0.17, 0.50, 0.33]
|
||||
```
|
||||
|
||||
One can easily produce new samples at desired class prevalence values:
|
||||
|
||||
```python
|
||||
sample_size = 10
|
||||
prev = [0.4, 0.1, 0.5]
|
||||
sample = data.sampling(sample_size, *prev)
|
||||
|
||||
print('instances:', sample.instances)
|
||||
print('labels:', sample.labels)
|
||||
print('prevalence:', F.strprev(sample.prevalence(), prec=2))
|
||||
```
|
||||
|
||||
Which outputs:
|
||||
```
|
||||
instances: ['the only negative document' '2nd positive document'
|
||||
'2nd positive document' '2nd neutral document' '1st positive document'
|
||||
'the only negative document' 'the only negative document'
|
||||
'the only negative document' '2nd positive document'
|
||||
'1st positive document']
|
||||
labels: [0 2 2 1 2 0 0 0 2 2]
|
||||
prevalence: [0.40, 0.10, 0.50]
|
||||
```
|
||||
|
||||
Samples can be made consistent across different runs (e.g., to test
|
||||
different methods on the same exact samples) by sampling and retaining
|
||||
the indexes, that can then be used to generate the sample:
|
||||
|
||||
```python
|
||||
index = data.sampling_index(sample_size, *prev)
|
||||
for method in methods:
|
||||
sample = data.sampling_from_index(index)
|
||||
...
|
||||
```
|
||||
|
||||
However, generating samples for evaluation purposes is tackled in QuaPy
|
||||
by means of the evaluation protocols (see the dedicated entries in the Wiki
|
||||
for [evaluation](https://github.com/HLT-ISTI/QuaPy/wiki/Evaluation) and
|
||||
[protocols](https://github.com/HLT-ISTI/QuaPy/wiki/Protocols)).
|
||||
|
||||
|
||||
## Reviews Datasets
|
||||
|
||||
Three datasets of reviews about Kindle devices, Harry Potter's series, and
|
||||
the well-known IMDb movie reviews can be fetched using a unified interface.
|
||||
For example:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
data = qp.datasets.fetch_reviews('kindle')
|
||||
```
|
||||
|
||||
These datasets have been used in:
|
||||
```
|
||||
Esuli, A., Moreo, A., & Sebastiani, F. (2018, October).
|
||||
A recurrent neural network for sentiment quantification.
|
||||
In Proceedings of the 27th ACM International Conference on
|
||||
Information and Knowledge Management (pp. 1775-1778).
|
||||
```
|
||||
|
||||
The list of reviews ids is available in:
|
||||
|
||||
```python
|
||||
qp.datasets.REVIEWS_SENTIMENT_DATASETS
|
||||
```
|
||||
|
||||
Some statistics of the fhe available datasets are summarized below:
|
||||
|
||||
| Dataset | classes | train size | test size | train prev | test prev | type |
|
||||
|---|:---:|:---:|:---:|:---:|:---:|---|
|
||||
| hp | 2 | 9533 | 18399 | [0.018, 0.982] | [0.065, 0.935] | text |
|
||||
| kindle | 2 | 3821 | 21591 | [0.081, 0.919] | [0.063, 0.937] | text |
|
||||
| imdb | 2 | 25000 | 25000 | [0.500, 0.500] | [0.500, 0.500] | text |
|
||||
|
||||
|
||||
## Twitter Sentiment Datasets
|
||||
|
||||
11 Twitter datasets for sentiment analysis.
|
||||
Text is not accessible, and the documents were made available
|
||||
in tf-idf format. Each dataset presents two splits: a train/val
|
||||
split for model selection purposes, and a train+val/test split
|
||||
for model evaluation. The following code exemplifies how to load
|
||||
a twitter dataset for model selection.
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
data = qp.datasets.fetch_twitter('gasp', for_model_selection=True)
|
||||
```
|
||||
|
||||
The datasets were used in:
|
||||
|
||||
```
|
||||
Gao, W., & Sebastiani, F. (2015, August).
|
||||
Tweet sentiment: From classification to quantification.
|
||||
In 2015 IEEE/ACM International Conference on Advances in
|
||||
Social Networks Analysis and Mining (ASONAM) (pp. 97-104). IEEE.
|
||||
```
|
||||
|
||||
Three of the datasets (semeval13, semeval14, and semeval15) share the
|
||||
same training set (semeval), meaning that the training split one would get
|
||||
when requesting any of them is the same. The dataset "semeval" can only
|
||||
be requested with "for_model_selection=True".
|
||||
The lists of the Twitter dataset's ids can be consulted in:
|
||||
|
||||
```python
|
||||
# a list of 11 dataset ids that can be used for model selection or model evaluation
|
||||
qp.datasets.TWITTER_SENTIMENT_DATASETS_TEST
|
||||
|
||||
# 9 dataset ids in which "semeval13", "semeval14", and "semeval15" are replaced with "semeval"
|
||||
qp.datasets.TWITTER_SENTIMENT_DATASETS_TRAIN
|
||||
```
|
||||
|
||||
Some details can be found below:
|
||||
|
||||
| Dataset | classes | train size | test size | features | train prev | test prev | type |
|
||||
|---|:---:|:---:|:---:|:---:|:---:|:---:|---|
|
||||
| gasp | 3 | 8788 | 3765 | 694582 | [0.421, 0.496, 0.082] | [0.407, 0.507, 0.086] | sparse |
|
||||
| hcr | 3 | 1594 | 798 | 222046 | [0.546, 0.211, 0.243] | [0.640, 0.167, 0.193] | sparse |
|
||||
| omd | 3 | 1839 | 787 | 199151 | [0.463, 0.271, 0.266] | [0.437, 0.283, 0.280] | sparse |
|
||||
| sanders | 3 | 2155 | 923 | 229399 | [0.161, 0.691, 0.148] | [0.164, 0.688, 0.148] | sparse |
|
||||
| semeval13 | 3 | 11338 | 3813 | 1215742 | [0.159, 0.470, 0.372] | [0.158, 0.430, 0.412] | sparse |
|
||||
| semeval14 | 3 | 11338 | 1853 | 1215742 | [0.159, 0.470, 0.372] | [0.109, 0.361, 0.530] | sparse |
|
||||
| semeval15 | 3 | 11338 | 2390 | 1215742 | [0.159, 0.470, 0.372] | [0.153, 0.413, 0.434] | sparse |
|
||||
| semeval16 | 3 | 8000 | 2000 | 889504 | [0.157, 0.351, 0.492] | [0.163, 0.341, 0.497] | sparse |
|
||||
| sst | 3 | 2971 | 1271 | 376132 | [0.261, 0.452, 0.288] | [0.207, 0.481, 0.312] | sparse |
|
||||
| wa | 3 | 2184 | 936 | 248563 | [0.305, 0.414, 0.281] | [0.282, 0.446, 0.272] | sparse |
|
||||
| wb | 3 | 4259 | 1823 | 404333 | [0.270, 0.392, 0.337] | [0.274, 0.392, 0.335] | sparse |
|
||||
|
||||
|
||||
## UCI Machine Learning
|
||||
|
||||
A set of 32 datasets from the [UCI Machine Learning repository](https://archive.ics.uci.edu/ml/datasets.php)
|
||||
used in:
|
||||
|
||||
```
|
||||
Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
Using ensembles for problems with characterizable changes
|
||||
in data distribution: A case study on quantification.
|
||||
Information Fusion, 34, 87-100.
|
||||
```
|
||||
|
||||
The list does not exactly coincide with that used in Pérez-Gállego et al. 2017
|
||||
since we were unable to find the datasets with ids "diabetes" and "phoneme".
|
||||
|
||||
These dataset can be loaded by calling, e.g.:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
data = qp.datasets.fetch_UCIDataset('yeast', verbose=True)
|
||||
```
|
||||
|
||||
This call will return a _Dataset_ object in which the training and
|
||||
test splits are randomly drawn, in a stratified manner, from the whole
|
||||
collection at 70% and 30%, respectively. The _verbose=True_ option indicates
|
||||
that the dataset description should be printed in standard output.
|
||||
The original data is not split,
|
||||
and some papers submit the entire collection to a kFCV validation.
|
||||
In order to accommodate with these practices, one could first instantiate
|
||||
the entire collection, and then creating a generator that will return one
|
||||
training+test dataset at a time, following a kFCV protocol:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
collection = qp.datasets.fetch_UCILabelledCollection("yeast")
|
||||
for data in qp.data.Dataset.kFCV(collection, nfolds=5, nrepeats=2):
|
||||
...
|
||||
```
|
||||
|
||||
Above code will allow to conduct a 2x5FCV evaluation on the "yeast" dataset.
|
||||
|
||||
All datasets come in numerical form (dense matrices); some statistics
|
||||
are summarized below.
|
||||
|
||||
| Dataset | classes | instances | features | prev | type |
|
||||
|---|:---:|:---:|:---:|:---:|---|
|
||||
| acute.a | 2 | 120 | 6 | [0.508, 0.492] | dense |
|
||||
| acute.b | 2 | 120 | 6 | [0.583, 0.417] | dense |
|
||||
| balance.1 | 2 | 625 | 4 | [0.539, 0.461] | dense |
|
||||
| balance.2 | 2 | 625 | 4 | [0.922, 0.078] | dense |
|
||||
| balance.3 | 2 | 625 | 4 | [0.539, 0.461] | dense |
|
||||
| breast-cancer | 2 | 683 | 9 | [0.350, 0.650] | dense |
|
||||
| cmc.1 | 2 | 1473 | 9 | [0.573, 0.427] | dense |
|
||||
| cmc.2 | 2 | 1473 | 9 | [0.774, 0.226] | dense |
|
||||
| cmc.3 | 2 | 1473 | 9 | [0.653, 0.347] | dense |
|
||||
| ctg.1 | 2 | 2126 | 22 | [0.222, 0.778] | dense |
|
||||
| ctg.2 | 2 | 2126 | 22 | [0.861, 0.139] | dense |
|
||||
| ctg.3 | 2 | 2126 | 22 | [0.917, 0.083] | dense |
|
||||
| german | 2 | 1000 | 24 | [0.300, 0.700] | dense |
|
||||
| haberman | 2 | 306 | 3 | [0.735, 0.265] | dense |
|
||||
| ionosphere | 2 | 351 | 34 | [0.641, 0.359] | dense |
|
||||
| iris.1 | 2 | 150 | 4 | [0.667, 0.333] | dense |
|
||||
| iris.2 | 2 | 150 | 4 | [0.667, 0.333] | dense |
|
||||
| iris.3 | 2 | 150 | 4 | [0.667, 0.333] | dense |
|
||||
| mammographic | 2 | 830 | 5 | [0.514, 0.486] | dense |
|
||||
| pageblocks.5 | 2 | 5473 | 10 | [0.979, 0.021] | dense |
|
||||
| semeion | 2 | 1593 | 256 | [0.901, 0.099] | dense |
|
||||
| sonar | 2 | 208 | 60 | [0.534, 0.466] | dense |
|
||||
| spambase | 2 | 4601 | 57 | [0.606, 0.394] | dense |
|
||||
| spectf | 2 | 267 | 44 | [0.794, 0.206] | dense |
|
||||
| tictactoe | 2 | 958 | 9 | [0.653, 0.347] | dense |
|
||||
| transfusion | 2 | 748 | 4 | [0.762, 0.238] | dense |
|
||||
| wdbc | 2 | 569 | 30 | [0.627, 0.373] | dense |
|
||||
| wine.1 | 2 | 178 | 13 | [0.669, 0.331] | dense |
|
||||
| wine.2 | 2 | 178 | 13 | [0.601, 0.399] | dense |
|
||||
| wine.3 | 2 | 178 | 13 | [0.730, 0.270] | dense |
|
||||
| wine-q-red | 2 | 1599 | 11 | [0.465, 0.535] | dense |
|
||||
| wine-q-white | 2 | 4898 | 11 | [0.335, 0.665] | dense |
|
||||
| yeast | 2 | 1484 | 8 | [0.711, 0.289] | dense |
|
||||
|
||||
### Issues:
|
||||
All datasets will be downloaded automatically the first time they are requested, and
|
||||
stored in the _quapy_data_ folder for faster further reuse.
|
||||
However, some datasets require special actions that at the moment are not fully
|
||||
automated.
|
||||
|
||||
* Datasets with ids "ctg.1", "ctg.2", and "ctg.3" (_Cardiotocography Data Set_) load
|
||||
an Excel file, which requires the user to install the _xlrd_ Python module in order
|
||||
to open it.
|
||||
* The dataset with id "pageblocks.5" (_Page Blocks Classification (5)_) needs to
|
||||
open a "unix compressed file" (extension .Z), which is not directly doable with
|
||||
standard Pythons packages like gzip or zip. This file would need to be uncompressed using
|
||||
OS-dependent software manually. Information on how to do it will be printed the first
|
||||
time the dataset is invoked.
|
||||
|
||||
## LeQua Datasets
|
||||
|
||||
QuaPy also provides the datasets used for the LeQua competition.
|
||||
In brief, there are 4 tasks (T1A, T1B, T2A, T2B) having to do with text quantification
|
||||
problems. Tasks T1A and T1B provide documents in vector form, while T2A and T2B provide
|
||||
raw documents instead.
|
||||
Tasks T1A and T2A are binary sentiment quantification problems, while T2A and T2B
|
||||
are multiclass quantification problems consisting of estimating the class prevalence
|
||||
values of 28 different merchandise products.
|
||||
|
||||
Every task consists of a training set, a set of validation samples (for model selection)
|
||||
and a set of test samples (for evaluation). QuaPy returns this data as a LabelledCollection
|
||||
(training) and two generation protocols (for validation and test samples), as follows:
|
||||
|
||||
```python
|
||||
training, val_generator, test_generator = fetch_lequa2022(task=task)
|
||||
```
|
||||
|
||||
See the `lequa2022_experiments.py` in the examples folder for further details on how to
|
||||
carry out experiments using these datasets.
|
||||
|
||||
The datasets are downloaded only once, and stored for fast reuse.
|
||||
|
||||
Some statistics are summarized below:
|
||||
|
||||
| Dataset | classes | train size | validation samples | test samples | docs by sample | type |
|
||||
|---------|:-------:|:----------:|:------------------:|:------------:|:----------------:|:--------:|
|
||||
| T1A | 2 | 5000 | 1000 | 5000 | 250 | vector |
|
||||
| T1B | 28 | 20000 | 1000 | 5000 | 1000 | vector |
|
||||
| T2A | 2 | 5000 | 1000 | 5000 | 250 | text |
|
||||
| T2B | 28 | 20000 | 1000 | 5000 | 1000 | text |
|
||||
|
||||
For further details on the datasets, we refer to the original
|
||||
[paper](https://ceur-ws.org/Vol-3180/paper-146.pdf):
|
||||
|
||||
```
|
||||
Esuli, A., Moreo, A., Sebastiani, F., & Sperduti, G. (2022).
|
||||
A Detailed Overview of LeQua@ CLEF 2022: Learning to Quantify.
|
||||
```
|
||||
|
||||
## Adding Custom Datasets
|
||||
|
||||
QuaPy provides data loaders for simple formats dealing with
|
||||
text, following the format:
|
||||
|
||||
```
|
||||
class-id \t first document's pre-processed text \n
|
||||
class-id \t second document's pre-processed text \n
|
||||
...
|
||||
```
|
||||
|
||||
and sparse representations of the form:
|
||||
|
||||
```
|
||||
{-1, 0, or +1} col(int):val(float) col(int):val(float) ... \n
|
||||
...
|
||||
```
|
||||
|
||||
The code in charge in loading a LabelledCollection is:
|
||||
|
||||
```python
|
||||
@classmethod
|
||||
def load(cls, path:str, loader_func:callable):
|
||||
return LabelledCollection(*loader_func(path))
|
||||
```
|
||||
|
||||
indicating that any _loader_func_ (e.g., a user-defined one) which
|
||||
returns valid arguments for initializing a _LabelledCollection_ object will allow
|
||||
to load any collection. In particular, the _LabelledCollection_ receives as
|
||||
arguments the instances (as an iterable) and the labels (as an iterable) and,
|
||||
additionally, the number of classes can be specified (it would otherwise be
|
||||
inferred from the labels, but that requires at least one positive example for
|
||||
all classes to be present in the collection).
|
||||
|
||||
The same _loader_func_ can be passed to a Dataset, along with two
|
||||
paths, in order to create a training and test pair of _LabelledCollection_,
|
||||
e.g.:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
|
||||
train_path = '../my_data/train.dat'
|
||||
test_path = '../my_data/test.dat'
|
||||
|
||||
def my_custom_loader(path):
|
||||
with open(path, 'rb') as fin:
|
||||
...
|
||||
return instances, labels
|
||||
|
||||
data = qp.data.Dataset.load(train_path, test_path, my_custom_loader)
|
||||
```
|
||||
|
||||
### Data Processing
|
||||
|
||||
QuaPy implements a number of preprocessing functions in the package _qp.data.preprocessing_, including:
|
||||
|
||||
* _text2tfidf_: tfidf vectorization
|
||||
* _reduce_columns_: reducing the number of columns based on term frequency
|
||||
* _standardize_: transforms the column values into z-scores (i.e., subtract the mean and normalizes by the standard deviation, so
|
||||
that the column values have zero mean and unit variance).
|
||||
* _index_: transforms textual tokens into lists of numeric ids)
|
||||
|
|
@ -1,169 +0,0 @@
|
|||
# Evaluation
|
||||
|
||||
Quantification is an appealing tool in scenarios of dataset shift,
|
||||
and particularly in scenarios of prior-probability shift.
|
||||
That is, the interest in estimating the class prevalences arises
|
||||
under the belief that those class prevalences might have changed
|
||||
with respect to the ones observed during training.
|
||||
In other words, one could simply return the training prevalence
|
||||
as a predictor of the test prevalence if this change is assumed
|
||||
to be unlikely (as is the case in general scenarios of
|
||||
machine learning governed by the iid assumption).
|
||||
In brief, quantification requires dedicated evaluation protocols,
|
||||
which are implemented in QuaPy and explained here.
|
||||
|
||||
## Error Measures
|
||||
|
||||
The module quapy.error implements the following error measures for quantification:
|
||||
* _mae_: mean absolute error
|
||||
* _mrae_: mean relative absolute error
|
||||
* _mse_: mean squared error
|
||||
* _mkld_: mean Kullback-Leibler Divergence
|
||||
* _mnkld_: mean normalized Kullback-Leibler Divergence
|
||||
|
||||
Functions _ae_, _rae_, _se_, _kld_, and _nkld_ are also available,
|
||||
which return the individual errors (i.e., without averaging the whole).
|
||||
|
||||
Some errors of classification are also available:
|
||||
* _acce_: accuracy error (1-accuracy)
|
||||
* _f1e_: F-1 score error (1-F1 score)
|
||||
|
||||
The error functions implement the following interface, e.g.:
|
||||
|
||||
```python
|
||||
mae(true_prevs, prevs_hat)
|
||||
```
|
||||
|
||||
in which the first argument is a ndarray containing the true
|
||||
prevalences, and the second argument is another ndarray with
|
||||
the estimations produced by some method.
|
||||
|
||||
Some error functions, e.g., _mrae_, _mkld_, and _mnkld_, are
|
||||
smoothed for numerical stability. In those cases, there is a
|
||||
third argument, e.g.:
|
||||
|
||||
```python
|
||||
def mrae(true_prevs, prevs_hat, eps=None): ...
|
||||
```
|
||||
|
||||
indicating the value for the smoothing parameter epsilon.
|
||||
Traditionally, this value is set to 1/(2T) in past literature,
|
||||
with T the sampling size. One could either pass this value
|
||||
to the function each time, or to set a QuaPy's environment
|
||||
variable _SAMPLE_SIZE_ once, and omit this argument
|
||||
thereafter (recommended);
|
||||
e.g.:
|
||||
|
||||
```python
|
||||
qp.environ['SAMPLE_SIZE'] = 100 # once for all
|
||||
true_prev = np.asarray([0.5, 0.3, 0.2]) # let's assume 3 classes
|
||||
estim_prev = np.asarray([0.1, 0.3, 0.6])
|
||||
error = qp.error.mrae(true_prev, estim_prev)
|
||||
print(f'mrae({true_prev}, {estim_prev}) = {error:.3f}')
|
||||
```
|
||||
|
||||
will print:
|
||||
```
|
||||
mrae([0.500, 0.300, 0.200], [0.100, 0.300, 0.600]) = 0.914
|
||||
```
|
||||
|
||||
Finally, it is possible to instantiate QuaPy's quantification
|
||||
error functions from strings using, e.g.:
|
||||
|
||||
```python
|
||||
error_function = qp.error.from_name('mse')
|
||||
error = error_function(true_prev, estim_prev)
|
||||
```
|
||||
|
||||
## Evaluation Protocols
|
||||
|
||||
An _evaluation protocol_ is an evaluation procedure that uses
|
||||
one specific _sample generation procotol_ to genereate many
|
||||
samples, typically characterized by widely varying amounts of
|
||||
_shift_ with respect to the original distribution, that are then
|
||||
used to evaluate the performance of a (trained) quantifier.
|
||||
These protocols are explained in more detail in a dedicated [entry
|
||||
in the wiki](Protocols.md). For the moment being, let us assume we already have
|
||||
chosen and instantiated one specific such protocol, that we here
|
||||
simply call _prot_. Let also assume our model is called
|
||||
_quantifier_ and that our evaluatio measure of choice is
|
||||
_mae_. The evaluation comes down to:
|
||||
|
||||
```python
|
||||
mae = qp.evaluation.evaluate(quantifier, protocol=prot, error_metric='mae')
|
||||
print(f'MAE = {mae:.4f}')
|
||||
```
|
||||
|
||||
It is often desirable to evaluate our system using more than one
|
||||
single evaluatio measure. In this case, it is convenient to generate
|
||||
a _report_. A report in QuaPy is a dataframe accounting for all the
|
||||
true prevalence values with their corresponding prevalence values
|
||||
as estimated by the quantifier, along with the error each has given
|
||||
rise.
|
||||
|
||||
```python
|
||||
report = qp.evaluation.evaluation_report(quantifier, protocol=prot, error_metrics=['mae', 'mrae', 'mkld'])
|
||||
```
|
||||
|
||||
From a pandas' dataframe, it is straightforward to visualize all the results,
|
||||
and compute the averaged values, e.g.:
|
||||
|
||||
```python
|
||||
pd.set_option('display.expand_frame_repr', False)
|
||||
report['estim-prev'] = report['estim-prev'].map(F.strprev)
|
||||
print(report)
|
||||
|
||||
print('Averaged values:')
|
||||
print(report.mean())
|
||||
```
|
||||
|
||||
This will produce an output like:
|
||||
|
||||
```
|
||||
true-prev estim-prev mae mrae mkld
|
||||
0 [0.308, 0.692] [0.314, 0.686] 0.005649 0.013182 0.000074
|
||||
1 [0.896, 0.104] [0.909, 0.091] 0.013145 0.069323 0.000985
|
||||
2 [0.848, 0.152] [0.809, 0.191] 0.039063 0.149806 0.005175
|
||||
3 [0.016, 0.984] [0.033, 0.967] 0.017236 0.487529 0.005298
|
||||
4 [0.728, 0.272] [0.751, 0.249] 0.022769 0.057146 0.001350
|
||||
... ... ... ... ... ...
|
||||
4995 [0.72, 0.28] [0.698, 0.302] 0.021752 0.053631 0.001133
|
||||
4996 [0.868, 0.132] [0.888, 0.112] 0.020490 0.088230 0.001985
|
||||
4997 [0.292, 0.708] [0.298, 0.702] 0.006149 0.014788 0.000090
|
||||
4998 [0.24, 0.76] [0.220, 0.780] 0.019950 0.054309 0.001127
|
||||
4999 [0.948, 0.052] [0.965, 0.035] 0.016941 0.165776 0.003538
|
||||
|
||||
[5000 rows x 5 columns]
|
||||
Averaged values:
|
||||
mae 0.023588
|
||||
mrae 0.108779
|
||||
mkld 0.003631
|
||||
dtype: float64
|
||||
|
||||
Process finished with exit code 0
|
||||
```
|
||||
|
||||
Alternatively, we can simply generate all the predictions by:
|
||||
|
||||
```python
|
||||
true_prevs, estim_prevs = qp.evaluation.prediction(quantifier, protocol=prot)
|
||||
```
|
||||
|
||||
All the evaluation functions implement specific optimizations for speeding-up
|
||||
the evaluation of aggregative quantifiers (i.e., of instances of _AggregativeQuantifier_).
|
||||
The optimization comes down to generating classification predictions (either crisp or soft)
|
||||
only once for the entire test set, and then applying the sampling procedure to the
|
||||
predictions, instead of generating samples of instances and then computing the
|
||||
classification predictions every time. This is only possible when the protocol
|
||||
is an instance of _OnLabelledCollectionProtocol_. The optimization is only
|
||||
carried out when the number of classification predictions thus generated would be
|
||||
smaller than the number of predictions required for the entire protocol; e.g.,
|
||||
if the original dataset contains 1M instances, but the protocol is such that it would
|
||||
at most generate 20 samples of 100 instances, then it would be preferable to postpone the
|
||||
classification for each sample. This behaviour is indicated by setting
|
||||
_aggr_speedup="auto"_. Conversely, when indicating _aggr_speedup="force"_ QuaPy will
|
||||
precompute all the predictions irrespectively of the number of instances and number of samples.
|
||||
Finally, this can be deactivated by setting _aggr_speedup=False_. Note that this optimization
|
||||
is not only applied for the final evaluation, but also for the internal evaluations carried
|
||||
out during _model selection_. Since these are typically many, the heuristic can help reduce the
|
||||
execution time a lot.
|
||||
|
|
@ -1,56 +0,0 @@
|
|||
Installation
|
||||
------------
|
||||
|
||||
QuaPy can be easily installed via `pip`
|
||||
|
||||
::
|
||||
|
||||
pip install quapy
|
||||
|
||||
See `pip page <https://pypi.org/project/QuaPy/>`_ for older versions.
|
||||
|
||||
Requirements
|
||||
************
|
||||
|
||||
* scikit-learn, numpy, scipy
|
||||
* pytorch (for QuaNet)
|
||||
* svmperf patched for quantification (see below)
|
||||
* joblib
|
||||
* tqdm
|
||||
* pandas, xlrd
|
||||
* matplotlib
|
||||
|
||||
|
||||
SVM-perf with quantification-oriented losses
|
||||
********************************************
|
||||
|
||||
In order to run experiments involving SVM(Q), SVM(KLD), SVM(NKLD),
|
||||
SVM(AE), or SVM(RAE), you have to first download the
|
||||
`svmperf <http://www.cs.cornell.edu/people/tj/svm_light/svm_perf.html>`_
|
||||
package, apply the patch
|
||||
`svm-perf-quantification-ext.patch <https://github.com/HLT-ISTI/QuaPy/blob/master/svm-perf-quantification-ext.patch>`_,
|
||||
and compile the sources.
|
||||
The script
|
||||
`prepare_svmperf.sh <https://github.com/HLT-ISTI/QuaPy/blob/master/prepare_svmperf.sh>`_,
|
||||
does all the job. Simply run:
|
||||
|
||||
::
|
||||
|
||||
./prepare_svmperf.sh
|
||||
|
||||
|
||||
The resulting directory `./svm_perf_quantification` contains the
|
||||
patched version of `svmperf` with quantification-oriented losses.
|
||||
|
||||
The
|
||||
`svm-perf-quantification-ext.patch <https://github.com/HLT-ISTI/QuaPy/blob/master/svm-perf-quantification-ext.patch>`_
|
||||
is an extension of the patch made available by
|
||||
`Esuli et al. 2015 <https://dl.acm.org/doi/abs/10.1145/2700406?casa_token=8D2fHsGCVn0AAAAA:ZfThYOvrzWxMGfZYlQW_y8Cagg-o_l6X_PcF09mdETQ4Tu7jK98mxFbGSXp9ZSO14JkUIYuDGFG0>`_
|
||||
that allows SVMperf to optimize for
|
||||
the `Q` measure as proposed by
|
||||
`Barranquero et al. 2015 <https://www.sciencedirect.com/science/article/abs/pii/S003132031400291X>`_
|
||||
and for the `KLD` and `NKLD` as proposed by
|
||||
`Esuli et al. 2015 <https://dl.acm.org/doi/abs/10.1145/2700406?casa_token=8D2fHsGCVn0AAAAA:ZfThYOvrzWxMGfZYlQW_y8Cagg-o_l6X_PcF09mdETQ4Tu7jK98mxFbGSXp9ZSO14JkUIYuDGFG0>`_
|
||||
for quantification.
|
||||
This patch extends the former by also allowing SVMperf to optimize for
|
||||
`AE` and `RAE`.
|
||||
|
|
@ -1,438 +0,0 @@
|
|||
# Quantification Methods
|
||||
|
||||
Quantification methods can be categorized as belonging to
|
||||
_aggregative_ and _non-aggregative_ groups.
|
||||
Most methods included in QuaPy at the moment are of type _aggregative_
|
||||
(though we plan to add many more methods in the near future), i.e.,
|
||||
are methods characterized by the fact that
|
||||
quantification is performed as an aggregation function of the individual
|
||||
products of classification.
|
||||
|
||||
Any quantifier in QuaPy shoud extend the class _BaseQuantifier_,
|
||||
and implement some abstract methods:
|
||||
```python
|
||||
@abstractmethod
|
||||
def fit(self, data: LabelledCollection): ...
|
||||
|
||||
@abstractmethod
|
||||
def quantify(self, instances): ...
|
||||
```
|
||||
The meaning of those functions should be familiar to those
|
||||
used to work with scikit-learn since the class structure of QuaPy
|
||||
is directly inspired by scikit-learn's _Estimators_. Functions
|
||||
_fit_ and _quantify_ are used to train the model and to provide
|
||||
class estimations (the reason why
|
||||
scikit-learn' structure has not been adopted _as is_ in QuaPy responds to
|
||||
the fact that scikit-learn's _predict_ function is expected to return
|
||||
one output for each input element --e.g., a predicted label for each
|
||||
instance in a sample-- while in quantification the output for a sample
|
||||
is one single array of class prevalences).
|
||||
Quantifiers also extend from scikit-learn's `BaseEstimator`, in order
|
||||
to simplify the use of _set_params_ and _get_params_ used in
|
||||
[model selector](https://github.com/HLT-ISTI/QuaPy/wiki/Model-Selection).
|
||||
|
||||
## Aggregative Methods
|
||||
|
||||
All quantification methods are implemented as part of the
|
||||
_qp.method_ package. In particular, _aggregative_ methods are defined in
|
||||
_qp.method.aggregative_, and extend _AggregativeQuantifier(BaseQuantifier)_.
|
||||
The methods that any _aggregative_ quantifier must implement are:
|
||||
|
||||
```python
|
||||
@abstractmethod
|
||||
def fit(self, data: LabelledCollection, fit_learner=True): ...
|
||||
|
||||
@abstractmethod
|
||||
def aggregate(self, classif_predictions:np.ndarray): ...
|
||||
```
|
||||
|
||||
since, as mentioned before, aggregative methods base their prediction on the
|
||||
individual predictions of a classifier. Indeed, a default implementation
|
||||
of _BaseQuantifier.quantify_ is already provided, which looks like:
|
||||
|
||||
```python
|
||||
def quantify(self, instances):
|
||||
classif_predictions = self.classify(instances)
|
||||
return self.aggregate(classif_predictions)
|
||||
```
|
||||
Aggregative quantifiers are expected to maintain a classifier (which is
|
||||
accessed through the _@property_ _classifier_). This classifier is
|
||||
given as input to the quantifier, and can be already fit
|
||||
on external data (in which case, the _fit_learner_ argument should
|
||||
be set to False), or be fit by the quantifier's fit (default).
|
||||
|
||||
Another class of _aggregative_ methods are the _probabilistic_
|
||||
aggregative methods, that should inherit from the abstract class
|
||||
_AggregativeProbabilisticQuantifier(AggregativeQuantifier)_.
|
||||
The particularity of _probabilistic_ aggregative methods (w.r.t.
|
||||
non-probabilistic ones), is that the default quantifier is defined
|
||||
in terms of the posterior probabilities returned by a probabilistic
|
||||
classifier, and not by the crisp decisions of a hard classifier.
|
||||
In any case, the interface _classify(instances)_ remains unchanged.
|
||||
|
||||
One advantage of _aggregative_ methods (either probabilistic or not)
|
||||
is that the evaluation according to any sampling procedure (e.g.,
|
||||
the [artificial sampling protocol](https://github.com/HLT-ISTI/QuaPy/wiki/Evaluation))
|
||||
can be achieved very efficiently, since the entire set can be pre-classified
|
||||
once, and the quantification estimations for different samples can directly
|
||||
reuse these predictions, without requiring to classify each element every time.
|
||||
QuaPy leverages this property to speed-up any procedure having to do with
|
||||
quantification over samples, as is customarily done in model selection or
|
||||
in evaluation.
|
||||
|
||||
### The Classify & Count variants
|
||||
|
||||
QuaPy implements the four CC variants, i.e.:
|
||||
|
||||
* _CC_ (Classify & Count), the simplest aggregative quantifier; one that
|
||||
simply relies on the label predictions of a classifier to deliver class estimates.
|
||||
* _ACC_ (Adjusted Classify & Count), the adjusted variant of CC.
|
||||
* _PCC_ (Probabilistic Classify & Count), the probabilistic variant of CC that
|
||||
relies on the soft estimations (or posterior probabilities) returned by a (probabilistic) classifier.
|
||||
* _PACC_ (Probabilistic Adjusted Classify & Count), the adjusted variant of PCC.
|
||||
|
||||
The following code serves as a complete example using CC equipped
|
||||
with a SVM as the classifier:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
import quapy.functional as F
|
||||
from sklearn.svm import LinearSVC
|
||||
|
||||
training, test = qp.datasets.fetch_twitter('hcr', pickle=True).train_test
|
||||
|
||||
# instantiate a classifier learner, in this case a SVM
|
||||
svm = LinearSVC()
|
||||
|
||||
# instantiate a Classify & Count with the SVM
|
||||
# (an alias is available in qp.method.aggregative.ClassifyAndCount)
|
||||
model = qp.method.aggregative.CC(svm)
|
||||
model.fit(training)
|
||||
estim_prevalence = model.quantify(test.instances)
|
||||
```
|
||||
|
||||
The same code could be used to instantiate an ACC, by simply replacing
|
||||
the instantiation of the model with:
|
||||
```python
|
||||
model = qp.method.aggregative.ACC(svm)
|
||||
```
|
||||
Note that the adjusted variants (ACC and PACC) need to estimate
|
||||
some parameters for performing the adjustment (e.g., the
|
||||
_true positive rate_ and the _false positive rate_ in case of
|
||||
binary classification) that are estimated on a validation split
|
||||
of the labelled set. In this case, the __init__ method of
|
||||
ACC defines an additional parameter, _val_split_ which, by
|
||||
default, is set to 0.4 and so, the 40% of the labelled data
|
||||
will be used for estimating the parameters for adjusting the
|
||||
predictions. This parameters can also be set with an integer,
|
||||
indicating that the parameters should be estimated by means of
|
||||
_k_-fold cross-validation, for which the integer indicates the
|
||||
number _k_ of folds. Finally, _val_split_ can be set to a
|
||||
specific held-out validation set (i.e., an instance of _LabelledCollection_).
|
||||
|
||||
The specification of _val_split_ can be
|
||||
postponed to the invokation of the fit method (if _val_split_ was also
|
||||
set in the constructor, the one specified at fit time would prevail),
|
||||
e.g.:
|
||||
|
||||
```python
|
||||
model = qp.method.aggregative.ACC(svm)
|
||||
# perform 5-fold cross validation for estimating ACC's parameters
|
||||
# (overrides the default val_split=0.4 in the constructor)
|
||||
model.fit(training, val_split=5)
|
||||
```
|
||||
|
||||
The following code illustrates the case in which PCC is used:
|
||||
|
||||
```python
|
||||
model = qp.method.aggregative.PCC(svm)
|
||||
model.fit(training)
|
||||
estim_prevalence = model.quantify(test.instances)
|
||||
print('classifier:', model.classifier)
|
||||
```
|
||||
In this case, QuaPy will print:
|
||||
```
|
||||
The learner LinearSVC does not seem to be probabilistic. The learner will be calibrated.
|
||||
classifier: CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)
|
||||
```
|
||||
The first output indicates that the learner (_LinearSVC_ in this case)
|
||||
is not a probabilistic classifier (i.e., it does not implement the
|
||||
_predict_proba_ method) and so, the classifier will be converted to
|
||||
a probabilistic one through [calibration](https://scikit-learn.org/stable/modules/calibration.html).
|
||||
As a result, the classifier that is printed in the second line points
|
||||
to a _CalibratedClassifier_ instance. Note that calibration can only
|
||||
be applied to hard classifiers when _fit_learner=True_; an exception
|
||||
will be raised otherwise.
|
||||
|
||||
Lastly, everything we said aboud ACC and PCC
|
||||
applies to PACC as well.
|
||||
|
||||
|
||||
### Expectation Maximization (EMQ)
|
||||
|
||||
The Expectation Maximization Quantifier (EMQ), also known as
|
||||
the SLD, is available at _qp.method.aggregative.EMQ_ or via the
|
||||
alias _qp.method.aggregative.ExpectationMaximizationQuantifier_.
|
||||
The method is described in:
|
||||
|
||||
_Saerens, M., Latinne, P., and Decaestecker, C. (2002). Adjusting the outputs of a classifier
|
||||
to new a priori probabilities: A simple procedure. Neural Computation, 14(1):21–41._
|
||||
|
||||
EMQ works with a probabilistic classifier (if the classifier
|
||||
given as input is a hard one, a calibration will be attempted).
|
||||
Although this method was originally proposed for improving the
|
||||
posterior probabilities of a probabilistic classifier, and not
|
||||
for improving the estimation of prior probabilities, EMQ ranks
|
||||
almost always among the most effective quantifiers in the
|
||||
experiments we have carried out.
|
||||
|
||||
An example of use can be found below:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
dataset = qp.datasets.fetch_twitter('hcr', pickle=True)
|
||||
|
||||
model = qp.method.aggregative.EMQ(LogisticRegression())
|
||||
model.fit(dataset.training)
|
||||
estim_prevalence = model.quantify(dataset.test.instances)
|
||||
```
|
||||
|
||||
_New in v0.1.7_: EMQ now accepts two new parameters in the construction method, namely
|
||||
_exact_train_prev_ which allows to use the true training prevalence as the departing
|
||||
prevalence estimation (default behaviour), or instead an approximation of it as
|
||||
suggested by [Alexandari et al. (2020)](http://proceedings.mlr.press/v119/alexandari20a.html)
|
||||
(by setting _exact_train_prev=False_).
|
||||
The other parameter is _recalib_ which allows to indicate a calibration method, among those
|
||||
proposed by [Alexandari et al. (2020)](http://proceedings.mlr.press/v119/alexandari20a.html),
|
||||
including the Bias-Corrected Temperature Scaling, Vector Scaling, etc.
|
||||
See the API documentation for further details.
|
||||
|
||||
|
||||
### Hellinger Distance y (HDy)
|
||||
|
||||
Implementation of the method based on the Hellinger Distance y (HDy) proposed by
|
||||
[González-Castro, V., Alaiz-Rodrı́guez, R., and Alegre, E. (2013). Class distribution
|
||||
estimation based on the Hellinger distance. Information Sciences, 218:146–164.](https://www.sciencedirect.com/science/article/pii/S0020025512004069)
|
||||
|
||||
It is implemented in _qp.method.aggregative.HDy_ (also accessible
|
||||
through the allias _qp.method.aggregative.HellingerDistanceY_).
|
||||
This method works with a probabilistic classifier (hard classifiers
|
||||
can be used as well and will be calibrated) and requires a validation
|
||||
set to estimate parameter for the mixture model. Just like
|
||||
ACC and PACC, this quantifier receives a _val_split_ argument
|
||||
in the constructor (or in the fit method, in which case the previous
|
||||
value is overridden) that can either be a float indicating the proportion
|
||||
of training data to be taken as the validation set (in a random
|
||||
stratified split), or a validation set (i.e., an instance of
|
||||
_LabelledCollection_) itself.
|
||||
|
||||
HDy was proposed as a binary classifier and the implementation
|
||||
provided in QuaPy accepts only binary datasets.
|
||||
|
||||
The following code shows an example of use:
|
||||
```python
|
||||
import quapy as qp
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
# load a binary dataset
|
||||
dataset = qp.datasets.fetch_reviews('hp', pickle=True)
|
||||
qp.data.preprocessing.text2tfidf(dataset, min_df=5, inplace=True)
|
||||
|
||||
model = qp.method.aggregative.HDy(LogisticRegression())
|
||||
model.fit(dataset.training)
|
||||
estim_prevalence = model.quantify(dataset.test.instances)
|
||||
```
|
||||
|
||||
_New in v0.1.7:_ QuaPy now provides an implementation of the generalized
|
||||
"Distribution Matching" approaches for multiclass, inspired by the framework
|
||||
of [Firat (2016)](https://arxiv.org/abs/1606.00868). One can instantiate
|
||||
a variant of HDy for multiclass quantification as follows:
|
||||
|
||||
```python
|
||||
mutliclassHDy = qp.method.aggregative.DistributionMatching(classifier=LogisticRegression(), divergence='HD', cdf=False)
|
||||
```
|
||||
|
||||
_New in v0.1.7:_ QuaPy now provides an implementation of the "DyS"
|
||||
framework proposed by [Maletzke et al (2020)](https://ojs.aaai.org/index.php/AAAI/article/view/4376)
|
||||
and the "SMM" method proposed by [Hassan et al (2019)](https://ieeexplore.ieee.org/document/9260028)
|
||||
(thanks to _Pablo González_ for the contributions!)
|
||||
|
||||
### Threshold Optimization methods
|
||||
|
||||
_New in v0.1.7:_ QuaPy now implements Forman's threshold optimization methods;
|
||||
see, e.g., [(Forman 2006)](https://dl.acm.org/doi/abs/10.1145/1150402.1150423)
|
||||
and [(Forman 2008)](https://link.springer.com/article/10.1007/s10618-008-0097-y).
|
||||
These include: T50, MAX, X, Median Sweep (MS), and its variant MS2.
|
||||
|
||||
### Explicit Loss Minimization
|
||||
|
||||
The Explicit Loss Minimization (ELM) represent a family of methods
|
||||
based on structured output learning, i.e., quantifiers relying on
|
||||
classifiers that have been optimized targeting a
|
||||
quantification-oriented evaluation measure.
|
||||
The original methods are implemented in QuaPy as classify & count (CC)
|
||||
quantifiers that use Joachim's [SVMperf](https://www.cs.cornell.edu/people/tj/svm_light/svm_perf.html)
|
||||
as the underlying classifier, properly set to optimize for the desired loss.
|
||||
|
||||
In QuaPy, this can be more achieved by calling the functions:
|
||||
|
||||
* _newSVMQ_: returns the quantification method called SVM(Q) that optimizes for the metric _Q_ defined
|
||||
in [_Barranquero, J., Díez, J., and del Coz, J. J. (2015). Quantification-oriented learning based
|
||||
on reliable classifiers. Pattern Recognition, 48(2):591–604._](https://www.sciencedirect.com/science/article/pii/S003132031400291X)
|
||||
* _newSVMKLD_ and _newSVMNKLD_: returns the quantification method called SVM(KLD) and SVM(nKLD), standing for
|
||||
Kullback-Leibler Divergence and Normalized Kullback-Leibler Divergence, as proposed in [_Esuli, A. and Sebastiani, F. (2015).
|
||||
Optimizing text quantifiers for multivariate loss functions.
|
||||
ACM Transactions on Knowledge Discovery and Data, 9(4):Article 27._](https://dl.acm.org/doi/abs/10.1145/2700406)
|
||||
* _newSVMAE_ and _newSVMRAE_: returns a quantification method called SVM(AE) and SVM(RAE) that optimizes for the (Mean) Absolute Error and for the
|
||||
(Mean) Relative Absolute Error, as first used by
|
||||
[_Moreo, A. and Sebastiani, F. (2021). Tweet sentiment quantification: An experimental re-evaluation. PLOS ONE 17 (9), 1-23._](https://arxiv.org/abs/2011.02552)
|
||||
|
||||
the last two methods (SVM(AE) and SVM(RAE)) have been implemented in
|
||||
QuaPy in order to make available ELM variants for what nowadays
|
||||
are considered the most well-behaved evaluation metrics in quantification.
|
||||
|
||||
In order to make these models work, you would need to run the script
|
||||
_prepare_svmperf.sh_ (distributed along with QuaPy) that
|
||||
downloads _SVMperf_' source code, applies a patch that
|
||||
implements the quantification oriented losses, and compiles the
|
||||
sources.
|
||||
|
||||
If you want to add any custom loss, you would need to modify
|
||||
the source code of _SVMperf_ in order to implement it, and
|
||||
assign a valid loss code to it. Then you must re-compile
|
||||
the whole thing and instantiate the quantifier in QuaPy
|
||||
as follows:
|
||||
|
||||
```python
|
||||
# you can either set the path to your custom svm_perf_quantification implementation
|
||||
# in the environment variable, or as an argument to the constructor of ELM
|
||||
qp.environ['SVMPERF_HOME'] = './path/to/svm_perf_quantification'
|
||||
|
||||
# assign an alias to your custom loss and the id you have assigned to it
|
||||
svmperf = qp.classification.svmperf.SVMperf
|
||||
svmperf.valid_losses['mycustomloss'] = 28
|
||||
|
||||
# instantiate the ELM method indicating the loss
|
||||
model = qp.method.aggregative.ELM(loss='mycustomloss')
|
||||
```
|
||||
|
||||
All ELM are binary quantifiers since they rely on _SVMperf_, that
|
||||
currently supports only binary classification.
|
||||
ELM variants (any binary quantifier in general) can be extended
|
||||
to operate in single-label scenarios trivially by adopting a
|
||||
"one-vs-all" strategy (as, e.g., in
|
||||
[_Gao, W. and Sebastiani, F. (2016). From classification to quantification in tweet sentiment
|
||||
analysis. Social Network Analysis and Mining, 6(19):1–22_](https://link.springer.com/article/10.1007/s13278-016-0327-z)).
|
||||
In QuaPy this is possible by using the _OneVsAll_ class.
|
||||
|
||||
There are two ways for instantiating this class, _OneVsAllGeneric_ that works for
|
||||
any quantifier, and _OneVsAllAggregative_ that is optimized for aggregative quantifiers.
|
||||
In general, you can simply use the _getOneVsAll_ function and QuaPy will choose
|
||||
the more convenient of the two.
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
from quapy.method.aggregative import SVMQ
|
||||
|
||||
# load a single-label dataset (this one contains 3 classes)
|
||||
dataset = qp.datasets.fetch_twitter('hcr', pickle=True)
|
||||
|
||||
# let qp know where svmperf is
|
||||
qp.environ['SVMPERF_HOME'] = '../svm_perf_quantification'
|
||||
|
||||
model = getOneVsAll(SVMQ(), n_jobs=-1) # run them on parallel
|
||||
model.fit(dataset.training)
|
||||
estim_prevalence = model.quantify(dataset.test.instances)
|
||||
```
|
||||
|
||||
Check the examples _[explicit_loss_minimization.py](..%2Fexamples%2Fexplicit_loss_minimization.py)_
|
||||
and [one_vs_all.py](..%2Fexamples%2Fone_vs_all.py) for more details.
|
||||
|
||||
## Meta Models
|
||||
|
||||
By _meta_ models we mean quantification methods that are defined on top of other
|
||||
quantification methods, and that thus do not squarely belong to the aggregative nor
|
||||
the non-aggregative group (indeed, _meta_ models could use quantifiers from any of those
|
||||
groups).
|
||||
_Meta_ models are implemented in the _qp.method.meta_ module.
|
||||
|
||||
### Ensembles
|
||||
|
||||
QuaPy implements (some of) the variants proposed in:
|
||||
|
||||
* [_Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
|
||||
Information Fusion, 34, 87-100._](https://www.sciencedirect.com/science/article/pii/S1566253516300628)
|
||||
* [_Pérez-Gállego, P., Castano, A., Quevedo, J. R., & del Coz, J. J. (2019).
|
||||
Dynamic ensemble selection for quantification tasks.
|
||||
Information Fusion, 45, 1-15._](https://www.sciencedirect.com/science/article/pii/S1566253517303652)
|
||||
|
||||
The following code shows how to instantiate an Ensemble of 30 _Adjusted Classify & Count_ (ACC)
|
||||
quantifiers operating with a _Logistic Regressor_ (LR) as the base classifier, and using the
|
||||
_average_ as the aggregation policy (see the original article for further details).
|
||||
The last parameter indicates to use all processors for parallelization.
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
from quapy.method.aggregative import ACC
|
||||
from quapy.method.meta import Ensemble
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
dataset = qp.datasets.fetch_UCIDataset('haberman')
|
||||
|
||||
model = Ensemble(quantifier=ACC(LogisticRegression()), size=30, policy='ave', n_jobs=-1)
|
||||
model.fit(dataset.training)
|
||||
estim_prevalence = model.quantify(dataset.test.instances)
|
||||
```
|
||||
|
||||
Other aggregation policies implemented in QuaPy include:
|
||||
* 'ptr' for applying a dynamic selection based on the training prevalence of the ensemble's members
|
||||
* 'ds' for applying a dynamic selection based on the Hellinger Distance
|
||||
* _any valid quantification measure_ (e.g., 'mse') for performing a static selection based on
|
||||
the performance estimated for each member of the ensemble in terms of that evaluation metric.
|
||||
|
||||
When using any of the above options, it is important to set the _red_size_ parameter, which
|
||||
informs of the number of members to retain.
|
||||
|
||||
Please, check the [model selection](https://github.com/HLT-ISTI/QuaPy/wiki/Model-Selection)
|
||||
wiki if you want to optimize the hyperparameters of ensemble for classification or quantification.
|
||||
|
||||
### The QuaNet neural network
|
||||
|
||||
QuaPy offers an implementation of QuaNet, a deep learning model presented in:
|
||||
|
||||
[_Esuli, A., Moreo, A., & Sebastiani, F. (2018, October).
|
||||
A recurrent neural network for sentiment quantification.
|
||||
In Proceedings of the 27th ACM International Conference on
|
||||
Information and Knowledge Management (pp. 1775-1778)._](https://dl.acm.org/doi/abs/10.1145/3269206.3269287)
|
||||
|
||||
This model requires _torch_ to be installed.
|
||||
QuaNet also requires a classifier that can provide embedded representations
|
||||
of the inputs.
|
||||
In the original paper, QuaNet was tested using an LSTM as the base classifier.
|
||||
In the following example, we show an instantiation of QuaNet that instead uses CNN as a probabilistic classifier, taking its last layer representation as the document embedding:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
from quapy.method.meta import QuaNet
|
||||
from quapy.classification.neural import NeuralClassifierTrainer, CNNnet
|
||||
|
||||
# use samples of 100 elements
|
||||
qp.environ['SAMPLE_SIZE'] = 100
|
||||
|
||||
# load the kindle dataset as text, and convert words to numerical indexes
|
||||
dataset = qp.datasets.fetch_reviews('kindle', pickle=True)
|
||||
qp.data.preprocessing.index(dataset, min_df=5, inplace=True)
|
||||
|
||||
# the text classifier is a CNN trained by NeuralClassifierTrainer
|
||||
cnn = CNNnet(dataset.vocabulary_size, dataset.n_classes)
|
||||
learner = NeuralClassifierTrainer(cnn, device='cuda')
|
||||
|
||||
# train QuaNet
|
||||
model = QuaNet(learner, device='cuda')
|
||||
model.fit(dataset.training)
|
||||
estim_prevalence = model.quantify(dataset.test.instances)
|
||||
```
|
||||
|
||||
|
|
@ -1,150 +0,0 @@
|
|||
# Model Selection
|
||||
|
||||
As a supervised machine learning task, quantification methods
|
||||
can strongly depend on a good choice of model hyper-parameters.
|
||||
The process whereby those hyper-parameters are chosen is
|
||||
typically known as _Model Selection_, and typically consists of
|
||||
testing different settings and picking the one that performed
|
||||
best in a held-out validation set in terms of any given
|
||||
evaluation measure.
|
||||
|
||||
## Targeting a Quantification-oriented loss
|
||||
|
||||
The task being optimized determines the evaluation protocol,
|
||||
i.e., the criteria according to which the performance of
|
||||
any given method for solving is to be assessed.
|
||||
As a task on its own right, quantification should impose
|
||||
its own model selection strategies, i.e., strategies
|
||||
aimed at finding appropriate configurations
|
||||
specifically designed for the task of quantification.
|
||||
|
||||
Quantification has long been regarded as an add-on of
|
||||
classification, and thus the model selection strategies
|
||||
customarily adopted in classification have simply been
|
||||
applied to quantification (see the next section).
|
||||
It has been argued in [Moreo, Alejandro, and Fabrizio Sebastiani.
|
||||
Re-Assessing the "Classify and Count" Quantification Method.
|
||||
ECIR 2021: Advances in Information Retrieval pp 75–91.](https://link.springer.com/chapter/10.1007/978-3-030-72240-1_6)
|
||||
that specific model selection strategies should
|
||||
be adopted for quantification. That is, model selection
|
||||
strategies for quantification should target
|
||||
quantification-oriented losses and be tested in a variety
|
||||
of scenarios exhibiting different degrees of prior
|
||||
probability shift.
|
||||
|
||||
The class _qp.model_selection.GridSearchQ_ implements a grid-search exploration over the space of
|
||||
hyper-parameter combinations that [evaluates](https://github.com/HLT-ISTI/QuaPy/wiki/Evaluation)
|
||||
each combination of hyper-parameters by means of a given quantification-oriented
|
||||
error metric (e.g., any of the error functions implemented
|
||||
in _qp.error_) and according to a
|
||||
[sampling generation protocol](https://github.com/HLT-ISTI/QuaPy/wiki/Protocols).
|
||||
|
||||
The following is an example (also included in the examples folder) of model selection for quantification:
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
from quapy.protocol import APP
|
||||
from quapy.method.aggregative import DistributionMatching
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
import numpy as np
|
||||
|
||||
"""
|
||||
In this example, we show how to perform model selection on a DistributionMatching quantifier.
|
||||
"""
|
||||
|
||||
model = DistributionMatching(LogisticRegression())
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 100
|
||||
qp.environ['N_JOBS'] = -1 # explore hyper-parameters in parallel
|
||||
|
||||
training, test = qp.datasets.fetch_reviews('imdb', tfidf=True, min_df=5).train_test
|
||||
|
||||
# The model will be returned by the fit method of GridSearchQ.
|
||||
# Every combination of hyper-parameters will be evaluated by confronting the
|
||||
# quantifier thus configured against a series of samples generated by means
|
||||
# of a sample generation protocol. For this example, we will use the
|
||||
# artificial-prevalence protocol (APP), that generates samples with prevalence
|
||||
# values in the entire range of values from a grid (e.g., [0, 0.1, 0.2, ..., 1]).
|
||||
# We devote 30% of the dataset for this exploration.
|
||||
training, validation = training.split_stratified(train_prop=0.7)
|
||||
protocol = APP(validation)
|
||||
|
||||
# We will explore a classification-dependent hyper-parameter (e.g., the 'C'
|
||||
# hyper-parameter of LogisticRegression) and a quantification-dependent hyper-parameter
|
||||
# (e.g., the number of bins in a DistributionMatching quantifier.
|
||||
# Classifier-dependent hyper-parameters have to be marked with a prefix "classifier__"
|
||||
# in order to let the quantifier know this hyper-parameter belongs to its underlying
|
||||
# classifier.
|
||||
param_grid = {
|
||||
'classifier__C': np.logspace(-3,3,7),
|
||||
'nbins': [8, 16, 32, 64],
|
||||
}
|
||||
|
||||
model = qp.model_selection.GridSearchQ(
|
||||
model=model,
|
||||
param_grid=param_grid,
|
||||
protocol=protocol,
|
||||
error='mae', # the error to optimize is the MAE (a quantification-oriented loss)
|
||||
refit=True, # retrain on the whole labelled set once done
|
||||
verbose=True # show information as the process goes on
|
||||
).fit(training)
|
||||
|
||||
print(f'model selection ended: best hyper-parameters={model.best_params_}')
|
||||
model = model.best_model_
|
||||
|
||||
# evaluation in terms of MAE
|
||||
# we use the same evaluation protocol (APP) on the test set
|
||||
mae_score = qp.evaluation.evaluate(model, protocol=APP(test), error_metric='mae')
|
||||
|
||||
print(f'MAE={mae_score:.5f}')
|
||||
```
|
||||
|
||||
In this example, the system outputs:
|
||||
```
|
||||
[GridSearchQ]: starting model selection with self.n_jobs =-1
|
||||
[GridSearchQ]: hyperparams={'classifier__C': 0.01, 'nbins': 64} got mae score 0.04021 [took 1.1356s]
|
||||
[GridSearchQ]: hyperparams={'classifier__C': 0.01, 'nbins': 32} got mae score 0.04286 [took 1.2139s]
|
||||
[GridSearchQ]: hyperparams={'classifier__C': 0.01, 'nbins': 16} got mae score 0.04888 [took 1.2491s]
|
||||
[GridSearchQ]: hyperparams={'classifier__C': 0.001, 'nbins': 8} got mae score 0.05163 [took 1.5372s]
|
||||
[...]
|
||||
[GridSearchQ]: hyperparams={'classifier__C': 1000.0, 'nbins': 32} got mae score 0.02445 [took 2.9056s]
|
||||
[GridSearchQ]: optimization finished: best params {'classifier__C': 100.0, 'nbins': 32} (score=0.02234) [took 7.3114s]
|
||||
[GridSearchQ]: refitting on the whole development set
|
||||
model selection ended: best hyper-parameters={'classifier__C': 100.0, 'nbins': 32}
|
||||
MAE=0.03102
|
||||
```
|
||||
|
||||
The parameter _val_split_ can alternatively be used to indicate
|
||||
a validation set (i.e., an instance of _LabelledCollection_) instead
|
||||
of a proportion. This could be useful if one wants to have control
|
||||
on the specific data split to be used across different model selection
|
||||
experiments.
|
||||
|
||||
## Targeting a Classification-oriented loss
|
||||
|
||||
Optimizing a model for quantification could rather be
|
||||
computationally costly.
|
||||
In aggregative methods, one could alternatively try to optimize
|
||||
the classifier's hyper-parameters for classification.
|
||||
Although this is theoretically suboptimal, many articles in
|
||||
quantification literature have opted for this strategy.
|
||||
|
||||
In QuaPy, this is achieved by simply instantiating the
|
||||
classifier learner as a GridSearchCV from scikit-learn.
|
||||
The following code illustrates how to do that:
|
||||
|
||||
```python
|
||||
learner = GridSearchCV(
|
||||
LogisticRegression(),
|
||||
param_grid={'C': np.logspace(-4, 5, 10), 'class_weight': ['balanced', None]},
|
||||
cv=5)
|
||||
model = DistributionMatching(learner).fit(dataset.training)
|
||||
```
|
||||
|
||||
However, this is conceptually flawed, since the model should be
|
||||
optimized for the task at hand (quantification), and not for a surrogate task (classification),
|
||||
i.e., the model should be requested to deliver low quantification errors, rather
|
||||
than low classification errors.
|
||||
|
||||
|
||||
|
||||
|
|
@ -1,250 +0,0 @@
|
|||
# Plotting
|
||||
|
||||
The module _qp.plot_ implements some basic plotting functions
|
||||
that can help analyse the performance of a quantification method.
|
||||
|
||||
All plotting functions receive as inputs the outcomes of
|
||||
some experiments and include, for each experiment,
|
||||
the following three main arguments:
|
||||
|
||||
* _method_names_ a list containing the names of the quantification methods
|
||||
* _true_prevs_ a list containing matrices of true prevalences
|
||||
* _estim_prevs_ a list containing matrices of estimated prevalences
|
||||
(should be of the same shape as the corresponding matrix in _true_prevs_)
|
||||
|
||||
Note that a method (as indicated by a name in _method_names_) can
|
||||
appear more than once. This could occur when various datasets are
|
||||
involved in the experiments. In this case, all experiments for the
|
||||
method will be merged and the plot will represent the method's
|
||||
performance across various datasets.
|
||||
|
||||
This is a very simple example of a valid input for the plotting functions:
|
||||
```python
|
||||
method_names = ['classify & count', 'EMQ', 'classify & count']
|
||||
true_prevs = [
|
||||
np.array([[0.5, 0.5], [0.25, 0.75]]),
|
||||
np.array([[0.0, 1.0], [0.25, 0.75], [0.0, 0.1]]),
|
||||
np.array([[0.0, 1.0], [0.25, 0.75], [0.0, 0.1]]),
|
||||
]
|
||||
estim_prevs = [
|
||||
np.array([[0.45, 0.55], [0.6, 0.4]]),
|
||||
np.array([[0.0, 1.0], [0.5, 0.5], [0.2, 0.8]]),
|
||||
np.array([[0.1, 0.9], [0.3, 0.7], [0.0, 0.1]]),
|
||||
]
|
||||
```
|
||||
in which the _classify & count_ has been tested in two datasets and
|
||||
the _EMQ_ method has been tested only in one dataset. For the first
|
||||
experiment, only two (binary) quantifications have been tested,
|
||||
while for the second and third experiments three instances have
|
||||
been tested.
|
||||
|
||||
In general, we would like to test the performance of the
|
||||
quantification methods across different scenarios showcasing
|
||||
the accuracy of the quantifier in predicting class prevalences
|
||||
for a wide range of prior distributions. This can easily be
|
||||
achieved by means of the
|
||||
[artificial sampling protocol](https://github.com/HLT-ISTI/QuaPy/wiki/Protocols)
|
||||
that is implemented in QuaPy.
|
||||
|
||||
The following code shows how to perform one simple experiment
|
||||
in which the 4 _CC-variants_, all equipped with a linear SVM, are
|
||||
applied to one binary dataset of reviews about _Kindle_ devices and
|
||||
tested across the entire spectrum of class priors (taking 21 splits
|
||||
of the interval [0,1], i.e., using prevalence steps of 0.05, and
|
||||
generating 100 random samples at each prevalence).
|
||||
|
||||
```python
|
||||
import quapy as qp
|
||||
from protocol import APP
|
||||
from quapy.method.aggregative import CC, ACC, PCC, PACC
|
||||
from sklearn.svm import LinearSVC
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 500
|
||||
|
||||
def gen_data():
|
||||
|
||||
def base_classifier():
|
||||
return LinearSVC(class_weight='balanced')
|
||||
|
||||
def models():
|
||||
yield 'CC', CC(base_classifier())
|
||||
yield 'ACC', ACC(base_classifier())
|
||||
yield 'PCC', PCC(base_classifier())
|
||||
yield 'PACC', PACC(base_classifier())
|
||||
|
||||
train, test = qp.datasets.fetch_reviews('kindle', tfidf=True, min_df=5).train_test
|
||||
|
||||
method_names, true_prevs, estim_prevs, tr_prevs = [], [], [], []
|
||||
|
||||
for method_name, model in models():
|
||||
model.fit(train)
|
||||
true_prev, estim_prev = qp.evaluation.prediction(model, APP(test, repeats=100, random_state=0))
|
||||
|
||||
method_names.append(method_name)
|
||||
true_prevs.append(true_prev)
|
||||
estim_prevs.append(estim_prev)
|
||||
tr_prevs.append(train.prevalence())
|
||||
|
||||
return method_names, true_prevs, estim_prevs, tr_prevs
|
||||
|
||||
method_names, true_prevs, estim_prevs, tr_prevs = gen_data()
|
||||
````
|
||||
the plots that can be generated are explained below.
|
||||
|
||||
## Diagonal Plot
|
||||
|
||||
The _diagonal_ plot shows a very insightful view of the
|
||||
quantifier's performance. It plots the predicted class
|
||||
prevalence (in the y-axis) against the true class prevalence
|
||||
(in the x-axis). Unfortunately, it is limited to binary quantification,
|
||||
although one can simply generate as many _diagonal_ plots as
|
||||
classes there are by indicating which class should be considered
|
||||
the target of the plot.
|
||||
|
||||
The following call will produce the plot:
|
||||
|
||||
```python
|
||||
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, train_prev=tr_prevs[0], savepath='./plots/bin_diag.png')
|
||||
```
|
||||
|
||||
the last argument is optional, and indicates the path where to save
|
||||
the plot (the file extension will determine the format -- typical extensions
|
||||
are '.png' or '.pdf'). If this path is not provided, then the plot
|
||||
will be shown but not saved.
|
||||
The resulting plot should look like:
|
||||
|
||||
|
||||
|
||||
Note that in this case, we are also indicating the training
|
||||
prevalence, which is plotted in the diagonal a as cyan dot.
|
||||
The color bands indicate the standard deviations of the predictions,
|
||||
and can be hidden by setting the argument _show_std=False_ (see
|
||||
the complete list of arguments in the documentation).
|
||||
|
||||
Finally, note how most quantifiers, and specially the "unadjusted"
|
||||
variants CC and PCC, are strongly biased towards the
|
||||
prevalence seen during training.
|
||||
|
||||
## Quantification bias
|
||||
|
||||
This plot aims at evincing the bias that any quantifier
|
||||
displays with respect to the training prevalences by
|
||||
means of [box plots](https://en.wikipedia.org/wiki/Box_plot).
|
||||
This plot can be generated by:
|
||||
|
||||
```python
|
||||
qp.plot.binary_bias_global(method_names, true_prevs, estim_prevs, savepath='./plots/bin_bias.png')
|
||||
```
|
||||
|
||||
and should look like:
|
||||
|
||||
|
||||
|
||||
The box plots show some interesting facts:
|
||||
* all methods are biased towards the training prevalence but specially
|
||||
so CC and PCC (an unbiased quantifier would have a box centered at 0)
|
||||
* the bias is always positive, indicating that all methods tend to
|
||||
overestimate the positive class prevalence
|
||||
* CC and PCC have high variability while ACC and specially PACC exhibit
|
||||
lower variability.
|
||||
|
||||
Again, these plots could be generated for experiments ranging across
|
||||
different datasets, and the plot will merge all data accordingly.
|
||||
|
||||
Another illustrative example can be shown that consists of
|
||||
training different CC quantifiers trained at different
|
||||
(artificially sampled) training prevalences.
|
||||
For this example, we generate training samples of 5000
|
||||
documents containing 10%, 20%, ..., 90% of positives from the
|
||||
IMDb dataset, and generate the bias plot again.
|
||||
This example can be run by rewritting the _gen_data()_ function
|
||||
like this:
|
||||
|
||||
```python
|
||||
def gen_data():
|
||||
|
||||
train, test = qp.datasets.fetch_reviews('imdb', tfidf=True, min_df=5).train_test
|
||||
model = CC(LinearSVC())
|
||||
|
||||
method_data = []
|
||||
for training_prevalence in np.linspace(0.1, 0.9, 9):
|
||||
training_size = 5000
|
||||
# since the problem is binary, it suffices to specify the negative prevalence, since the positive is constrained
|
||||
train_sample = train.sampling(training_size, 1-training_prevalence)
|
||||
model.fit(train_sample)
|
||||
true_prev, estim_prev = qp.evaluation.prediction(model, APP(test, repeats=100, random_state=0))
|
||||
method_name = 'CC$_{'+f'{int(100*training_prevalence)}' + '\%}$'
|
||||
method_data.append((method_name, true_prev, estim_prev, train_sample.prevalence()))
|
||||
|
||||
return zip(*method_data)
|
||||
```
|
||||
|
||||
and the plot should now look like:
|
||||
|
||||
|
||||
|
||||
which clearly shows a negative bias for CC variants trained on
|
||||
data containing more negatives (i.e., < 50%) and positive biases
|
||||
in cases containing more positives (i.e., >50%). The CC trained
|
||||
at 50% behaves as an unbiased estimator of the positive class
|
||||
prevalence.
|
||||
|
||||
The function _qp.plot.binary_bias_bins_ allows the user to
|
||||
generate box plots broken down by bins of true test prevalence.
|
||||
To this aim, an argument _nbins_ is passed which indicates
|
||||
how many isometric subintervals to take. For example
|
||||
the following plot is produced for _nbins=3_:
|
||||
|
||||
|
||||
|
||||
Interestingly enough, the seemingly unbiased estimator (CC at 50%) happens to display
|
||||
a positive bias (or a tendency to overestimate) in cases of low prevalence
|
||||
(i.e., when the true prevalence of the positive class is below 33%),
|
||||
and a negative bias (or a tendency to underestimate) in cases of high prevalence
|
||||
(i.e., when the true prevalence is beyond 67%).
|
||||
|
||||
Out of curiosity, the diagonal plot for this experiment looks like:
|
||||
|
||||
|
||||
|
||||
showing pretty clearly the dependency of CC on the prior probabilities
|
||||
of the labeled set it was trained on.
|
||||
|
||||
|
||||
## Error by Drift
|
||||
|
||||
Above discussed plots are useful for analyzing and comparing
|
||||
the performance of different quantification methods, but are
|
||||
limited to the binary case. The "error by drift" is a plot
|
||||
that shows the error in predictions as a function of the
|
||||
(prior probability) drift between each test sample and the
|
||||
training set. Interestingly, the error and drift can both be measured
|
||||
in terms of any evaluation measure for quantification (like the
|
||||
ones available in _qp.error_) and can thus be computed
|
||||
irrespectively of the number of classes.
|
||||
|
||||
The following shows how to generate the plot for the 4 CC variants,
|
||||
using 10 bins for the drift
|
||||
and _absolute error_ as the measure of the error (the
|
||||
drift in the x-axis is always computed in terms of _absolute error_ since
|
||||
other errors are harder to interpret):
|
||||
|
||||
```python
|
||||
qp.plot.error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs,
|
||||
error_name='ae', n_bins=10, savepath='./plots/err_drift.png')
|
||||
```
|
||||
|
||||
|
||||
|
||||
Note that all methods work reasonably well in cases of low prevalence
|
||||
drift (i.e., any CC-variant is a good quantifier whenever the IID
|
||||
assumption is approximately preserved). The higher the drift, the worse
|
||||
those quantifiers tend to perform, although it is clear that PACC
|
||||
yields the lowest error for the most difficult cases.
|
||||
|
||||
Remember that any plot can be generated _across many datasets_, and
|
||||
that this would probably result in a more solid comparison.
|
||||
In those cases, however, it is likely that the variances of each
|
||||
method get higher, to the detriment of the visualization.
|
||||
We recommend to set _show_std=False_ in those cases
|
||||
in order to hide the color bands.
|
||||
|
|
@ -1,87 +1,36 @@
|
|||
.. QuaPy documentation master file, created by
|
||||
sphinx-quickstart on Tue Nov 9 11:31:32 2021.
|
||||
.. QuaPy: A Python-based open-source framework for quantification documentation master file, created by
|
||||
sphinx-quickstart on Wed Feb 7 16:26:46 2024.
|
||||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
Welcome to QuaPy's documentation!
|
||||
=================================
|
||||
==========================================================================================
|
||||
|
||||
QuaPy is an open source framework for Quantification (a.k.a. Supervised Prevalence Estimation)
|
||||
written in Python.
|
||||
QuaPy is a Python-based open-source framework for quantification.
|
||||
|
||||
Introduction
|
||||
This document contains the API of the modules included in QuaPy.
|
||||
|
||||
Installation
|
||||
------------
|
||||
|
||||
QuaPy roots on the concept of data sample, and provides implementations of most important concepts
|
||||
in quantification literature, such as the most important quantification baselines, many advanced
|
||||
quantification methods, quantification-oriented model selection, many evaluation measures and protocols
|
||||
used for evaluating quantification methods.
|
||||
QuaPy also integrates commonly used datasets and offers visualization tools for facilitating the analysis and
|
||||
interpretation of results.
|
||||
`pip install quapy`
|
||||
|
||||
A quick example:
|
||||
****************
|
||||
GitHub
|
||||
------------
|
||||
|
||||
The following script fetchs a Twitter dataset, trains and evaluates an
|
||||
`Adjusted Classify & Count` model in terms of the `Mean Absolute Error` (MAE)
|
||||
between the class prevalences estimated for the test set and the true prevalences
|
||||
of the test set.
|
||||
QuaPy is hosted in GitHub at `https://github.com/HLT-ISTI/QuaPy <https://github.com/HLT-ISTI/QuaPy>`_
|
||||
|
||||
::
|
||||
|
||||
import quapy as qp
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
dataset = qp.datasets.fetch_twitter('semeval16')
|
||||
|
||||
# create an "Adjusted Classify & Count" quantifier
|
||||
model = qp.method.aggregative.ACC(LogisticRegression())
|
||||
model.fit(dataset.training)
|
||||
|
||||
estim_prevalences = model.quantify(dataset.test.instances)
|
||||
true_prevalences = dataset.test.prevalence()
|
||||
|
||||
error = qp.error.mae(true_prevalences, estim_prevalences)
|
||||
|
||||
print(f'Mean Absolute Error (MAE)={error:.3f}')
|
||||
|
||||
|
||||
Quantification is useful in scenarios of prior probability shift. In other
|
||||
words, we would not be interested in estimating the class prevalences of the test set if
|
||||
we could assume the IID assumption to hold, as this prevalence would simply coincide with the
|
||||
class prevalence of the training set. For this reason, any Quantification model
|
||||
should be tested across samples characterized by different class prevalences.
|
||||
QuaPy implements sampling procedures and evaluation protocols that automates this endeavour.
|
||||
See the :doc:`Evaluation` for detailed examples.
|
||||
|
||||
Features
|
||||
********
|
||||
|
||||
* Implementation of most popular quantification methods (Classify-&-Count variants, Expectation-Maximization, SVM-based variants for quantification, HDy, QuaNet, and Ensembles).
|
||||
* Versatile functionality for performing evaluation based on artificial sampling protocols.
|
||||
* Implementation of most commonly used evaluation metrics (e.g., MAE, MRAE, MSE, NKLD, etc.).
|
||||
* Popular datasets for Quantification (textual and numeric) available, including:
|
||||
* 32 UCI Machine Learning datasets.
|
||||
* 11 Twitter Sentiment datasets.
|
||||
* 3 Reviews Sentiment datasets.
|
||||
* 4 tasks from LeQua competition (_new in v0.1.7!_)
|
||||
* Native supports for binary and single-label scenarios of quantification.
|
||||
* Model selection functionality targeting quantification-oriented losses.
|
||||
* Visualization tools for analysing results.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:caption: Contents:
|
||||
|
||||
Installation
|
||||
Datasets
|
||||
Evaluation
|
||||
Protocols
|
||||
Methods
|
||||
Model-Selection
|
||||
Plotting
|
||||
API Developers documentation<modules>
|
||||
Contents
|
||||
--------
|
||||
|
||||
.. toctree::
|
||||
|
||||
modules
|
||||
|
||||
|
||||
Indices and tables
|
||||
|
|
|
|||
|
|
@ -1,38 +1,35 @@
|
|||
:tocdepth: 2
|
||||
|
||||
quapy.classification package
|
||||
============================
|
||||
|
||||
Submodules
|
||||
----------
|
||||
|
||||
quapy.classification.calibration
|
||||
--------------------------------
|
||||
quapy.classification.calibration module
|
||||
---------------------------------------
|
||||
|
||||
.. versionadded:: 0.1.7
|
||||
.. automodule:: quapy.classification.calibration
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.classification.methods
|
||||
----------------------------
|
||||
quapy.classification.methods module
|
||||
-----------------------------------
|
||||
|
||||
.. automodule:: quapy.classification.methods
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.classification.neural
|
||||
---------------------------
|
||||
quapy.classification.neural module
|
||||
----------------------------------
|
||||
|
||||
.. automodule:: quapy.classification.neural
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.classification.svmperf
|
||||
----------------------------
|
||||
quapy.classification.svmperf module
|
||||
-----------------------------------
|
||||
|
||||
.. automodule:: quapy.classification.svmperf
|
||||
:members:
|
||||
|
|
|
|||
|
|
@ -1,37 +1,36 @@
|
|||
:tocdepth: 2
|
||||
|
||||
quapy.data package
|
||||
==================
|
||||
|
||||
Submodules
|
||||
----------
|
||||
|
||||
quapy.data.base
|
||||
---------------
|
||||
quapy.data.base module
|
||||
----------------------
|
||||
|
||||
.. automodule:: quapy.data.base
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.data.datasets
|
||||
-------------------
|
||||
quapy.data.datasets module
|
||||
--------------------------
|
||||
|
||||
.. automodule:: quapy.data.datasets
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.data.preprocessing
|
||||
------------------------
|
||||
|
||||
quapy.data.preprocessing module
|
||||
-------------------------------
|
||||
|
||||
.. automodule:: quapy.data.preprocessing
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.data.reader
|
||||
-----------------
|
||||
quapy.data.reader module
|
||||
------------------------
|
||||
|
||||
.. automodule:: quapy.data.reader
|
||||
:members:
|
||||
|
|
|
|||
|
|
@ -1,45 +1,51 @@
|
|||
:tocdepth: 2
|
||||
|
||||
quapy.method package
|
||||
====================
|
||||
|
||||
Submodules
|
||||
----------
|
||||
|
||||
quapy.method.aggregative
|
||||
------------------------
|
||||
quapy.method.aggregative module
|
||||
-------------------------------
|
||||
|
||||
.. automodule:: quapy.method.aggregative
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.method.base
|
||||
-----------------
|
||||
.. automodule:: quapy.method._kdey
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
.. automodule:: quapy.method._neural
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
.. automodule:: quapy.method._threshold_optim
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
|
||||
quapy.method.base module
|
||||
------------------------
|
||||
|
||||
.. automodule:: quapy.method.base
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.method.meta
|
||||
-----------------
|
||||
quapy.method.meta module
|
||||
------------------------
|
||||
|
||||
.. automodule:: quapy.method.meta
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.method.neural
|
||||
-------------------
|
||||
|
||||
.. automodule:: quapy.method.neural
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.method.non\_aggregative
|
||||
-----------------------------
|
||||
quapy.method.non\_aggregative module
|
||||
------------------------------------
|
||||
|
||||
.. automodule:: quapy.method.non_aggregative
|
||||
:members:
|
||||
|
|
|
|||
|
|
@ -1,79 +1,76 @@
|
|||
:tocdepth: 2
|
||||
|
||||
quapy package
|
||||
=============
|
||||
|
||||
Subpackages
|
||||
-----------
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 4
|
||||
|
||||
quapy.classification
|
||||
quapy.data
|
||||
quapy.method
|
||||
|
||||
|
||||
Submodules
|
||||
----------
|
||||
|
||||
quapy.error
|
||||
-----------
|
||||
quapy.error module
|
||||
------------------
|
||||
|
||||
.. automodule:: quapy.error
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.evaluation
|
||||
----------------
|
||||
quapy.evaluation module
|
||||
-----------------------
|
||||
|
||||
.. automodule:: quapy.evaluation
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.protocol
|
||||
--------------
|
||||
|
||||
.. versionadded:: 0.1.7
|
||||
.. automodule:: quapy.protocol
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.functional
|
||||
----------------
|
||||
quapy.functional module
|
||||
-----------------------
|
||||
|
||||
.. automodule:: quapy.functional
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.model\_selection
|
||||
----------------------
|
||||
quapy.model\_selection module
|
||||
-----------------------------
|
||||
|
||||
.. automodule:: quapy.model_selection
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.plot
|
||||
----------
|
||||
quapy.plot module
|
||||
-----------------
|
||||
|
||||
.. automodule:: quapy.plot
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.util
|
||||
----------
|
||||
quapy.protocol module
|
||||
---------------------
|
||||
|
||||
.. automodule:: quapy.protocol
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
quapy.util module
|
||||
-----------------
|
||||
|
||||
.. automodule:: quapy.util
|
||||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
Subpackages
|
||||
-----------
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 3
|
||||
|
||||
quapy.classification
|
||||
quapy.data
|
||||
quapy.method
|
||||
|
||||
|
||||
Module contents
|
||||
---------------
|
||||
|
||||
|
|
@ -81,4 +78,3 @@ Module contents
|
|||
:members:
|
||||
:undoc-members:
|
||||
:show-inheritance:
|
||||
|
||||
|
|
|
|||
Binary file not shown.
|
Before Width: | Height: | Size: 78 B |
|
|
@ -4,7 +4,7 @@
|
|||
*
|
||||
* Sphinx stylesheet -- basic theme.
|
||||
*
|
||||
* :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
|
||||
* :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
|
||||
* :license: BSD, see LICENSE for details.
|
||||
*
|
||||
*/
|
||||
|
|
@ -55,7 +55,7 @@ div.sphinxsidebarwrapper {
|
|||
|
||||
div.sphinxsidebar {
|
||||
float: left;
|
||||
width: 210px;
|
||||
width: 230px;
|
||||
margin-left: -100%;
|
||||
font-size: 90%;
|
||||
word-wrap: break-word;
|
||||
|
|
@ -237,6 +237,10 @@ a.headerlink {
|
|||
visibility: hidden;
|
||||
}
|
||||
|
||||
a:visited {
|
||||
color: #551A8B;
|
||||
}
|
||||
|
||||
h1:hover > a.headerlink,
|
||||
h2:hover > a.headerlink,
|
||||
h3:hover > a.headerlink,
|
||||
|
|
@ -324,6 +328,7 @@ aside.sidebar {
|
|||
p.sidebar-title {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
nav.contents,
|
||||
aside.topic,
|
||||
div.admonition, div.topic, blockquote {
|
||||
|
|
@ -331,6 +336,7 @@ div.admonition, div.topic, blockquote {
|
|||
}
|
||||
|
||||
/* -- topics ---------------------------------------------------------------- */
|
||||
|
||||
nav.contents,
|
||||
aside.topic,
|
||||
div.topic {
|
||||
|
|
@ -606,6 +612,7 @@ ol.simple p,
|
|||
ul.simple p {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
aside.footnote > span,
|
||||
div.citation > span {
|
||||
float: left;
|
||||
|
|
@ -667,6 +674,16 @@ dd {
|
|||
margin-left: 30px;
|
||||
}
|
||||
|
||||
.sig dd {
|
||||
margin-top: 0px;
|
||||
margin-bottom: 0px;
|
||||
}
|
||||
|
||||
.sig dl {
|
||||
margin-top: 0px;
|
||||
margin-bottom: 0px;
|
||||
}
|
||||
|
||||
dl > dd:last-child,
|
||||
dl > dd:last-child > :last-child {
|
||||
margin-bottom: 0;
|
||||
|
|
@ -735,6 +752,14 @@ abbr, acronym {
|
|||
cursor: help;
|
||||
}
|
||||
|
||||
.translated {
|
||||
background-color: rgba(207, 255, 207, 0.2)
|
||||
}
|
||||
|
||||
.untranslated {
|
||||
background-color: rgba(255, 207, 207, 0.2)
|
||||
}
|
||||
|
||||
/* -- code displays --------------------------------------------------------- */
|
||||
|
||||
pre {
|
||||
|
|
|
|||
|
|
@ -1,508 +0,0 @@
|
|||
/*
|
||||
* bizstyle.css_t
|
||||
* ~~~~~~~~~~~~~~
|
||||
*
|
||||
* Sphinx stylesheet -- business style theme.
|
||||
*
|
||||
* :copyright: Copyright 2011-2014 by Sphinx team, see AUTHORS.
|
||||
* :license: BSD, see LICENSE for details.
|
||||
*
|
||||
*/
|
||||
|
||||
@import url("basic.css");
|
||||
|
||||
/* -- page layout ----------------------------------------------------------- */
|
||||
|
||||
body {
|
||||
font-family: 'Lucida Grande', 'Lucida Sans Unicode', 'Geneva',
|
||||
'Verdana', sans-serif;
|
||||
font-size: 14px;
|
||||
letter-spacing: -0.01em;
|
||||
line-height: 150%;
|
||||
text-align: center;
|
||||
background-color: white;
|
||||
background-image: url(background_b01.png);
|
||||
color: black;
|
||||
padding: 0;
|
||||
border-right: 1px solid #336699;
|
||||
border-left: 1px solid #336699;
|
||||
|
||||
margin: 0px 40px 0px 40px;
|
||||
}
|
||||
|
||||
div.document {
|
||||
background-color: white;
|
||||
text-align: left;
|
||||
background-repeat: repeat-x;
|
||||
|
||||
-moz-box-shadow: 2px 2px 5px #000;
|
||||
-webkit-box-shadow: 2px 2px 5px #000;
|
||||
}
|
||||
|
||||
div.documentwrapper {
|
||||
float: left;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
div.bodywrapper {
|
||||
margin: 0 0 0 240px;
|
||||
border-left: 1px solid #ccc;
|
||||
}
|
||||
|
||||
div.body {
|
||||
margin: 0;
|
||||
padding: 0.5em 20px 20px 20px;
|
||||
}
|
||||
div.bodywrapper {
|
||||
margin: 0 0 0 calc(210px + 30px);
|
||||
}
|
||||
|
||||
div.related {
|
||||
font-size: 1em;
|
||||
|
||||
-moz-box-shadow: 2px 2px 5px #000;
|
||||
-webkit-box-shadow: 2px 2px 5px #000;
|
||||
}
|
||||
|
||||
div.related ul {
|
||||
background-color: #336699;
|
||||
height: 100%;
|
||||
overflow: hidden;
|
||||
border-top: 1px solid #ddd;
|
||||
border-bottom: 1px solid #ddd;
|
||||
}
|
||||
|
||||
div.related ul li {
|
||||
color: white;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
height: 2em;
|
||||
float: left;
|
||||
}
|
||||
|
||||
div.related ul li.right {
|
||||
float: right;
|
||||
margin-right: 5px;
|
||||
}
|
||||
|
||||
div.related ul li a {
|
||||
margin: 0;
|
||||
padding: 0 5px 0 5px;
|
||||
line-height: 1.75em;
|
||||
color: #fff;
|
||||
}
|
||||
|
||||
div.related ul li a:hover {
|
||||
color: #fff;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
div.sphinxsidebarwrapper {
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
div.sphinxsidebar {
|
||||
padding: 0.5em 12px 12px 12px;
|
||||
width: 210px;
|
||||
font-size: 1em;
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
div.sphinxsidebar h3, div.sphinxsidebar h4 {
|
||||
margin: 1em 0 0.5em 0;
|
||||
font-size: 1em;
|
||||
padding: 0.1em 0 0.1em 0.5em;
|
||||
color: white;
|
||||
border: 1px solid #336699;
|
||||
background-color: #336699;
|
||||
}
|
||||
|
||||
div.sphinxsidebar h3 a {
|
||||
color: white;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul {
|
||||
padding-left: 1.5em;
|
||||
margin-top: 7px;
|
||||
padding: 0;
|
||||
line-height: 130%;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul ul {
|
||||
margin-left: 20px;
|
||||
}
|
||||
|
||||
div.sphinxsidebar input {
|
||||
border: 1px solid #336699;
|
||||
}
|
||||
|
||||
div.footer {
|
||||
background-color: white;
|
||||
color: #336699;
|
||||
padding: 3px 8px 3px 0;
|
||||
clear: both;
|
||||
font-size: 0.8em;
|
||||
text-align: right;
|
||||
border-bottom: 1px solid #336699;
|
||||
|
||||
-moz-box-shadow: 2px 2px 5px #000;
|
||||
-webkit-box-shadow: 2px 2px 5px #000;
|
||||
}
|
||||
|
||||
div.footer a {
|
||||
color: #336699;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
/* -- body styles ----------------------------------------------------------- */
|
||||
|
||||
p {
|
||||
margin: 0.8em 0 0.5em 0;
|
||||
}
|
||||
|
||||
a {
|
||||
color: #336699;
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
color: #336699;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
div.body a {
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
h1, h2, h3 {
|
||||
color: #336699;
|
||||
}
|
||||
|
||||
h1 {
|
||||
margin: 0;
|
||||
padding: 0.7em 0 0.3em 0;
|
||||
font-size: 1.5em;
|
||||
}
|
||||
|
||||
h2 {
|
||||
margin: 1.3em 0 0.2em 0;
|
||||
font-size: 1.35em;
|
||||
padding-bottom: .5em;
|
||||
border-bottom: 1px solid #336699;
|
||||
}
|
||||
|
||||
h3 {
|
||||
margin: 1em 0 -0.3em 0;
|
||||
font-size: 1.2em;
|
||||
padding-bottom: .3em;
|
||||
border-bottom: 1px solid #CCCCCC;
|
||||
}
|
||||
|
||||
div.body h1 a, div.body h2 a, div.body h3 a,
|
||||
div.body h4 a, div.body h5 a, div.body h6 a {
|
||||
color: black!important;
|
||||
}
|
||||
|
||||
h1 a.anchor, h2 a.anchor, h3 a.anchor,
|
||||
h4 a.anchor, h5 a.anchor, h6 a.anchor {
|
||||
display: none;
|
||||
margin: 0 0 0 0.3em;
|
||||
padding: 0 0.2em 0 0.2em;
|
||||
color: #aaa!important;
|
||||
}
|
||||
|
||||
h1:hover a.anchor, h2:hover a.anchor, h3:hover a.anchor, h4:hover a.anchor,
|
||||
h5:hover a.anchor, h6:hover a.anchor {
|
||||
display: inline;
|
||||
}
|
||||
|
||||
h1 a.anchor:hover, h2 a.anchor:hover, h3 a.anchor:hover, h4 a.anchor:hover,
|
||||
h5 a.anchor:hover, h6 a.anchor:hover {
|
||||
color: #777;
|
||||
background-color: #eee;
|
||||
}
|
||||
|
||||
a.headerlink {
|
||||
color: #c60f0f!important;
|
||||
font-size: 1em;
|
||||
margin-left: 6px;
|
||||
padding: 0 4px 0 4px;
|
||||
text-decoration: none!important;
|
||||
}
|
||||
|
||||
a.headerlink:hover {
|
||||
background-color: #ccc;
|
||||
color: white!important;
|
||||
}
|
||||
|
||||
cite, code, tt {
|
||||
font-family: 'Consolas', 'Deja Vu Sans Mono',
|
||||
'Bitstream Vera Sans Mono', monospace;
|
||||
font-size: 0.95em;
|
||||
letter-spacing: 0.01em;
|
||||
}
|
||||
|
||||
code {
|
||||
background-color: #F2F2F2;
|
||||
border-bottom: 1px solid #ddd;
|
||||
color: #333;
|
||||
}
|
||||
|
||||
code.descname, code.descclassname, code.xref {
|
||||
border: 0;
|
||||
}
|
||||
|
||||
hr {
|
||||
border: 1px solid #abc;
|
||||
margin: 2em;
|
||||
}
|
||||
|
||||
a code {
|
||||
border: 0;
|
||||
color: #CA7900;
|
||||
}
|
||||
|
||||
a code:hover {
|
||||
color: #2491CF;
|
||||
}
|
||||
|
||||
pre {
|
||||
background-color: transparent !important;
|
||||
font-family: 'Consolas', 'Deja Vu Sans Mono',
|
||||
'Bitstream Vera Sans Mono', monospace;
|
||||
font-size: 0.95em;
|
||||
letter-spacing: 0.015em;
|
||||
line-height: 120%;
|
||||
padding: 0.5em;
|
||||
border-right: 5px solid #ccc;
|
||||
border-left: 5px solid #ccc;
|
||||
}
|
||||
|
||||
pre a {
|
||||
color: inherit;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
td.linenos pre {
|
||||
padding: 0.5em 0;
|
||||
}
|
||||
|
||||
div.quotebar {
|
||||
background-color: #f8f8f8;
|
||||
max-width: 250px;
|
||||
float: right;
|
||||
padding: 2px 7px;
|
||||
border: 1px solid #ccc;
|
||||
}
|
||||
nav.contents,
|
||||
aside.topic,
|
||||
|
||||
div.topic {
|
||||
background-color: #f8f8f8;
|
||||
}
|
||||
|
||||
table {
|
||||
border-collapse: collapse;
|
||||
margin: 0 -0.5em 0 -0.5em;
|
||||
}
|
||||
|
||||
table td, table th {
|
||||
padding: 0.2em 0.5em 0.2em 0.5em;
|
||||
}
|
||||
|
||||
div.admonition {
|
||||
font-size: 0.9em;
|
||||
margin: 1em 0 1em 0;
|
||||
border: 3px solid #cccccc;
|
||||
background-color: #f7f7f7;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
div.admonition p {
|
||||
margin: 0.5em 1em 0.5em 1em;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
div.admonition li p {
|
||||
margin-left: 0;
|
||||
}
|
||||
|
||||
div.admonition pre, div.warning pre {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
div.highlight {
|
||||
margin: 0.4em 1em;
|
||||
}
|
||||
|
||||
div.admonition p.admonition-title {
|
||||
margin: 0;
|
||||
padding: 0.1em 0 0.1em 0.5em;
|
||||
color: white;
|
||||
border-bottom: 3px solid #cccccc;
|
||||
font-weight: bold;
|
||||
background-color: #165e83;
|
||||
}
|
||||
|
||||
div.danger { border: 3px solid #f0908d; background-color: #f0cfa0; }
|
||||
div.error { border: 3px solid #f0908d; background-color: #ede4cd; }
|
||||
div.warning { border: 3px solid #f8b862; background-color: #f0cfa0; }
|
||||
div.caution { border: 3px solid #f8b862; background-color: #ede4cd; }
|
||||
div.attention { border: 3px solid #f8b862; background-color: #f3f3f3; }
|
||||
div.important { border: 3px solid #f0cfa0; background-color: #ede4cd; }
|
||||
div.note { border: 3px solid #f0cfa0; background-color: #f3f3f3; }
|
||||
div.hint { border: 3px solid #bed2c3; background-color: #f3f3f3; }
|
||||
div.tip { border: 3px solid #bed2c3; background-color: #f3f3f3; }
|
||||
|
||||
div.danger p.admonition-title, div.error p.admonition-title {
|
||||
background-color: #b7282e;
|
||||
border-bottom: 3px solid #f0908d;
|
||||
}
|
||||
|
||||
div.caution p.admonition-title,
|
||||
div.warning p.admonition-title,
|
||||
div.attention p.admonition-title {
|
||||
background-color: #f19072;
|
||||
border-bottom: 3px solid #f8b862;
|
||||
}
|
||||
|
||||
div.note p.admonition-title, div.important p.admonition-title {
|
||||
background-color: #f8b862;
|
||||
border-bottom: 3px solid #f0cfa0;
|
||||
}
|
||||
|
||||
div.hint p.admonition-title, div.tip p.admonition-title {
|
||||
background-color: #7ebea5;
|
||||
border-bottom: 3px solid #bed2c3;
|
||||
}
|
||||
|
||||
div.admonition ul, div.admonition ol,
|
||||
div.warning ul, div.warning ol {
|
||||
margin: 0.1em 0.5em 0.5em 3em;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
div.versioninfo {
|
||||
margin: 1em 0 0 0;
|
||||
border: 1px solid #ccc;
|
||||
background-color: #DDEAF0;
|
||||
padding: 8px;
|
||||
line-height: 1.3em;
|
||||
font-size: 0.9em;
|
||||
}
|
||||
|
||||
.viewcode-back {
|
||||
font-family: 'Lucida Grande', 'Lucida Sans Unicode', 'Geneva',
|
||||
'Verdana', sans-serif;
|
||||
}
|
||||
|
||||
div.viewcode-block:target {
|
||||
background-color: #f4debf;
|
||||
border-top: 1px solid #ac9;
|
||||
border-bottom: 1px solid #ac9;
|
||||
}
|
||||
|
||||
p.versionchanged span.versionmodified {
|
||||
font-size: 0.9em;
|
||||
margin-right: 0.2em;
|
||||
padding: 0.1em;
|
||||
background-color: #DCE6A0;
|
||||
}
|
||||
|
||||
dl.field-list > dt {
|
||||
color: white;
|
||||
background-color: #82A0BE;
|
||||
}
|
||||
|
||||
dl.field-list > dd {
|
||||
background-color: #f7f7f7;
|
||||
}
|
||||
|
||||
/* -- table styles ---------------------------------------------------------- */
|
||||
|
||||
table.docutils {
|
||||
margin: 1em 0;
|
||||
padding: 0;
|
||||
border: 1px solid white;
|
||||
background-color: #f7f7f7;
|
||||
}
|
||||
|
||||
table.docutils td, table.docutils th {
|
||||
padding: 1px 8px 1px 5px;
|
||||
border-top: 0;
|
||||
border-left: 0;
|
||||
border-right: 1px solid white;
|
||||
border-bottom: 1px solid white;
|
||||
}
|
||||
|
||||
table.docutils td p {
|
||||
margin-top: 0;
|
||||
margin-bottom: 0.3em;
|
||||
}
|
||||
|
||||
table.field-list td, table.field-list th {
|
||||
border: 0 !important;
|
||||
word-break: break-word;
|
||||
}
|
||||
|
||||
table.footnote td, table.footnote th {
|
||||
border: 0 !important;
|
||||
}
|
||||
|
||||
th {
|
||||
color: white;
|
||||
text-align: left;
|
||||
padding-right: 5px;
|
||||
background-color: #82A0BE;
|
||||
}
|
||||
|
||||
div.literal-block-wrapper div.code-block-caption {
|
||||
background-color: #EEE;
|
||||
border-style: solid;
|
||||
border-color: #CCC;
|
||||
border-width: 1px 5px;
|
||||
}
|
||||
|
||||
/* WIDE DESKTOP STYLE */
|
||||
@media only screen and (min-width: 1176px) {
|
||||
body {
|
||||
margin: 0 40px 0 40px;
|
||||
}
|
||||
}
|
||||
|
||||
/* TABLET STYLE */
|
||||
@media only screen and (min-width: 768px) and (max-width: 991px) {
|
||||
body {
|
||||
margin: 0 40px 0 40px;
|
||||
}
|
||||
}
|
||||
|
||||
/* MOBILE LAYOUT (PORTRAIT/320px) */
|
||||
@media only screen and (max-width: 767px) {
|
||||
body {
|
||||
margin: 0;
|
||||
}
|
||||
div.bodywrapper {
|
||||
margin: 0;
|
||||
width: 100%;
|
||||
border: none;
|
||||
}
|
||||
div.sphinxsidebar {
|
||||
display: none;
|
||||
}
|
||||
}
|
||||
|
||||
/* MOBILE LAYOUT (LANDSCAPE/480px) */
|
||||
@media only screen and (min-width: 480px) and (max-width: 767px) {
|
||||
body {
|
||||
margin: 0 20px 0 20px;
|
||||
}
|
||||
}
|
||||
|
||||
/* RETINA OVERRIDES */
|
||||
@media
|
||||
only screen and (-webkit-min-device-pixel-ratio: 2),
|
||||
only screen and (min-device-pixel-ratio: 2) {
|
||||
}
|
||||
|
||||
/* -- end ------------------------------------------------------------------- */
|
||||
|
|
@ -1,30 +0,0 @@
|
|||
//
|
||||
// bizstyle.js
|
||||
// ~~~~~~~~~~~
|
||||
//
|
||||
// Sphinx javascript -- for bizstyle theme.
|
||||
//
|
||||
// This theme was created by referring to 'sphinxdoc'
|
||||
//
|
||||
// :copyright: Copyright 2012-2014 by Sphinx team, see AUTHORS.
|
||||
// :license: BSD, see LICENSE for details.
|
||||
//
|
||||
const initialiseBizStyle = () => {
|
||||
if (navigator.userAgent.indexOf("iPhone") > 0 || navigator.userAgent.indexOf("Android") > 0) {
|
||||
document.querySelector("li.nav-item-0 a").innerText = "Top"
|
||||
}
|
||||
const truncator = item => {if (item.textContent.length > 20) {
|
||||
item.title = item.innerText
|
||||
item.innerText = item.innerText.substr(0, 17) + "..."
|
||||
}
|
||||
}
|
||||
document.querySelectorAll("div.related:first ul li:not(.right) a").slice(1).forEach(truncator);
|
||||
document.querySelectorAll("div.related:last ul li:not(.right) a").slice(1).forEach(truncator);
|
||||
}
|
||||
|
||||
window.addEventListener("resize",
|
||||
() => (document.querySelector("li.nav-item-0 a").innerText = (window.innerWidth <= 776) ? "Top" : "QuaPy 0.1.7 documentation")
|
||||
)
|
||||
|
||||
if (document.readyState !== "loading") initialiseBizStyle()
|
||||
else document.addEventListener("DOMContentLoaded", initialiseBizStyle)
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
|
|
@ -4,7 +4,7 @@
|
|||
*
|
||||
* Base JavaScript utilities for all Sphinx HTML documentation.
|
||||
*
|
||||
* :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
|
||||
* :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
|
||||
* :license: BSD, see LICENSE for details.
|
||||
*
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -1,6 +1,5 @@
|
|||
var DOCUMENTATION_OPTIONS = {
|
||||
URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
|
||||
VERSION: '0.1.7',
|
||||
const DOCUMENTATION_OPTIONS = {
|
||||
VERSION: '0.1.8',
|
||||
LANGUAGE: 'en',
|
||||
COLLAPSE_INDEX: false,
|
||||
BUILDER: 'html',
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
* This script contains the language-specific data used by searchtools.js,
|
||||
* namely the list of stopwords, stemmer, scorer and splitter.
|
||||
*
|
||||
* :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
|
||||
* :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
|
||||
* :license: BSD, see LICENSE for details.
|
||||
*
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -1,74 +1,74 @@
|
|||
pre { line-height: 125%; }
|
||||
td.linenos .normal { color: #666666; background-color: transparent; padding-left: 5px; padding-right: 5px; }
|
||||
span.linenos { color: #666666; background-color: transparent; padding-left: 5px; padding-right: 5px; }
|
||||
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
|
||||
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
|
||||
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
|
||||
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
|
||||
.highlight .hll { background-color: #ffffcc }
|
||||
.highlight { background: #f0f0f0; }
|
||||
.highlight .c { color: #60a0b0; font-style: italic } /* Comment */
|
||||
.highlight { background: #f8f8f8; }
|
||||
.highlight .c { color: #3D7B7B; font-style: italic } /* Comment */
|
||||
.highlight .err { border: 1px solid #FF0000 } /* Error */
|
||||
.highlight .k { color: #007020; font-weight: bold } /* Keyword */
|
||||
.highlight .k { color: #008000; font-weight: bold } /* Keyword */
|
||||
.highlight .o { color: #666666 } /* Operator */
|
||||
.highlight .ch { color: #60a0b0; font-style: italic } /* Comment.Hashbang */
|
||||
.highlight .cm { color: #60a0b0; font-style: italic } /* Comment.Multiline */
|
||||
.highlight .cp { color: #007020 } /* Comment.Preproc */
|
||||
.highlight .cpf { color: #60a0b0; font-style: italic } /* Comment.PreprocFile */
|
||||
.highlight .c1 { color: #60a0b0; font-style: italic } /* Comment.Single */
|
||||
.highlight .cs { color: #60a0b0; background-color: #fff0f0 } /* Comment.Special */
|
||||
.highlight .ch { color: #3D7B7B; font-style: italic } /* Comment.Hashbang */
|
||||
.highlight .cm { color: #3D7B7B; font-style: italic } /* Comment.Multiline */
|
||||
.highlight .cp { color: #9C6500 } /* Comment.Preproc */
|
||||
.highlight .cpf { color: #3D7B7B; font-style: italic } /* Comment.PreprocFile */
|
||||
.highlight .c1 { color: #3D7B7B; font-style: italic } /* Comment.Single */
|
||||
.highlight .cs { color: #3D7B7B; font-style: italic } /* Comment.Special */
|
||||
.highlight .gd { color: #A00000 } /* Generic.Deleted */
|
||||
.highlight .ge { font-style: italic } /* Generic.Emph */
|
||||
.highlight .gr { color: #FF0000 } /* Generic.Error */
|
||||
.highlight .gr { color: #E40000 } /* Generic.Error */
|
||||
.highlight .gh { color: #000080; font-weight: bold } /* Generic.Heading */
|
||||
.highlight .gi { color: #00A000 } /* Generic.Inserted */
|
||||
.highlight .go { color: #888888 } /* Generic.Output */
|
||||
.highlight .gp { color: #c65d09; font-weight: bold } /* Generic.Prompt */
|
||||
.highlight .gi { color: #008400 } /* Generic.Inserted */
|
||||
.highlight .go { color: #717171 } /* Generic.Output */
|
||||
.highlight .gp { color: #000080; font-weight: bold } /* Generic.Prompt */
|
||||
.highlight .gs { font-weight: bold } /* Generic.Strong */
|
||||
.highlight .gu { color: #800080; font-weight: bold } /* Generic.Subheading */
|
||||
.highlight .gt { color: #0044DD } /* Generic.Traceback */
|
||||
.highlight .kc { color: #007020; font-weight: bold } /* Keyword.Constant */
|
||||
.highlight .kd { color: #007020; font-weight: bold } /* Keyword.Declaration */
|
||||
.highlight .kn { color: #007020; font-weight: bold } /* Keyword.Namespace */
|
||||
.highlight .kp { color: #007020 } /* Keyword.Pseudo */
|
||||
.highlight .kr { color: #007020; font-weight: bold } /* Keyword.Reserved */
|
||||
.highlight .kt { color: #902000 } /* Keyword.Type */
|
||||
.highlight .m { color: #40a070 } /* Literal.Number */
|
||||
.highlight .s { color: #4070a0 } /* Literal.String */
|
||||
.highlight .na { color: #4070a0 } /* Name.Attribute */
|
||||
.highlight .nb { color: #007020 } /* Name.Builtin */
|
||||
.highlight .nc { color: #0e84b5; font-weight: bold } /* Name.Class */
|
||||
.highlight .no { color: #60add5 } /* Name.Constant */
|
||||
.highlight .nd { color: #555555; font-weight: bold } /* Name.Decorator */
|
||||
.highlight .ni { color: #d55537; font-weight: bold } /* Name.Entity */
|
||||
.highlight .ne { color: #007020 } /* Name.Exception */
|
||||
.highlight .nf { color: #06287e } /* Name.Function */
|
||||
.highlight .nl { color: #002070; font-weight: bold } /* Name.Label */
|
||||
.highlight .nn { color: #0e84b5; font-weight: bold } /* Name.Namespace */
|
||||
.highlight .nt { color: #062873; font-weight: bold } /* Name.Tag */
|
||||
.highlight .nv { color: #bb60d5 } /* Name.Variable */
|
||||
.highlight .ow { color: #007020; font-weight: bold } /* Operator.Word */
|
||||
.highlight .kc { color: #008000; font-weight: bold } /* Keyword.Constant */
|
||||
.highlight .kd { color: #008000; font-weight: bold } /* Keyword.Declaration */
|
||||
.highlight .kn { color: #008000; font-weight: bold } /* Keyword.Namespace */
|
||||
.highlight .kp { color: #008000 } /* Keyword.Pseudo */
|
||||
.highlight .kr { color: #008000; font-weight: bold } /* Keyword.Reserved */
|
||||
.highlight .kt { color: #B00040 } /* Keyword.Type */
|
||||
.highlight .m { color: #666666 } /* Literal.Number */
|
||||
.highlight .s { color: #BA2121 } /* Literal.String */
|
||||
.highlight .na { color: #687822 } /* Name.Attribute */
|
||||
.highlight .nb { color: #008000 } /* Name.Builtin */
|
||||
.highlight .nc { color: #0000FF; font-weight: bold } /* Name.Class */
|
||||
.highlight .no { color: #880000 } /* Name.Constant */
|
||||
.highlight .nd { color: #AA22FF } /* Name.Decorator */
|
||||
.highlight .ni { color: #717171; font-weight: bold } /* Name.Entity */
|
||||
.highlight .ne { color: #CB3F38; font-weight: bold } /* Name.Exception */
|
||||
.highlight .nf { color: #0000FF } /* Name.Function */
|
||||
.highlight .nl { color: #767600 } /* Name.Label */
|
||||
.highlight .nn { color: #0000FF; font-weight: bold } /* Name.Namespace */
|
||||
.highlight .nt { color: #008000; font-weight: bold } /* Name.Tag */
|
||||
.highlight .nv { color: #19177C } /* Name.Variable */
|
||||
.highlight .ow { color: #AA22FF; font-weight: bold } /* Operator.Word */
|
||||
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
|
||||
.highlight .mb { color: #40a070 } /* Literal.Number.Bin */
|
||||
.highlight .mf { color: #40a070 } /* Literal.Number.Float */
|
||||
.highlight .mh { color: #40a070 } /* Literal.Number.Hex */
|
||||
.highlight .mi { color: #40a070 } /* Literal.Number.Integer */
|
||||
.highlight .mo { color: #40a070 } /* Literal.Number.Oct */
|
||||
.highlight .sa { color: #4070a0 } /* Literal.String.Affix */
|
||||
.highlight .sb { color: #4070a0 } /* Literal.String.Backtick */
|
||||
.highlight .sc { color: #4070a0 } /* Literal.String.Char */
|
||||
.highlight .dl { color: #4070a0 } /* Literal.String.Delimiter */
|
||||
.highlight .sd { color: #4070a0; font-style: italic } /* Literal.String.Doc */
|
||||
.highlight .s2 { color: #4070a0 } /* Literal.String.Double */
|
||||
.highlight .se { color: #4070a0; font-weight: bold } /* Literal.String.Escape */
|
||||
.highlight .sh { color: #4070a0 } /* Literal.String.Heredoc */
|
||||
.highlight .si { color: #70a0d0; font-style: italic } /* Literal.String.Interpol */
|
||||
.highlight .sx { color: #c65d09 } /* Literal.String.Other */
|
||||
.highlight .sr { color: #235388 } /* Literal.String.Regex */
|
||||
.highlight .s1 { color: #4070a0 } /* Literal.String.Single */
|
||||
.highlight .ss { color: #517918 } /* Literal.String.Symbol */
|
||||
.highlight .bp { color: #007020 } /* Name.Builtin.Pseudo */
|
||||
.highlight .fm { color: #06287e } /* Name.Function.Magic */
|
||||
.highlight .vc { color: #bb60d5 } /* Name.Variable.Class */
|
||||
.highlight .vg { color: #bb60d5 } /* Name.Variable.Global */
|
||||
.highlight .vi { color: #bb60d5 } /* Name.Variable.Instance */
|
||||
.highlight .vm { color: #bb60d5 } /* Name.Variable.Magic */
|
||||
.highlight .il { color: #40a070 } /* Literal.Number.Integer.Long */
|
||||
.highlight .mb { color: #666666 } /* Literal.Number.Bin */
|
||||
.highlight .mf { color: #666666 } /* Literal.Number.Float */
|
||||
.highlight .mh { color: #666666 } /* Literal.Number.Hex */
|
||||
.highlight .mi { color: #666666 } /* Literal.Number.Integer */
|
||||
.highlight .mo { color: #666666 } /* Literal.Number.Oct */
|
||||
.highlight .sa { color: #BA2121 } /* Literal.String.Affix */
|
||||
.highlight .sb { color: #BA2121 } /* Literal.String.Backtick */
|
||||
.highlight .sc { color: #BA2121 } /* Literal.String.Char */
|
||||
.highlight .dl { color: #BA2121 } /* Literal.String.Delimiter */
|
||||
.highlight .sd { color: #BA2121; font-style: italic } /* Literal.String.Doc */
|
||||
.highlight .s2 { color: #BA2121 } /* Literal.String.Double */
|
||||
.highlight .se { color: #AA5D1F; font-weight: bold } /* Literal.String.Escape */
|
||||
.highlight .sh { color: #BA2121 } /* Literal.String.Heredoc */
|
||||
.highlight .si { color: #A45A77; font-weight: bold } /* Literal.String.Interpol */
|
||||
.highlight .sx { color: #008000 } /* Literal.String.Other */
|
||||
.highlight .sr { color: #A45A77 } /* Literal.String.Regex */
|
||||
.highlight .s1 { color: #BA2121 } /* Literal.String.Single */
|
||||
.highlight .ss { color: #19177C } /* Literal.String.Symbol */
|
||||
.highlight .bp { color: #008000 } /* Name.Builtin.Pseudo */
|
||||
.highlight .fm { color: #0000FF } /* Name.Function.Magic */
|
||||
.highlight .vc { color: #19177C } /* Name.Variable.Class */
|
||||
.highlight .vg { color: #19177C } /* Name.Variable.Global */
|
||||
.highlight .vi { color: #19177C } /* Name.Variable.Instance */
|
||||
.highlight .vm { color: #19177C } /* Name.Variable.Magic */
|
||||
.highlight .il { color: #666666 } /* Literal.Number.Integer.Long */
|
||||
|
|
@ -4,7 +4,7 @@
|
|||
*
|
||||
* Sphinx JavaScript utilities for the full-text search.
|
||||
*
|
||||
* :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
|
||||
* :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
|
||||
* :license: BSD, see LICENSE for details.
|
||||
*
|
||||
*/
|
||||
|
|
@ -57,12 +57,12 @@ const _removeChildren = (element) => {
|
|||
const _escapeRegExp = (string) =>
|
||||
string.replace(/[.*+\-?^${}()|[\]\\]/g, "\\$&"); // $& means the whole matched string
|
||||
|
||||
const _displayItem = (item, searchTerms) => {
|
||||
const _displayItem = (item, searchTerms, highlightTerms) => {
|
||||
const docBuilder = DOCUMENTATION_OPTIONS.BUILDER;
|
||||
const docUrlRoot = DOCUMENTATION_OPTIONS.URL_ROOT;
|
||||
const docFileSuffix = DOCUMENTATION_OPTIONS.FILE_SUFFIX;
|
||||
const docLinkSuffix = DOCUMENTATION_OPTIONS.LINK_SUFFIX;
|
||||
const showSearchSummary = DOCUMENTATION_OPTIONS.SHOW_SEARCH_SUMMARY;
|
||||
const contentRoot = document.documentElement.dataset.content_root;
|
||||
|
||||
const [docName, title, anchor, descr, score, _filename] = item;
|
||||
|
||||
|
|
@ -75,20 +75,24 @@ const _displayItem = (item, searchTerms) => {
|
|||
if (dirname.match(/\/index\/$/))
|
||||
dirname = dirname.substring(0, dirname.length - 6);
|
||||
else if (dirname === "index/") dirname = "";
|
||||
requestUrl = docUrlRoot + dirname;
|
||||
requestUrl = contentRoot + dirname;
|
||||
linkUrl = requestUrl;
|
||||
} else {
|
||||
// normal html builders
|
||||
requestUrl = docUrlRoot + docName + docFileSuffix;
|
||||
requestUrl = contentRoot + docName + docFileSuffix;
|
||||
linkUrl = docName + docLinkSuffix;
|
||||
}
|
||||
let linkEl = listItem.appendChild(document.createElement("a"));
|
||||
linkEl.href = linkUrl + anchor;
|
||||
linkEl.dataset.score = score;
|
||||
linkEl.innerHTML = title;
|
||||
if (descr)
|
||||
if (descr) {
|
||||
listItem.appendChild(document.createElement("span")).innerHTML =
|
||||
" (" + descr + ")";
|
||||
// highlight search terms in the description
|
||||
if (SPHINX_HIGHLIGHT_ENABLED) // set in sphinx_highlight.js
|
||||
highlightTerms.forEach((term) => _highlightText(listItem, term, "highlighted"));
|
||||
}
|
||||
else if (showSearchSummary)
|
||||
fetch(requestUrl)
|
||||
.then((responseData) => responseData.text())
|
||||
|
|
@ -97,6 +101,9 @@ const _displayItem = (item, searchTerms) => {
|
|||
listItem.appendChild(
|
||||
Search.makeSearchSummary(data, searchTerms)
|
||||
);
|
||||
// highlight search terms in the summary
|
||||
if (SPHINX_HIGHLIGHT_ENABLED) // set in sphinx_highlight.js
|
||||
highlightTerms.forEach((term) => _highlightText(listItem, term, "highlighted"));
|
||||
});
|
||||
Search.output.appendChild(listItem);
|
||||
};
|
||||
|
|
@ -115,14 +122,15 @@ const _finishSearch = (resultCount) => {
|
|||
const _displayNextItem = (
|
||||
results,
|
||||
resultCount,
|
||||
searchTerms
|
||||
searchTerms,
|
||||
highlightTerms,
|
||||
) => {
|
||||
// results left, load the summary and display it
|
||||
// this is intended to be dynamic (don't sub resultsCount)
|
||||
if (results.length) {
|
||||
_displayItem(results.pop(), searchTerms);
|
||||
_displayItem(results.pop(), searchTerms, highlightTerms);
|
||||
setTimeout(
|
||||
() => _displayNextItem(results, resultCount, searchTerms),
|
||||
() => _displayNextItem(results, resultCount, searchTerms, highlightTerms),
|
||||
5
|
||||
);
|
||||
}
|
||||
|
|
@ -156,7 +164,7 @@ const Search = {
|
|||
const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
|
||||
htmlElement.querySelectorAll(".headerlink").forEach((el) => { el.remove() });
|
||||
const docContent = htmlElement.querySelector('[role="main"]');
|
||||
if (docContent !== undefined) return docContent.textContent;
|
||||
if (docContent) return docContent.textContent;
|
||||
console.warn(
|
||||
"Content block not found. Sphinx search tries to obtain it via '[role=main]'. Could you check your theme or template."
|
||||
);
|
||||
|
|
@ -280,9 +288,9 @@ const Search = {
|
|||
let results = [];
|
||||
_removeChildren(document.getElementById("search-progress"));
|
||||
|
||||
const queryLower = query.toLowerCase();
|
||||
const queryLower = query.toLowerCase().trim();
|
||||
for (const [title, foundTitles] of Object.entries(allTitles)) {
|
||||
if (title.toLowerCase().includes(queryLower) && (queryLower.length >= title.length/2)) {
|
||||
if (title.toLowerCase().trim().includes(queryLower) && (queryLower.length >= title.length/2)) {
|
||||
for (const [file, id] of foundTitles) {
|
||||
let score = Math.round(100 * queryLower.length / title.length)
|
||||
results.push([
|
||||
|
|
@ -360,7 +368,7 @@ const Search = {
|
|||
// console.info("search results:", Search.lastresults);
|
||||
|
||||
// print the results
|
||||
_displayNextItem(results, results.length, searchTerms);
|
||||
_displayNextItem(results, results.length, searchTerms, highlightTerms);
|
||||
},
|
||||
|
||||
/**
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
|
|
@ -1,48 +1,73 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Index — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Index — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<link rel="index" title="Index" href="#" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="#" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Index</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
</head>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
<a href="index.html" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">quapy</a></li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="index.html">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item active">Index</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
|
||||
<h1 id="index">Index</h1>
|
||||
|
||||
|
|
@ -97,14 +122,24 @@
|
|||
</li>
|
||||
<li><a href="quapy.html#quapy.error.ae">ae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ACC.aggregate">aggregate() (quapy.method.aggregative.ACC method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyCS.aggregate">aggregate() (quapy.method._kdey.KDEyCS method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyHD.aggregate">(quapy.method._kdey.KDEyHD method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyML.aggregate">(quapy.method._kdey.KDEyML method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MS.aggregate">(quapy.method._threshold_optim.MS method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.aggregate">(quapy.method._threshold_optim.ThresholdOptimization method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ACC.aggregate">(quapy.method.aggregative.ACC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.aggregate">(quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.CC.aggregate">(quapy.method.aggregative.CC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DistributionMatching.aggregate">(quapy.method.aggregative.DistributionMatching method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DMy.aggregate">(quapy.method.aggregative.DMy method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DyS.aggregate">(quapy.method.aggregative.DyS method)</a>
|
||||
</li>
|
||||
|
|
@ -119,21 +154,61 @@
|
|||
<li><a href="quapy.method.html#quapy.method.aggregative.PCC.aggregate">(quapy.method.aggregative.PCC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.SMM.aggregate">(quapy.method.aggregative.SMM method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ThresholdOptimization.aggregate">(quapy.method.aggregative.ThresholdOptimization method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.aggregate_with_threshold">aggregate_with_threshold() (quapy.method._threshold_optim.ThresholdOptimization method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyCS.aggregation_fit">aggregation_fit() (quapy.method._kdey.KDEyCS method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyHD.aggregation_fit">(quapy.method._kdey.KDEyHD method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyML.aggregation_fit">(quapy.method._kdey.KDEyML method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MS.aggregation_fit">(quapy.method._threshold_optim.MS method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.aggregation_fit">(quapy.method._threshold_optim.ThresholdOptimization method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ACC.aggregation_fit">(quapy.method.aggregative.ACC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.aggregation_fit">(quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.CC.aggregation_fit">(quapy.method.aggregative.CC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DMy.aggregation_fit">(quapy.method.aggregative.DMy method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DyS.aggregation_fit">(quapy.method.aggregative.DyS method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.aggregation_fit">(quapy.method.aggregative.EMQ method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.HDy.aggregation_fit">(quapy.method.aggregative.HDy method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.PACC.aggregation_fit">(quapy.method.aggregative.PACC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.PCC.aggregation_fit">(quapy.method.aggregative.PCC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.SMM.aggregation_fit">(quapy.method.aggregative.SMM method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble.aggregative">aggregative (quapy.method.meta.Ensemble property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeProbabilisticQuantifier">AggregativeProbabilisticQuantifier (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeCrispQuantifier">AggregativeCrispQuantifier (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator">AggregativeMedianEstimator (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier">AggregativeQuantifier (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeSoftQuantifier">AggregativeSoftQuantifier (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.APP">APP (class in quapy.protocol)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.argmin_prevalence">argmin_prevalence() (in module quapy.functional)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.ArtificialPrevalenceProtocol">ArtificialPrevalenceProtocol (in module quapy.protocol)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.as_binary_prevalence">as_binary_prevalence() (in module quapy.functional)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.TorchDataset.asDataloader">asDataloader() (quapy.classification.neural.TorchDataset method)</a>
|
||||
</li>
|
||||
|
|
@ -143,6 +218,8 @@
|
|||
<h2 id="B">B</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEBase.BANDWIDTH_METHOD">BANDWIDTH_METHOD (quapy.method._kdey.KDEBase attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.BaseQuantifier">BaseQuantifier (class in quapy.method.base)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.calibration.BCTSCalibration">BCTSCalibration (class in quapy.classification.calibration)</a>
|
||||
|
|
@ -164,6 +241,8 @@
|
|||
<li><a href="quapy.html#quapy.plot.binary_bias_global">binary_bias_global() (in module quapy.plot)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.plot.binary_diagonal">binary_diagonal() (in module quapy.plot)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier">BinaryAggregativeQuantifier (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.BinaryQuantifier">BinaryQuantifier (class in quapy.method.base)</a>
|
||||
</li>
|
||||
|
|
@ -183,47 +262,57 @@
|
|||
|
||||
<ul>
|
||||
<li><a href="quapy.data.html#quapy.data.base.Dataset.classes_">(quapy.data.base.Dataset property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.classes_">(quapy.method._neural.QuaNetTrainer property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classes_">(quapy.method.aggregative.AggregativeQuantifier property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.OneVsAllGeneric.classes_">(quapy.method.base.OneVsAllGeneric property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.classes_">(quapy.method.neural.QuaNetTrainer property)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classifier">classifier (quapy.method.aggregative.AggregativeQuantifier property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ACC.classify">classify() (quapy.method.aggregative.ACC method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classifier_fit_predict">classifier_fit_predict() (quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classify">classify() (quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeProbabilisticQuantifier.classify">(quapy.method.aggregative.AggregativeProbabilisticQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classify">(quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.classify">(quapy.method.aggregative.EMQ method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.OneVsAllAggregative.classify">(quapy.method.aggregative.OneVsAllAggregative method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.PACC.classify">(quapy.method.aggregative.PACC method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ClassifyAndCount">ClassifyAndCount (in module quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.clean_checkpoint">clean_checkpoint() (quapy.method.neural.QuaNetTrainer method)</a>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.clean_checkpoint">clean_checkpoint() (quapy.method._neural.QuaNetTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.clean_checkpoint_dir">clean_checkpoint_dir() (quapy.method.neural.QuaNetTrainer method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.clean_checkpoint_dir">clean_checkpoint_dir() (quapy.method._neural.QuaNetTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.CNNnet">CNNnet (class in quapy.classification.neural)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.collator">collator() (quapy.protocol.AbstractStochasticSeededProtocol method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MAX.condition">condition() (quapy.method._threshold_optim.MAX method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MS.condition">(quapy.method._threshold_optim.MS method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.T50.condition">(quapy.method._threshold_optim.T50 method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.condition">(quapy.method._threshold_optim.ThresholdOptimization method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.X.condition">(quapy.method._threshold_optim.X method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.html#quapy.model_selection.ConfigStatus">ConfigStatus (class in quapy.model_selection)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.base.LabelledCollection.counts">counts() (quapy.data.base.LabelledCollection method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.util.create_if_not_exist">create_if_not_exist() (in module quapy.util)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.util.create_parent_dir">create_parent_dir() (in module quapy.util)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.cross_generate_predictions">cross_generate_predictions() (in module quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.cross_val_predict">cross_val_predict() (in module quapy.model_selection)</a>
|
||||
</li>
|
||||
|
|
@ -240,15 +329,27 @@
|
|||
<li><a href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.device">device (quapy.classification.neural.NeuralClassifierTrainer property)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetModule.device">(quapy.method.neural.QuaNetModule property)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetModule.device">(quapy.method._neural.QuaNetModule property)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.dimensions">dimensions() (quapy.classification.neural.TextClassifierNet method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DistributionMatching">DistributionMatching (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MS2.discard">discard() (quapy.method._threshold_optim.MS2 method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.discard">(quapy.method._threshold_optim.ThresholdOptimization method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.DistributionMatchingX">DistributionMatchingX (in module quapy.method.non_aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DistributionMatchingY">DistributionMatchingY (in module quapy.method.aggregative)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.DMx">DMx (class in quapy.method.non_aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DMy">DMy (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.CNNnet.document_embedding">document_embedding() (quapy.classification.neural.CNNnet method)</a>
|
||||
|
||||
<ul>
|
||||
|
|
@ -284,6 +385,8 @@
|
|||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.EM">EM() (quapy.method.aggregative.EMQ class method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ">EMQ (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.EMQ_BCTS">EMQ_BCTS() (quapy.method.aggregative.EMQ class method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble">Ensemble (class in quapy.method.meta)</a>
|
||||
</li>
|
||||
|
|
@ -294,6 +397,8 @@
|
|||
<li><a href="quapy.method.html#quapy.method.meta.EPACC">EPACC() (in module quapy.method.meta)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.EPSILON">EPSILON (quapy.method.aggregative.EMQ attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.Status.ERROR">ERROR (quapy.model_selection.Status attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.plot.error_by_drift">error_by_drift() (in module quapy.plot)</a>
|
||||
</li>
|
||||
|
|
@ -302,6 +407,8 @@
|
|||
<li><a href="quapy.html#quapy.evaluation.evaluate_on_samples">evaluate_on_samples() (in module quapy.evaluation)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.evaluation.evaluation_report">evaluation_report() (in module quapy.evaluation)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.expand_grid">expand_grid() (in module quapy.model_selection)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ExpectationMaximizationQuantifier">ExpectationMaximizationQuantifier (in module quapy.method.aggregative)</a>
|
||||
</li>
|
||||
|
|
@ -314,6 +421,10 @@
|
|||
<li><a href="quapy.html#quapy.error.f1_error">f1_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.f1e">f1e() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.ConfigStatus.failed">failed() (quapy.model_selection.ConfigStatus method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_IFCB">fetch_IFCB() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_lequa2022">fetch_lequa2022() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
|
|
@ -321,9 +432,13 @@
|
|||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_twitter">fetch_twitter() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_UCIDataset">fetch_UCIDataset() (in module quapy.data.datasets)</a>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_UCIBinaryDataset">fetch_UCIBinaryDataset() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_UCILabelledCollection">fetch_UCILabelledCollection() (in module quapy.data.datasets)</a>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_UCIBinaryLabelledCollection">fetch_UCIBinaryLabelledCollection() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_UCIMulticlassDataset">fetch_UCIMulticlassDataset() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.datasets.fetch_UCIMulticlassLabelledCollection">fetch_UCIMulticlassLabelledCollection() (in module quapy.data.datasets)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit">fit() (quapy.classification.calibration.RecalibratedProbabilisticClassifierBase method)</a>
|
||||
|
||||
|
|
@ -336,27 +451,13 @@
|
|||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.fit">(quapy.data.preprocessing.IndexTransformer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ACC.fit">(quapy.method.aggregative.ACC method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.fit">(quapy.method._neural.QuaNetTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.fit">(quapy.method.aggregative.AggregativeMedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.fit">(quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.CC.fit">(quapy.method.aggregative.CC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DistributionMatching.fit">(quapy.method.aggregative.DistributionMatching method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.DyS.fit">(quapy.method.aggregative.DyS method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.fit">(quapy.method.aggregative.EMQ method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.HDy.fit">(quapy.method.aggregative.HDy method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.PACC.fit">(quapy.method.aggregative.PACC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.PCC.fit">(quapy.method.aggregative.PCC method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.SMM.fit">(quapy.method.aggregative.SMM method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ThresholdOptimization.fit">(quapy.method.aggregative.ThresholdOptimization method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier.fit">(quapy.method.aggregative.BinaryAggregativeQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.BaseQuantifier.fit">(quapy.method.base.BaseQuantifier method)</a>
|
||||
</li>
|
||||
|
|
@ -364,7 +465,11 @@
|
|||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble.fit">(quapy.method.meta.Ensemble method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.fit">(quapy.method.neural.QuaNetTrainer method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator.fit">(quapy.method.meta.MedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator2.fit">(quapy.method.meta.MedianEstimator2 method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.DMx.fit">(quapy.method.non_aggregative.DMx method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.fit">(quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation method)</a>
|
||||
</li>
|
||||
|
|
@ -382,7 +487,7 @@
|
|||
<li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.forward">forward() (quapy.classification.neural.TextClassifierNet method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetModule.forward">(quapy.method.neural.QuaNetModule method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetModule.forward">(quapy.method._neural.QuaNetModule method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.data.html#quapy.data.reader.from_csv">from_csv() (in module quapy.data.reader)</a>
|
||||
|
|
@ -400,8 +505,14 @@
|
|||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_collator">get_collator() (quapy.protocol.OnLabelledCollectionProtocol class method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.get_divergence">get_divergence() (in module quapy.functional)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEBase.get_kde_function">get_kde_function() (quapy.method._kdey.KDEBase method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_labelled_collection">get_labelled_collection() (quapy.protocol.OnLabelledCollectionProtocol method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEBase.get_mixture_components">get_mixture_components() (quapy.method._kdey.KDEBase method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.get_nprevpoints_approximation">get_nprevpoints_approximation() (in module quapy.functional)</a>
|
||||
</li>
|
||||
|
|
@ -415,10 +526,16 @@
|
|||
<li><a href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.get_params">(quapy.classification.neural.NeuralClassifierTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.get_params">(quapy.classification.neural.TextClassifierNet method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.get_params">(quapy.method._neural.QuaNetTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.get_params">(quapy.method.aggregative.AggregativeMedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble.get_params">(quapy.method.meta.Ensemble method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.get_params">(quapy.method.neural.QuaNetTrainer method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator.get_params">(quapy.method.meta.MedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator2.get_params">(quapy.method.meta.MedianEstimator2 method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.GridSearchQ.get_params">(quapy.model_selection.GridSearchQ method)</a>
|
||||
</li>
|
||||
|
|
@ -435,7 +552,11 @@
|
|||
<li><a href="quapy.method.html#quapy.method.aggregative.PACC.getPteCondEstim">(quapy.method.aggregative.PACC class method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyCS.gram_matrix_mix_sum">gram_matrix_mix_sum() (quapy.method._kdey.KDEyCS method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.GridSearchQ">GridSearchQ (class in quapy.model_selection)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.group_params">group_params() (in module quapy.model_selection)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
|
@ -443,6 +564,8 @@
|
|||
<h2 id="H">H</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.DMx.HDx">HDx() (quapy.method.non_aggregative.DMx class method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.HDy">HDy (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
|
|
@ -458,10 +581,12 @@
|
|||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.data.html#quapy.data.preprocessing.index">index() (in module quapy.data.preprocessing)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.preprocessing.IndexTransformer">IndexTransformer (class in quapy.data.preprocessing)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.data.html#quapy.data.preprocessing.IndexTransformer">IndexTransformer (class in quapy.data.preprocessing)</a>
|
||||
<li><a href="quapy.html#quapy.model_selection.Status.INVALID">INVALID (quapy.model_selection.Status attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.IterateProtocol">IterateProtocol (class in quapy.protocol)</a>
|
||||
</li>
|
||||
|
|
@ -479,14 +604,22 @@
|
|||
<h2 id="K">K</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEBase">KDEBase (class in quapy.method._kdey)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyCS">KDEyCS (class in quapy.method._kdey)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyHD">KDEyHD (class in quapy.method._kdey)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEyML">KDEyML (class in quapy.method._kdey)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.base.Dataset.kFCV">kFCV() (quapy.data.base.Dataset class method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.data.html#quapy.data.base.LabelledCollection.kFCV">(quapy.data.base.LabelledCollection method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.html#quapy.error.kld">kld() (in module quapy.error)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
|
|
@ -496,6 +629,8 @@
|
|||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.data.html#quapy.data.base.LabelledCollection">LabelledCollection (class in quapy.data.base)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.linear_search">linear_search() (in module quapy.functional)</a>
|
||||
</li>
|
||||
<li><a href="quapy.data.html#quapy.data.base.Dataset.load">load() (quapy.data.base.Dataset class method)</a>
|
||||
|
||||
|
|
@ -517,33 +652,41 @@
|
|||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.html#quapy.error.mae">mae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.mae_loss">mae_loss() (in module quapy.method.neural)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.mae_loss">mae_loss() (in module quapy.method._neural)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.util.map_parallel">map_parallel() (in module quapy.util)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.MAX">MAX (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MAX">MAX (class in quapy.method._threshold_optim)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.EMQ.MAX_ITER">MAX_ITER (quapy.method.aggregative.EMQ attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation">MaximumLikelihoodPrevalenceEstimation (class in quapy.method.non_aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mean_absolute_error">mean_absolute_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mean_normalized_absolute_error">mean_normalized_absolute_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mean_normalized_relative_absolute_error">mean_normalized_relative_absolute_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mean_relative_absolute_error">mean_relative_absolute_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.MedianSweep">MedianSweep (in module quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator">MedianEstimator (class in quapy.method.meta)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.MedianSweep2">MedianSweep2 (in module quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator2">MedianEstimator2 (class in quapy.method.meta)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mkld">mkld() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mnae">mnae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mnkld">mnkld() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mnrae">mnrae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li>
|
||||
module
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.html#module-quapy">quapy</a>
|
||||
<li><a href="generated/quapy.html#module-quapy">quapy</a>, <a href="quapy.html#module-quapy">[1]</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#module-quapy.classification">quapy.classification</a>
|
||||
</li>
|
||||
|
|
@ -572,14 +715,18 @@
|
|||
<li><a href="quapy.html#module-quapy.functional">quapy.functional</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method">quapy.method</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method._kdey">quapy.method._kdey</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method._neural">quapy.method._neural</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method._threshold_optim">quapy.method._threshold_optim</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method.aggregative">quapy.method.aggregative</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method.base">quapy.method.base</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method.meta">quapy.method.meta</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method.neural">quapy.method.neural</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#module-quapy.method.non_aggregative">quapy.method.non_aggregative</a>
|
||||
</li>
|
||||
|
|
@ -596,9 +743,9 @@
|
|||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.html#quapy.error.mrae">mrae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.MS">MS (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MS">MS (class in quapy.method._threshold_optim)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.MS2">MS2 (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.MS2">MS2 (class in quapy.method._threshold_optim)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.mse">mse() (in module quapy.error)</a>
|
||||
</li>
|
||||
|
|
@ -614,9 +761,13 @@
|
|||
<li><a href="quapy.data.html#quapy.data.base.LabelledCollection.n_classes">(quapy.data.base.LabelledCollection property)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.html#quapy.error.nae">nae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.NaturalPrevalenceProtocol">NaturalPrevalenceProtocol (in module quapy.protocol)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.calibration.NBVSCalibration">NBVSCalibration (class in quapy.classification.calibration)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier.neg_label">neg_label (quapy.method.aggregative.BinaryAggregativeQuantifier property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer">NeuralClassifierTrainer (class in quapy.classification.neural)</a>
|
||||
</li>
|
||||
|
|
@ -624,10 +775,10 @@
|
|||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.newOneVsAll">newOneVsAll() (in module quapy.method.base)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.newSVMAE">newSVMAE() (in module quapy.method.aggregative)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.newSVMKLD">newSVMKLD() (in module quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.newSVMQ">newSVMQ() (in module quapy.method.aggregative)</a>
|
||||
|
|
@ -637,8 +788,14 @@
|
|||
<li><a href="quapy.html#quapy.error.nkld">nkld() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.normalize_prevalence">normalize_prevalence() (in module quapy.functional)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.normalized_absolute_error">normalized_absolute_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.normalized_relative_absolute_error">normalized_relative_absolute_error() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.NPP">NPP (class in quapy.protocol)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.error.nrae">nrae() (in module quapy.error)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.num_prevalence_combinations">num_prevalence_combinations() (in module quapy.functional)</a>
|
||||
</li>
|
||||
|
|
@ -652,13 +809,15 @@
|
|||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.OneVsAll">OneVsAll (class in quapy.method.base)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.OneVsAllAggregative">OneVsAllAggregative (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.base.OneVsAllGeneric">OneVsAllGeneric (class in quapy.method.base)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol">OnLabelledCollectionProtocol (class in quapy.protocol)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.optim_minimize">optim_minimize() (in module quapy.functional)</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
|
@ -673,8 +832,12 @@
|
|||
<li><a href="quapy.html#quapy.util.parallel">parallel() (in module quapy.util)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.PCC">PCC (class in quapy.method.aggregative)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._kdey.KDEBase.pdf">pdf() (quapy.method._kdey.KDEBase method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.util.pickled_resource">pickled_resource() (in module quapy.util)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier.pos_label">pos_label (quapy.method.aggregative.BinaryAggregativeQuantifier property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict">predict() (quapy.classification.calibration.RecalibratedProbabilisticClassifierBase method)</a>
|
||||
|
||||
|
|
@ -724,20 +887,28 @@
|
|||
<h2 id="Q">Q</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetModule">QuaNetModule (class in quapy.method.neural)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetModule">QuaNetModule (class in quapy.method._neural)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer">QuaNetTrainer (class in quapy.method.neural)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer">QuaNetTrainer (class in quapy.method._neural)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.quantify">quantify() (quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.quantify">quantify() (quapy.method._neural.QuaNetTrainer method)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.quantify">(quapy.method.aggregative.AggregativeMedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.quantify">(quapy.method.aggregative.AggregativeQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.BaseQuantifier.quantify">(quapy.method.base.BaseQuantifier method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.base.OneVsAllGeneric.quantify">(quapy.method.base.OneVsAllGeneric method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble.quantify">(quapy.method.meta.Ensemble method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.quantify">(quapy.method.neural.QuaNetTrainer method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator.quantify">(quapy.method.meta.MedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator2.quantify">(quapy.method.meta.MedianEstimator2 method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.DMx.quantify">(quapy.method.non_aggregative.DMx method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.quantify">(quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation method)</a>
|
||||
</li>
|
||||
|
|
@ -748,7 +919,7 @@
|
|||
quapy
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.html#module-quapy">module</a>
|
||||
<li><a href="generated/quapy.html#module-quapy">module</a>, <a href="quapy.html#module-quapy">[1]</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
|
|
@ -849,6 +1020,27 @@
|
|||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#module-quapy.method">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
quapy.method._kdey
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#module-quapy.method._kdey">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
quapy.method._neural
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#module-quapy.method._neural">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
quapy.method._threshold_optim
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#module-quapy.method._threshold_optim">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
|
|
@ -870,13 +1062,6 @@
|
|||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#module-quapy.method.meta">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
quapy.method.neural
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.method.html#module-quapy.method.neural">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
|
|
@ -986,10 +1171,16 @@
|
|||
|
||||
<ul>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.set_params">(quapy.classification.neural.NeuralClassifierTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method._neural.QuaNetTrainer.set_params">(quapy.method._neural.QuaNetTrainer method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.set_params">(quapy.method.aggregative.AggregativeMedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble.set_params">(quapy.method.meta.Ensemble method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetTrainer.set_params">(quapy.method.neural.QuaNetTrainer method)</a>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator.set_params">(quapy.method.meta.MedianEstimator method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.MedianEstimator2.set_params">(quapy.method.meta.MedianEstimator2 method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.GridSearchQ.set_params">(quapy.model_selection.GridSearchQ method)</a>
|
||||
</li>
|
||||
|
|
@ -1018,7 +1209,13 @@
|
|||
<li><a href="quapy.data.html#quapy.data.base.LabelledCollection.stats">(quapy.data.base.LabelledCollection method)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.html#quapy.model_selection.Status">Status (class in quapy.model_selection)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.strprev">strprev() (in module quapy.functional)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.Status.SUCCESS">SUCCESS (quapy.model_selection.Status attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.ConfigStatus.success">success() (quapy.model_selection.ConfigStatus method)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.svmperf.SVMperf">SVMperf (class in quapy.classification.svmperf)</a>
|
||||
</li>
|
||||
|
|
@ -1028,7 +1225,7 @@
|
|||
<h2 id="T">T</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.T50">T50 (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.T50">T50 (class in quapy.method._threshold_optim)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.util.temp_seed">temp_seed() (in module quapy.util)</a>
|
||||
</li>
|
||||
|
|
@ -1036,7 +1233,11 @@
|
|||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet">TextClassifierNet (class in quapy.classification.neural)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.ThresholdOptimization">ThresholdOptimization (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization">ThresholdOptimization (class in quapy.method._threshold_optim)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.model_selection.Status.TIMEOUT">TIMEOUT (quapy.model_selection.Status attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.util.timeout">timeout() (in module quapy.util)</a>
|
||||
</li>
|
||||
<li><a href="quapy.html#quapy.functional.TopsoeDistance">TopsoeDistance() (in module quapy.functional)</a>
|
||||
</li>
|
||||
|
|
@ -1060,16 +1261,6 @@
|
|||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.data.html#quapy.data.base.Dataset.train_test">train_test (quapy.data.base.Dataset property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.CNNnet.training">training (quapy.classification.neural.CNNnet attribute)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.LSTMnet.training">(quapy.classification.neural.LSTMnet attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.training">(quapy.classification.neural.TextClassifierNet attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.neural.QuaNetModule.training">(quapy.method.neural.QuaNetModule attribute)</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.transform">transform() (quapy.classification.methods.LowRankLogisticRegression method)</a>
|
||||
|
||||
<ul>
|
||||
|
|
@ -1106,6 +1297,10 @@
|
|||
<h2 id="V">V</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.val_split">val_split (quapy.method.aggregative.AggregativeQuantifier property)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.val_split_">val_split_ (quapy.method.aggregative.AggregativeQuantifier attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.classification.html#quapy.classification.svmperf.SVMperf.valid_losses">valid_losses (quapy.classification.svmperf.SVMperf attribute)</a>
|
||||
</li>
|
||||
<li><a href="quapy.method.html#quapy.method.meta.Ensemble.VALID_POLICIES">VALID_POLICIES (quapy.method.meta.Ensemble attribute)</a>
|
||||
|
|
@ -1140,7 +1335,7 @@
|
|||
<h2 id="X">X</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quapy.method.html#quapy.method.aggregative.X">X (class in quapy.method.aggregative)</a>
|
||||
<li><a href="quapy.method.html#quapy.method._threshold_optim.X">X (class in quapy.method._threshold_optim)</a>
|
||||
|
||||
<ul>
|
||||
<li><a href="quapy.data.html#quapy.data.base.LabelledCollection.X">(quapy.data.base.LabelledCollection property)</a>
|
||||
|
|
@ -1167,42 +1362,31 @@
|
|||
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="#" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Index</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,171 +1,679 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Welcome to QuaPy’s documentation! — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>Welcome to QuaPy’s documentation! — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script async="async" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Installation" href="Installation.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Installation.html" title="Installation"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="#">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Welcome to QuaPy’s documentation!</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<link rel="next" title="quapy" href="modules.html" />
|
||||
</head>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
<a href="#" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">quapy</a></li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="#">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="#" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item active">Welcome to QuaPy’s documentation!</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
<a href="_sources/index.rst.txt" rel="nofollow"> View page source</a>
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<section id="welcome-to-quapy-s-documentation">
|
||||
<h1>Welcome to QuaPy’s documentation!<a class="headerlink" href="#welcome-to-quapy-s-documentation" title="Permalink to this heading">¶</a></h1>
|
||||
<p>QuaPy is an open source framework for Quantification (a.k.a. Supervised Prevalence Estimation)
|
||||
written in Python.</p>
|
||||
<section id="introduction">
|
||||
<h2>Introduction<a class="headerlink" href="#introduction" title="Permalink to this heading">¶</a></h2>
|
||||
<p>QuaPy roots on the concept of data sample, and provides implementations of most important concepts
|
||||
in quantification literature, such as the most important quantification baselines, many advanced
|
||||
quantification methods, quantification-oriented model selection, many evaluation measures and protocols
|
||||
used for evaluating quantification methods.
|
||||
QuaPy also integrates commonly used datasets and offers visualization tools for facilitating the analysis and
|
||||
interpretation of results.</p>
|
||||
<section id="a-quick-example">
|
||||
<h3>A quick example:<a class="headerlink" href="#a-quick-example" title="Permalink to this heading">¶</a></h3>
|
||||
<p>The following script fetchs a Twitter dataset, trains and evaluates an
|
||||
<cite>Adjusted Classify & Count</cite> model in terms of the <cite>Mean Absolute Error</cite> (MAE)
|
||||
between the class prevalences estimated for the test set and the true prevalences
|
||||
of the test set.</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
|
||||
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_twitter</span><span class="p">(</span><span class="s1">'semeval16'</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># create an "Adjusted Classify & Count" quantifier</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">method</span><span class="o">.</span><span class="n">aggregative</span><span class="o">.</span><span class="n">ACC</span><span class="p">(</span><span class="n">LogisticRegression</span><span class="p">())</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
|
||||
|
||||
<span class="n">estim_prevalences</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">quantify</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">instances</span><span class="p">)</span>
|
||||
<span class="n">true_prevalences</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">test</span><span class="o">.</span><span class="n">prevalence</span><span class="p">()</span>
|
||||
|
||||
<span class="n">error</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">error</span><span class="o">.</span><span class="n">mae</span><span class="p">(</span><span class="n">true_prevalences</span><span class="p">,</span> <span class="n">estim_prevalences</span><span class="p">)</span>
|
||||
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'Mean Absolute Error (MAE)=</span><span class="si">{</span><span class="n">error</span><span class="si">:</span><span class="s1">.3f</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>Quantification is useful in scenarios of prior probability shift. In other
|
||||
words, we would not be interested in estimating the class prevalences of the test set if
|
||||
we could assume the IID assumption to hold, as this prevalence would simply coincide with the
|
||||
class prevalence of the training set. For this reason, any Quantification model
|
||||
should be tested across samples characterized by different class prevalences.
|
||||
QuaPy implements sampling procedures and evaluation protocols that automates this endeavour.
|
||||
See the <a class="reference internal" href="Evaluation.html"><span class="doc">Evaluation</span></a> for detailed examples.</p>
|
||||
<h1>Welcome to QuaPy’s documentation!<a class="headerlink" href="#welcome-to-quapy-s-documentation" title="Link to this heading"></a></h1>
|
||||
<p>QuaPy is a Python-based open-source framework for quantification.</p>
|
||||
<p>This document contains the API of the modules included in QuaPy.</p>
|
||||
<section id="installation">
|
||||
<h2>Installation<a class="headerlink" href="#installation" title="Link to this heading"></a></h2>
|
||||
<p><cite>pip install quapy</cite></p>
|
||||
</section>
|
||||
<section id="features">
|
||||
<h3>Features<a class="headerlink" href="#features" title="Permalink to this heading">¶</a></h3>
|
||||
<ul class="simple">
|
||||
<li><p>Implementation of most popular quantification methods (Classify-&-Count variants, Expectation-Maximization, SVM-based variants for quantification, HDy, QuaNet, and Ensembles).</p></li>
|
||||
<li><p>Versatile functionality for performing evaluation based on artificial sampling protocols.</p></li>
|
||||
<li><p>Implementation of most commonly used evaluation metrics (e.g., MAE, MRAE, MSE, NKLD, etc.).</p></li>
|
||||
<li><dl class="simple">
|
||||
<dt>Popular datasets for Quantification (textual and numeric) available, including:</dt><dd><ul>
|
||||
<li><p>32 UCI Machine Learning datasets.</p></li>
|
||||
<li><p>11 Twitter Sentiment datasets.</p></li>
|
||||
<li><p>3 Reviews Sentiment datasets.</p></li>
|
||||
<li><p>4 tasks from LeQua competition (_new in v0.1.7!_)</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
</dl>
|
||||
</li>
|
||||
<li><p>Native supports for binary and single-label scenarios of quantification.</p></li>
|
||||
<li><p>Model selection functionality targeting quantification-oriented losses.</p></li>
|
||||
<li><p>Visualization tools for analysing results.</p></li>
|
||||
</ul>
|
||||
<section id="github">
|
||||
<h2>GitHub<a class="headerlink" href="#github" title="Link to this heading"></a></h2>
|
||||
<p>QuaPy is hosted in GitHub at <a class="reference external" href="https://github.com/HLT-ISTI/QuaPy">https://github.com/HLT-ISTI/QuaPy</a></p>
|
||||
<div class="toctree-wrapper compound">
|
||||
</div>
|
||||
</section>
|
||||
<section id="contents">
|
||||
<h2>Contents<a class="headerlink" href="#contents" title="Link to this heading"></a></h2>
|
||||
<div class="toctree-wrapper compound">
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Installation.html">Installation</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Installation.html#requirements">Requirements</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Installation.html#svm-perf-with-quantification-oriented-losses">SVM-perf with quantification-oriented losses</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">quapy</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html">quapy package</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#subpackages">Subpackages</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html">quapy.classification package</a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.classification.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.calibration">quapy.classification.calibration module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.BCTSCalibration"><code class="docutils literal notranslate"><span class="pre">BCTSCalibration</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.NBVSCalibration"><code class="docutils literal notranslate"><span class="pre">NBVSCalibration</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifier"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifier</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.classes_"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase.classes_</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_cv"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase.fit_cv()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_tr_val"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase.fit_tr_val()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase.predict()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict_proba"><code class="docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase.predict_proba()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Datasets.html">Datasets</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Datasets.html#reviews-datasets">Reviews Datasets</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Datasets.html#twitter-sentiment-datasets">Twitter Sentiment Datasets</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Datasets.html#uci-machine-learning">UCI Machine Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Datasets.html#lequa-datasets">LeQua Datasets</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Datasets.html#adding-custom-datasets">Adding Custom Datasets</a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.TSCalibration"><code class="docutils literal notranslate"><span class="pre">TSCalibration</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.calibration.VSCalibration"><code class="docutils literal notranslate"><span class="pre">VSCalibration</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Evaluation.html">Evaluation</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Evaluation.html#error-measures">Error Measures</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Evaluation.html#evaluation-protocols">Evaluation Protocols</a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.methods">quapy.classification.methods module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.fit"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.get_params"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.predict"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression.predict()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.predict_proba"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression.predict_proba()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.set_params"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression.set_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.methods.LowRankLogisticRegression.transform"><code class="docutils literal notranslate"><span class="pre">LowRankLogisticRegression.transform()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Protocols.html">Protocols</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Protocols.html#artificial-prevalence-protocol">Artificial-Prevalence Protocol</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Protocols.html#sampling-from-the-unit-simplex-the-uniform-prevalence-protocol-upp">Sampling from the unit-simplex, the Uniform-Prevalence Protocol (UPP)</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Protocols.html#natural-prevalence-protocol">Natural-Prevalence Protocol</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Protocols.html#other-protocols">Other protocols</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Methods.html">Quantification Methods</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Methods.html#aggregative-methods">Aggregative Methods</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Methods.html#meta-models">Meta Models</a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.neural">quapy.classification.neural module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.CNNnet"><code class="docutils literal notranslate"><span class="pre">CNNnet</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.CNNnet.document_embedding"><code class="docutils literal notranslate"><span class="pre">CNNnet.document_embedding()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.CNNnet.get_params"><code class="docutils literal notranslate"><span class="pre">CNNnet.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.CNNnet.vocabulary_size"><code class="docutils literal notranslate"><span class="pre">CNNnet.vocabulary_size</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Model-Selection.html">Model Selection</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Model-Selection.html#targeting-a-quantification-oriented-loss">Targeting a Quantification-oriented loss</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Model-Selection.html#targeting-a-classification-oriented-loss">Targeting a Classification-oriented loss</a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.LSTMnet"><code class="docutils literal notranslate"><span class="pre">LSTMnet</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.LSTMnet.document_embedding"><code class="docutils literal notranslate"><span class="pre">LSTMnet.document_embedding()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.LSTMnet.get_params"><code class="docutils literal notranslate"><span class="pre">LSTMnet.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.LSTMnet.vocabulary_size"><code class="docutils literal notranslate"><span class="pre">LSTMnet.vocabulary_size</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="Plotting.html">Plotting</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Plotting.html#diagonal-plot">Diagonal Plot</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Plotting.html#quantification-bias">Quantification bias</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="Plotting.html#error-by-drift">Error by Drift</a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.device"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.device</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.fit"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.get_params"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.predict"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.predict()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.predict_proba"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.predict_proba()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.reset_net_params"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.reset_net_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.set_params"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.set_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.NeuralClassifierTrainer.transform"><code class="docutils literal notranslate"><span class="pre">NeuralClassifierTrainer.transform()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.dimensions"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.dimensions()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.document_embedding"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.document_embedding()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.forward"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.forward()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.get_params"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.predict_proba"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.predict_proba()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.vocabulary_size"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.vocabulary_size</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.xavier_uniform"><code class="docutils literal notranslate"><span class="pre">TextClassifierNet.xavier_uniform()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TorchDataset"><code class="docutils literal notranslate"><span class="pre">TorchDataset</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.neural.TorchDataset.asDataloader"><code class="docutils literal notranslate"><span class="pre">TorchDataset.asDataloader()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.svmperf">quapy.classification.svmperf module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.classification.html#quapy.classification.svmperf.SVMperf"><code class="docutils literal notranslate"><span class="pre">SVMperf</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.svmperf.SVMperf.decision_function"><code class="docutils literal notranslate"><span class="pre">SVMperf.decision_function()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.svmperf.SVMperf.fit"><code class="docutils literal notranslate"><span class="pre">SVMperf.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.svmperf.SVMperf.predict"><code class="docutils literal notranslate"><span class="pre">SVMperf.predict()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.classification.html#quapy.classification.svmperf.SVMperf.valid_losses"><code class="docutils literal notranslate"><span class="pre">SVMperf.valid_losses</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.classification.html#module-quapy.classification">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html">quapy.data package</a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.data.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.data.html#module-quapy.data.base">quapy.data.base module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset"><code class="docutils literal notranslate"><span class="pre">Dataset</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.SplitStratified"><code class="docutils literal notranslate"><span class="pre">Dataset.SplitStratified()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.binary"><code class="docutils literal notranslate"><span class="pre">Dataset.binary</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.classes_"><code class="docutils literal notranslate"><span class="pre">Dataset.classes_</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.kFCV"><code class="docutils literal notranslate"><span class="pre">Dataset.kFCV()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.load"><code class="docutils literal notranslate"><span class="pre">Dataset.load()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.n_classes"><code class="docutils literal notranslate"><span class="pre">Dataset.n_classes</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.reduce"><code class="docutils literal notranslate"><span class="pre">Dataset.reduce()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.stats"><code class="docutils literal notranslate"><span class="pre">Dataset.stats()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.train_test"><code class="docutils literal notranslate"><span class="pre">Dataset.train_test</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.Dataset.vocabulary_size"><code class="docutils literal notranslate"><span class="pre">Dataset.vocabulary_size</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection"><code class="docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.X"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.X</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.Xp"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.Xp</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.Xy"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.Xy</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.binary"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.binary</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.counts"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.counts()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.join"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.join()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.kFCV"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.kFCV()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.load"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.load()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.n_classes"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.n_classes</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.p"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.p</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.prevalence"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.prevalence()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.sampling"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.sampling()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.sampling_from_index"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.sampling_from_index()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.sampling_index"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.sampling_index()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.split_random"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.split_random()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.split_stratified"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.split_stratified()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.stats"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.stats()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.uniform_sampling"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.uniform_sampling()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.uniform_sampling_index"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.uniform_sampling_index()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection.y"><code class="docutils literal notranslate"><span class="pre">LabelledCollection.y</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.data.html#module-quapy.data.datasets">quapy.data.datasets module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_IFCB"><code class="docutils literal notranslate"><span class="pre">fetch_IFCB()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_UCIBinaryDataset"><code class="docutils literal notranslate"><span class="pre">fetch_UCIBinaryDataset()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_UCIBinaryLabelledCollection"><code class="docutils literal notranslate"><span class="pre">fetch_UCIBinaryLabelledCollection()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_UCIMulticlassDataset"><code class="docutils literal notranslate"><span class="pre">fetch_UCIMulticlassDataset()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_UCIMulticlassLabelledCollection"><code class="docutils literal notranslate"><span class="pre">fetch_UCIMulticlassLabelledCollection()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_lequa2022"><code class="docutils literal notranslate"><span class="pre">fetch_lequa2022()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_reviews"><code class="docutils literal notranslate"><span class="pre">fetch_reviews()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.fetch_twitter"><code class="docutils literal notranslate"><span class="pre">fetch_twitter()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.datasets.warn"><code class="docutils literal notranslate"><span class="pre">warn()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.data.html#module-quapy.data.preprocessing">quapy.data.preprocessing module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.IndexTransformer"><code class="docutils literal notranslate"><span class="pre">IndexTransformer</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.add_word"><code class="docutils literal notranslate"><span class="pre">IndexTransformer.add_word()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.fit"><code class="docutils literal notranslate"><span class="pre">IndexTransformer.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.fit_transform"><code class="docutils literal notranslate"><span class="pre">IndexTransformer.fit_transform()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.transform"><code class="docutils literal notranslate"><span class="pre">IndexTransformer.transform()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.vocabulary_size"><code class="docutils literal notranslate"><span class="pre">IndexTransformer.vocabulary_size()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.index"><code class="docutils literal notranslate"><span class="pre">index()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.reduce_columns"><code class="docutils literal notranslate"><span class="pre">reduce_columns()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.standardize"><code class="docutils literal notranslate"><span class="pre">standardize()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.preprocessing.text2tfidf"><code class="docutils literal notranslate"><span class="pre">text2tfidf()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.data.html#module-quapy.data.reader">quapy.data.reader module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.reader.binarize"><code class="docutils literal notranslate"><span class="pre">binarize()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.reader.from_csv"><code class="docutils literal notranslate"><span class="pre">from_csv()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.reader.from_sparse"><code class="docutils literal notranslate"><span class="pre">from_sparse()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.reader.from_text"><code class="docutils literal notranslate"><span class="pre">from_text()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.data.html#quapy.data.reader.reindex_labels"><code class="docutils literal notranslate"><span class="pre">reindex_labels()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.data.html#module-quapy.data">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html">quapy.method package</a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.method.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.method.html#module-quapy.method.aggregative">quapy.method.aggregative module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ACC"><code class="docutils literal notranslate"><span class="pre">ACC</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ACC.aggregate"><code class="docutils literal notranslate"><span class="pre">ACC.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ACC.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">ACC.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ACC.getPteCondEstim"><code class="docutils literal notranslate"><span class="pre">ACC.getPteCondEstim()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ACC.solve_adjustment"><code class="docutils literal notranslate"><span class="pre">ACC.solve_adjustment()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AdjustedClassifyAndCount"><code class="docutils literal notranslate"><span class="pre">AdjustedClassifyAndCount</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeCrispQuantifier"><code class="docutils literal notranslate"><span class="pre">AggregativeCrispQuantifier</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator"><code class="docutils literal notranslate"><span class="pre">AggregativeMedianEstimator</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.fit"><code class="docutils literal notranslate"><span class="pre">AggregativeMedianEstimator.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.get_params"><code class="docutils literal notranslate"><span class="pre">AggregativeMedianEstimator.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.quantify"><code class="docutils literal notranslate"><span class="pre">AggregativeMedianEstimator.quantify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeMedianEstimator.set_params"><code class="docutils literal notranslate"><span class="pre">AggregativeMedianEstimator.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.aggregate"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classes_"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.classes_</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classifier"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.classifier</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classifier_fit_predict"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.classifier_fit_predict()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.classify"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.classify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.fit"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.quantify"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.quantify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.val_split"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.val_split</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeQuantifier.val_split_"><code class="docutils literal notranslate"><span class="pre">AggregativeQuantifier.val_split_</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.AggregativeSoftQuantifier"><code class="docutils literal notranslate"><span class="pre">AggregativeSoftQuantifier</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier"><code class="docutils literal notranslate"><span class="pre">BinaryAggregativeQuantifier</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier.fit"><code class="docutils literal notranslate"><span class="pre">BinaryAggregativeQuantifier.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier.neg_label"><code class="docutils literal notranslate"><span class="pre">BinaryAggregativeQuantifier.neg_label</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.BinaryAggregativeQuantifier.pos_label"><code class="docutils literal notranslate"><span class="pre">BinaryAggregativeQuantifier.pos_label</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.CC"><code class="docutils literal notranslate"><span class="pre">CC</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.CC.aggregate"><code class="docutils literal notranslate"><span class="pre">CC.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.CC.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">CC.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ClassifyAndCount"><code class="docutils literal notranslate"><span class="pre">ClassifyAndCount</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DMy"><code class="docutils literal notranslate"><span class="pre">DMy</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DMy.aggregate"><code class="docutils literal notranslate"><span class="pre">DMy.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DMy.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">DMy.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DistributionMatchingY"><code class="docutils literal notranslate"><span class="pre">DistributionMatchingY</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DyS"><code class="docutils literal notranslate"><span class="pre">DyS</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DyS.aggregate"><code class="docutils literal notranslate"><span class="pre">DyS.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.DyS.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">DyS.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ"><code class="docutils literal notranslate"><span class="pre">EMQ</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.EM"><code class="docutils literal notranslate"><span class="pre">EMQ.EM()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.EMQ_BCTS"><code class="docutils literal notranslate"><span class="pre">EMQ.EMQ_BCTS()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.EPSILON"><code class="docutils literal notranslate"><span class="pre">EMQ.EPSILON</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.MAX_ITER"><code class="docutils literal notranslate"><span class="pre">EMQ.MAX_ITER</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.aggregate"><code class="docutils literal notranslate"><span class="pre">EMQ.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">EMQ.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.classify"><code class="docutils literal notranslate"><span class="pre">EMQ.classify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.EMQ.predict_proba"><code class="docutils literal notranslate"><span class="pre">EMQ.predict_proba()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ExpectationMaximizationQuantifier"><code class="docutils literal notranslate"><span class="pre">ExpectationMaximizationQuantifier</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.HDy"><code class="docutils literal notranslate"><span class="pre">HDy</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.HDy.aggregate"><code class="docutils literal notranslate"><span class="pre">HDy.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.HDy.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">HDy.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.HellingerDistanceY"><code class="docutils literal notranslate"><span class="pre">HellingerDistanceY</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.OneVsAllAggregative"><code class="docutils literal notranslate"><span class="pre">OneVsAllAggregative</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.OneVsAllAggregative.aggregate"><code class="docutils literal notranslate"><span class="pre">OneVsAllAggregative.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.OneVsAllAggregative.classify"><code class="docutils literal notranslate"><span class="pre">OneVsAllAggregative.classify()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PACC"><code class="docutils literal notranslate"><span class="pre">PACC</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PACC.aggregate"><code class="docutils literal notranslate"><span class="pre">PACC.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PACC.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">PACC.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PACC.getPteCondEstim"><code class="docutils literal notranslate"><span class="pre">PACC.getPteCondEstim()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PCC"><code class="docutils literal notranslate"><span class="pre">PCC</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PCC.aggregate"><code class="docutils literal notranslate"><span class="pre">PCC.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.PCC.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">PCC.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ProbabilisticAdjustedClassifyAndCount"><code class="docutils literal notranslate"><span class="pre">ProbabilisticAdjustedClassifyAndCount</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.ProbabilisticClassifyAndCount"><code class="docutils literal notranslate"><span class="pre">ProbabilisticClassifyAndCount</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.SLD"><code class="docutils literal notranslate"><span class="pre">SLD</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.SMM"><code class="docutils literal notranslate"><span class="pre">SMM</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.SMM.aggregate"><code class="docutils literal notranslate"><span class="pre">SMM.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.SMM.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">SMM.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.newELM"><code class="docutils literal notranslate"><span class="pre">newELM()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.newSVMAE"><code class="docutils literal notranslate"><span class="pre">newSVMAE()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.newSVMKLD"><code class="docutils literal notranslate"><span class="pre">newSVMKLD()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.newSVMQ"><code class="docutils literal notranslate"><span class="pre">newSVMQ()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.aggregative.newSVMRAE"><code class="docutils literal notranslate"><span class="pre">newSVMRAE()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEBase"><code class="docutils literal notranslate"><span class="pre">KDEBase</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEBase.BANDWIDTH_METHOD"><code class="docutils literal notranslate"><span class="pre">KDEBase.BANDWIDTH_METHOD</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEBase.get_kde_function"><code class="docutils literal notranslate"><span class="pre">KDEBase.get_kde_function()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEBase.get_mixture_components"><code class="docutils literal notranslate"><span class="pre">KDEBase.get_mixture_components()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEBase.pdf"><code class="docutils literal notranslate"><span class="pre">KDEBase.pdf()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyCS"><code class="docutils literal notranslate"><span class="pre">KDEyCS</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyCS.aggregate"><code class="docutils literal notranslate"><span class="pre">KDEyCS.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyCS.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">KDEyCS.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyCS.gram_matrix_mix_sum"><code class="docutils literal notranslate"><span class="pre">KDEyCS.gram_matrix_mix_sum()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyHD"><code class="docutils literal notranslate"><span class="pre">KDEyHD</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyHD.aggregate"><code class="docutils literal notranslate"><span class="pre">KDEyHD.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyHD.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">KDEyHD.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyML"><code class="docutils literal notranslate"><span class="pre">KDEyML</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyML.aggregate"><code class="docutils literal notranslate"><span class="pre">KDEyML.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._kdey.KDEyML.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">KDEyML.aggregation_fit()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetModule"><code class="docutils literal notranslate"><span class="pre">QuaNetModule</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetModule.device"><code class="docutils literal notranslate"><span class="pre">QuaNetModule.device</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetModule.forward"><code class="docutils literal notranslate"><span class="pre">QuaNetModule.forward()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.classes_"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.classes_</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.clean_checkpoint"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.clean_checkpoint()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.clean_checkpoint_dir"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.clean_checkpoint_dir()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.fit"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.get_params"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.quantify"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.quantify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._neural.QuaNetTrainer.set_params"><code class="docutils literal notranslate"><span class="pre">QuaNetTrainer.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._neural.mae_loss"><code class="docutils literal notranslate"><span class="pre">mae_loss()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MAX"><code class="docutils literal notranslate"><span class="pre">MAX</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MAX.condition"><code class="docutils literal notranslate"><span class="pre">MAX.condition()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MS"><code class="docutils literal notranslate"><span class="pre">MS</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MS.aggregate"><code class="docutils literal notranslate"><span class="pre">MS.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MS.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">MS.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MS.condition"><code class="docutils literal notranslate"><span class="pre">MS.condition()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MS2"><code class="docutils literal notranslate"><span class="pre">MS2</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.MS2.discard"><code class="docutils literal notranslate"><span class="pre">MS2.discard()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.T50"><code class="docutils literal notranslate"><span class="pre">T50</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.T50.condition"><code class="docutils literal notranslate"><span class="pre">T50.condition()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization"><code class="docutils literal notranslate"><span class="pre">ThresholdOptimization</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.aggregate"><code class="docutils literal notranslate"><span class="pre">ThresholdOptimization.aggregate()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.aggregate_with_threshold"><code class="docutils literal notranslate"><span class="pre">ThresholdOptimization.aggregate_with_threshold()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.aggregation_fit"><code class="docutils literal notranslate"><span class="pre">ThresholdOptimization.aggregation_fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.condition"><code class="docutils literal notranslate"><span class="pre">ThresholdOptimization.condition()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.ThresholdOptimization.discard"><code class="docutils literal notranslate"><span class="pre">ThresholdOptimization.discard()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.X"><code class="docutils literal notranslate"><span class="pre">X</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method._threshold_optim.X.condition"><code class="docutils literal notranslate"><span class="pre">X.condition()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.method.html#module-quapy.method.base">quapy.method.base module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.base.BaseQuantifier"><code class="docutils literal notranslate"><span class="pre">BaseQuantifier</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.base.BaseQuantifier.fit"><code class="docutils literal notranslate"><span class="pre">BaseQuantifier.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.base.BaseQuantifier.quantify"><code class="docutils literal notranslate"><span class="pre">BaseQuantifier.quantify()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.base.BinaryQuantifier"><code class="docutils literal notranslate"><span class="pre">BinaryQuantifier</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.base.OneVsAll"><code class="docutils literal notranslate"><span class="pre">OneVsAll</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.base.OneVsAllGeneric"><code class="docutils literal notranslate"><span class="pre">OneVsAllGeneric</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.base.OneVsAllGeneric.classes_"><code class="docutils literal notranslate"><span class="pre">OneVsAllGeneric.classes_</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.base.OneVsAllGeneric.fit"><code class="docutils literal notranslate"><span class="pre">OneVsAllGeneric.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.base.OneVsAllGeneric.quantify"><code class="docutils literal notranslate"><span class="pre">OneVsAllGeneric.quantify()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.base.newOneVsAll"><code class="docutils literal notranslate"><span class="pre">newOneVsAll()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.method.html#module-quapy.method.meta">quapy.method.meta module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.EACC"><code class="docutils literal notranslate"><span class="pre">EACC()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.ECC"><code class="docutils literal notranslate"><span class="pre">ECC()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.EEMQ"><code class="docutils literal notranslate"><span class="pre">EEMQ()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.EHDy"><code class="docutils literal notranslate"><span class="pre">EHDy()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.EPACC"><code class="docutils literal notranslate"><span class="pre">EPACC()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble"><code class="docutils literal notranslate"><span class="pre">Ensemble</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.VALID_POLICIES"><code class="docutils literal notranslate"><span class="pre">Ensemble.VALID_POLICIES</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.aggregative"><code class="docutils literal notranslate"><span class="pre">Ensemble.aggregative</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.fit"><code class="docutils literal notranslate"><span class="pre">Ensemble.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.get_params"><code class="docutils literal notranslate"><span class="pre">Ensemble.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.probabilistic"><code class="docutils literal notranslate"><span class="pre">Ensemble.probabilistic</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.quantify"><code class="docutils literal notranslate"><span class="pre">Ensemble.quantify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.Ensemble.set_params"><code class="docutils literal notranslate"><span class="pre">Ensemble.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator"><code class="docutils literal notranslate"><span class="pre">MedianEstimator</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator.fit"><code class="docutils literal notranslate"><span class="pre">MedianEstimator.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator.get_params"><code class="docutils literal notranslate"><span class="pre">MedianEstimator.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator.quantify"><code class="docutils literal notranslate"><span class="pre">MedianEstimator.quantify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator.set_params"><code class="docutils literal notranslate"><span class="pre">MedianEstimator.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator2"><code class="docutils literal notranslate"><span class="pre">MedianEstimator2</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator2.fit"><code class="docutils literal notranslate"><span class="pre">MedianEstimator2.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator2.get_params"><code class="docutils literal notranslate"><span class="pre">MedianEstimator2.get_params()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator2.quantify"><code class="docutils literal notranslate"><span class="pre">MedianEstimator2.quantify()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.meta.MedianEstimator2.set_params"><code class="docutils literal notranslate"><span class="pre">MedianEstimator2.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.ensembleFactory"><code class="docutils literal notranslate"><span class="pre">ensembleFactory()</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.meta.get_probability_distribution"><code class="docutils literal notranslate"><span class="pre">get_probability_distribution()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.method.html#module-quapy.method.non_aggregative">quapy.method.non_aggregative module</a><ul>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.DMx"><code class="docutils literal notranslate"><span class="pre">DMx</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.DMx.HDx"><code class="docutils literal notranslate"><span class="pre">DMx.HDx()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.DMx.fit"><code class="docutils literal notranslate"><span class="pre">DMx.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.DMx.quantify"><code class="docutils literal notranslate"><span class="pre">DMx.quantify()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.DistributionMatchingX"><code class="docutils literal notranslate"><span class="pre">DistributionMatchingX</span></code></a></li>
|
||||
<li class="toctree-l6"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation"><code class="docutils literal notranslate"><span class="pre">MaximumLikelihoodPrevalenceEstimation</span></code></a><ul>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.fit"><code class="docutils literal notranslate"><span class="pre">MaximumLikelihoodPrevalenceEstimation.fit()</span></code></a></li>
|
||||
<li class="toctree-l7"><a class="reference internal" href="quapy.method.html#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.quantify"><code class="docutils literal notranslate"><span class="pre">MaximumLikelihoodPrevalenceEstimation.quantify()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.method.html#module-quapy.method">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.error">quapy.error module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.absolute_error"><code class="docutils literal notranslate"><span class="pre">absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.acc_error"><code class="docutils literal notranslate"><span class="pre">acc_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.acce"><code class="docutils literal notranslate"><span class="pre">acce()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.ae"><code class="docutils literal notranslate"><span class="pre">ae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.f1_error"><code class="docutils literal notranslate"><span class="pre">f1_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.f1e"><code class="docutils literal notranslate"><span class="pre">f1e()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.from_name"><code class="docutils literal notranslate"><span class="pre">from_name()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.kld"><code class="docutils literal notranslate"><span class="pre">kld()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mae"><code class="docutils literal notranslate"><span class="pre">mae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mean_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mean_normalized_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_normalized_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mean_normalized_relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_normalized_relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mean_relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mkld"><code class="docutils literal notranslate"><span class="pre">mkld()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mnae"><code class="docutils literal notranslate"><span class="pre">mnae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mnkld"><code class="docutils literal notranslate"><span class="pre">mnkld()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mnrae"><code class="docutils literal notranslate"><span class="pre">mnrae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mrae"><code class="docutils literal notranslate"><span class="pre">mrae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.mse"><code class="docutils literal notranslate"><span class="pre">mse()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.nae"><code class="docutils literal notranslate"><span class="pre">nae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.nkld"><code class="docutils literal notranslate"><span class="pre">nkld()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.normalized_absolute_error"><code class="docutils literal notranslate"><span class="pre">normalized_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.normalized_relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">normalized_relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.nrae"><code class="docutils literal notranslate"><span class="pre">nrae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.rae"><code class="docutils literal notranslate"><span class="pre">rae()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.se"><code class="docutils literal notranslate"><span class="pre">se()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.error.smooth"><code class="docutils literal notranslate"><span class="pre">smooth()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.evaluation">quapy.evaluation module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.evaluation.evaluate"><code class="docutils literal notranslate"><span class="pre">evaluate()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.evaluation.evaluate_on_samples"><code class="docutils literal notranslate"><span class="pre">evaluate_on_samples()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.evaluation.evaluation_report"><code class="docutils literal notranslate"><span class="pre">evaluation_report()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.evaluation.prediction"><code class="docutils literal notranslate"><span class="pre">prediction()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.functional">quapy.functional module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.HellingerDistance"><code class="docutils literal notranslate"><span class="pre">HellingerDistance()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.TopsoeDistance"><code class="docutils literal notranslate"><span class="pre">TopsoeDistance()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.adjusted_quantification"><code class="docutils literal notranslate"><span class="pre">adjusted_quantification()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.argmin_prevalence"><code class="docutils literal notranslate"><span class="pre">argmin_prevalence()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.as_binary_prevalence"><code class="docutils literal notranslate"><span class="pre">as_binary_prevalence()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.check_prevalence_vector"><code class="docutils literal notranslate"><span class="pre">check_prevalence_vector()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.get_divergence"><code class="docutils literal notranslate"><span class="pre">get_divergence()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.get_nprevpoints_approximation"><code class="docutils literal notranslate"><span class="pre">get_nprevpoints_approximation()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.linear_search"><code class="docutils literal notranslate"><span class="pre">linear_search()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.normalize_prevalence"><code class="docutils literal notranslate"><span class="pre">normalize_prevalence()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.num_prevalence_combinations"><code class="docutils literal notranslate"><span class="pre">num_prevalence_combinations()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.optim_minimize"><code class="docutils literal notranslate"><span class="pre">optim_minimize()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.prevalence_from_labels"><code class="docutils literal notranslate"><span class="pre">prevalence_from_labels()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.prevalence_from_probabilities"><code class="docutils literal notranslate"><span class="pre">prevalence_from_probabilities()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.prevalence_linspace"><code class="docutils literal notranslate"><span class="pre">prevalence_linspace()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.strprev"><code class="docutils literal notranslate"><span class="pre">strprev()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.uniform_prevalence_sampling"><code class="docutils literal notranslate"><span class="pre">uniform_prevalence_sampling()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.functional.uniform_simplex_sampling"><code class="docutils literal notranslate"><span class="pre">uniform_simplex_sampling()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.model_selection">quapy.model_selection module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.ConfigStatus"><code class="docutils literal notranslate"><span class="pre">ConfigStatus</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.ConfigStatus.failed"><code class="docutils literal notranslate"><span class="pre">ConfigStatus.failed()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.ConfigStatus.success"><code class="docutils literal notranslate"><span class="pre">ConfigStatus.success()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ"><code class="docutils literal notranslate"><span class="pre">GridSearchQ</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.best_model"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.best_model()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.fit"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.fit()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.get_params"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.get_params()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.quantify"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.quantify()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.set_params"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.Status"><code class="docutils literal notranslate"><span class="pre">Status</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.ERROR"><code class="docutils literal notranslate"><span class="pre">Status.ERROR</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.INVALID"><code class="docutils literal notranslate"><span class="pre">Status.INVALID</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.SUCCESS"><code class="docutils literal notranslate"><span class="pre">Status.SUCCESS</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.TIMEOUT"><code class="docutils literal notranslate"><span class="pre">Status.TIMEOUT</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.cross_val_predict"><code class="docutils literal notranslate"><span class="pre">cross_val_predict()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.expand_grid"><code class="docutils literal notranslate"><span class="pre">expand_grid()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.group_params"><code class="docutils literal notranslate"><span class="pre">group_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.plot">quapy.plot module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.plot.binary_bias_bins"><code class="docutils literal notranslate"><span class="pre">binary_bias_bins()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.plot.binary_bias_global"><code class="docutils literal notranslate"><span class="pre">binary_bias_global()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.plot.binary_diagonal"><code class="docutils literal notranslate"><span class="pre">binary_diagonal()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.plot.brokenbar_supremacy_by_drift"><code class="docutils literal notranslate"><span class="pre">brokenbar_supremacy_by_drift()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.plot.error_by_drift"><code class="docutils literal notranslate"><span class="pre">error_by_drift()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.protocol">quapy.protocol module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.APP"><code class="docutils literal notranslate"><span class="pre">APP</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.APP.prevalence_grid"><code class="docutils literal notranslate"><span class="pre">APP.prevalence_grid()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.APP.sample"><code class="docutils literal notranslate"><span class="pre">APP.sample()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.APP.samples_parameters"><code class="docutils literal notranslate"><span class="pre">APP.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.APP.total"><code class="docutils literal notranslate"><span class="pre">APP.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractProtocol"><code class="docutils literal notranslate"><span class="pre">AbstractProtocol</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractProtocol.total"><code class="docutils literal notranslate"><span class="pre">AbstractProtocol.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.collator"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.collator()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.random_state"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.random_state</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.sample"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.sample()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.samples_parameters"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.samples_parameters()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.ArtificialPrevalenceProtocol"><code class="docutils literal notranslate"><span class="pre">ArtificialPrevalenceProtocol</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer"><code class="docutils literal notranslate"><span class="pre">DomainMixer</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer.sample"><code class="docutils literal notranslate"><span class="pre">DomainMixer.sample()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer.samples_parameters"><code class="docutils literal notranslate"><span class="pre">DomainMixer.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer.total"><code class="docutils literal notranslate"><span class="pre">DomainMixer.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.IterateProtocol"><code class="docutils literal notranslate"><span class="pre">IterateProtocol</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.IterateProtocol.total"><code class="docutils literal notranslate"><span class="pre">IterateProtocol.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.NPP"><code class="docutils literal notranslate"><span class="pre">NPP</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.NPP.sample"><code class="docutils literal notranslate"><span class="pre">NPP.sample()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.NPP.samples_parameters"><code class="docutils literal notranslate"><span class="pre">NPP.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.NPP.total"><code class="docutils literal notranslate"><span class="pre">NPP.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.NaturalPrevalenceProtocol"><code class="docutils literal notranslate"><span class="pre">NaturalPrevalenceProtocol</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.RETURN_TYPES"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.RETURN_TYPES</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_collator"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.get_collator()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_labelled_collection"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.get_labelled_collection()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.on_preclassified_instances"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.on_preclassified_instances()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.UPP"><code class="docutils literal notranslate"><span class="pre">UPP</span></code></a><ul>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.UPP.sample"><code class="docutils literal notranslate"><span class="pre">UPP.sample()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.UPP.samples_parameters"><code class="docutils literal notranslate"><span class="pre">UPP.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l5"><a class="reference internal" href="quapy.html#quapy.protocol.UPP.total"><code class="docutils literal notranslate"><span class="pre">UPP.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.UniformPrevalenceProtocol"><code class="docutils literal notranslate"><span class="pre">UniformPrevalenceProtocol</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.util">quapy.util module</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.EarlyStop"><code class="docutils literal notranslate"><span class="pre">EarlyStop</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.create_if_not_exist"><code class="docutils literal notranslate"><span class="pre">create_if_not_exist()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.create_parent_dir"><code class="docutils literal notranslate"><span class="pre">create_parent_dir()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.download_file"><code class="docutils literal notranslate"><span class="pre">download_file()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.download_file_if_not_exists"><code class="docutils literal notranslate"><span class="pre">download_file_if_not_exists()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.get_quapy_home"><code class="docutils literal notranslate"><span class="pre">get_quapy_home()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.map_parallel"><code class="docutils literal notranslate"><span class="pre">map_parallel()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.parallel"><code class="docutils literal notranslate"><span class="pre">parallel()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.pickled_resource"><code class="docutils literal notranslate"><span class="pre">pickled_resource()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.save_text_file"><code class="docutils literal notranslate"><span class="pre">save_text_file()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.temp_seed"><code class="docutils literal notranslate"><span class="pre">temp_seed()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.util.timeout"><code class="docutils literal notranslate"><span class="pre">timeout()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">API Developers documentation</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html">quapy package</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
</section>
|
||||
<section id="indices-and-tables">
|
||||
<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Permalink to this heading">¶</a></h1>
|
||||
<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Link to this heading"></a></h1>
|
||||
<ul class="simple">
|
||||
<li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
|
||||
<li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
|
||||
|
|
@ -174,72 +682,33 @@ See the <a class="reference internal" href="Evaluation.html"><span class="doc">E
|
|||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="#">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">Welcome to QuaPy’s documentation!</a><ul>
|
||||
<li><a class="reference internal" href="#introduction">Introduction</a><ul>
|
||||
<li><a class="reference internal" href="#a-quick-example">A quick example:</a></li>
|
||||
<li><a class="reference internal" href="#features">Features</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><a class="reference internal" href="#indices-and-tables">Indices and tables</a></li>
|
||||
</ul>
|
||||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||||
<a href="modules.html" class="btn btn-neutral float-right" title="quapy" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||||
</div>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="Installation.html"
|
||||
title="next chapter">Installation</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/index.rst.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Installation.html" title="Installation"
|
||||
>next</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="#">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Welcome to QuaPy’s documentation!</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,71 +1,278 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>quapy — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>quapy — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script async="async" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="quapy package" href="quapy.html" />
|
||||
<link rel="prev" title="Plotting" href="Plotting.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.html" title="quapy package"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Plotting.html" title="Plotting"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">quapy</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<link rel="prev" title="Welcome to QuaPy’s documentation!" href="index.html" />
|
||||
</head>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
<a href="index.html" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">quapy</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html">quapy package</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="index.html">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item active">quapy</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
<a href="_sources/modules.rst.txt" rel="nofollow"> View page source</a>
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<section id="quapy">
|
||||
<h1>quapy<a class="headerlink" href="#quapy" title="Permalink to this heading">¶</a></h1>
|
||||
<h1>quapy<a class="headerlink" href="#quapy" title="Link to this heading"></a></h1>
|
||||
<div class="toctree-wrapper compound">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quapy.html">quapy package</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#subpackages">Subpackages</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.classification.html">quapy.classification package</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.calibration">quapy.classification.calibration module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.methods">quapy.classification.methods module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.neural">quapy.classification.neural module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html#module-quapy.classification.svmperf">quapy.classification.svmperf module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html#module-quapy.classification">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.data.html">quapy.data package</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html#module-quapy.data.base">quapy.data.base module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html#module-quapy.data.datasets">quapy.data.datasets module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html#module-quapy.data.preprocessing">quapy.data.preprocessing module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html#module-quapy.data.reader">quapy.data.reader module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html#module-quapy.data">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.method.html">quapy.method package</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html#module-quapy.method.aggregative">quapy.method.aggregative module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html#module-quapy.method.base">quapy.method.base module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html#module-quapy.method.meta">quapy.method.meta module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html#module-quapy.method.non_aggregative">quapy.method.non_aggregative module</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html#module-quapy.method">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.error">quapy.error</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.evaluation">quapy.evaluation</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#quapy-protocol">quapy.protocol</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.functional">quapy.functional</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.model_selection">quapy.model_selection</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.plot">quapy.plot</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.util">quapy.util</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#subpackages">Subpackages</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.error">quapy.error module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.absolute_error"><code class="docutils literal notranslate"><span class="pre">absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.acc_error"><code class="docutils literal notranslate"><span class="pre">acc_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.acce"><code class="docutils literal notranslate"><span class="pre">acce()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.ae"><code class="docutils literal notranslate"><span class="pre">ae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.f1_error"><code class="docutils literal notranslate"><span class="pre">f1_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.f1e"><code class="docutils literal notranslate"><span class="pre">f1e()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.from_name"><code class="docutils literal notranslate"><span class="pre">from_name()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.kld"><code class="docutils literal notranslate"><span class="pre">kld()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mae"><code class="docutils literal notranslate"><span class="pre">mae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mean_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mean_normalized_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_normalized_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mean_normalized_relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_normalized_relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mean_relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">mean_relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mkld"><code class="docutils literal notranslate"><span class="pre">mkld()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mnae"><code class="docutils literal notranslate"><span class="pre">mnae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mnkld"><code class="docutils literal notranslate"><span class="pre">mnkld()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mnrae"><code class="docutils literal notranslate"><span class="pre">mnrae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mrae"><code class="docutils literal notranslate"><span class="pre">mrae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.mse"><code class="docutils literal notranslate"><span class="pre">mse()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.nae"><code class="docutils literal notranslate"><span class="pre">nae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.nkld"><code class="docutils literal notranslate"><span class="pre">nkld()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.normalized_absolute_error"><code class="docutils literal notranslate"><span class="pre">normalized_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.normalized_relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">normalized_relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.nrae"><code class="docutils literal notranslate"><span class="pre">nrae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.rae"><code class="docutils literal notranslate"><span class="pre">rae()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.relative_absolute_error"><code class="docutils literal notranslate"><span class="pre">relative_absolute_error()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.se"><code class="docutils literal notranslate"><span class="pre">se()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.error.smooth"><code class="docutils literal notranslate"><span class="pre">smooth()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.evaluation">quapy.evaluation module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.evaluation.evaluate"><code class="docutils literal notranslate"><span class="pre">evaluate()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.evaluation.evaluate_on_samples"><code class="docutils literal notranslate"><span class="pre">evaluate_on_samples()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.evaluation.evaluation_report"><code class="docutils literal notranslate"><span class="pre">evaluation_report()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.evaluation.prediction"><code class="docutils literal notranslate"><span class="pre">prediction()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.functional">quapy.functional module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.HellingerDistance"><code class="docutils literal notranslate"><span class="pre">HellingerDistance()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.TopsoeDistance"><code class="docutils literal notranslate"><span class="pre">TopsoeDistance()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.adjusted_quantification"><code class="docutils literal notranslate"><span class="pre">adjusted_quantification()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.argmin_prevalence"><code class="docutils literal notranslate"><span class="pre">argmin_prevalence()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.as_binary_prevalence"><code class="docutils literal notranslate"><span class="pre">as_binary_prevalence()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.check_prevalence_vector"><code class="docutils literal notranslate"><span class="pre">check_prevalence_vector()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.get_divergence"><code class="docutils literal notranslate"><span class="pre">get_divergence()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.get_nprevpoints_approximation"><code class="docutils literal notranslate"><span class="pre">get_nprevpoints_approximation()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.linear_search"><code class="docutils literal notranslate"><span class="pre">linear_search()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.normalize_prevalence"><code class="docutils literal notranslate"><span class="pre">normalize_prevalence()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.num_prevalence_combinations"><code class="docutils literal notranslate"><span class="pre">num_prevalence_combinations()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.optim_minimize"><code class="docutils literal notranslate"><span class="pre">optim_minimize()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.prevalence_from_labels"><code class="docutils literal notranslate"><span class="pre">prevalence_from_labels()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.prevalence_from_probabilities"><code class="docutils literal notranslate"><span class="pre">prevalence_from_probabilities()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.prevalence_linspace"><code class="docutils literal notranslate"><span class="pre">prevalence_linspace()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.strprev"><code class="docutils literal notranslate"><span class="pre">strprev()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.uniform_prevalence_sampling"><code class="docutils literal notranslate"><span class="pre">uniform_prevalence_sampling()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.functional.uniform_simplex_sampling"><code class="docutils literal notranslate"><span class="pre">uniform_simplex_sampling()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.model_selection">quapy.model_selection module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.model_selection.ConfigStatus"><code class="docutils literal notranslate"><span class="pre">ConfigStatus</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.ConfigStatus.failed"><code class="docutils literal notranslate"><span class="pre">ConfigStatus.failed()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.ConfigStatus.success"><code class="docutils literal notranslate"><span class="pre">ConfigStatus.success()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ"><code class="docutils literal notranslate"><span class="pre">GridSearchQ</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.best_model"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.best_model()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.fit"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.fit()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.get_params"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.get_params()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.quantify"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.quantify()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.GridSearchQ.set_params"><code class="docutils literal notranslate"><span class="pre">GridSearchQ.set_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.model_selection.Status"><code class="docutils literal notranslate"><span class="pre">Status</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.ERROR"><code class="docutils literal notranslate"><span class="pre">Status.ERROR</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.INVALID"><code class="docutils literal notranslate"><span class="pre">Status.INVALID</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.SUCCESS"><code class="docutils literal notranslate"><span class="pre">Status.SUCCESS</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.model_selection.Status.TIMEOUT"><code class="docutils literal notranslate"><span class="pre">Status.TIMEOUT</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.model_selection.cross_val_predict"><code class="docutils literal notranslate"><span class="pre">cross_val_predict()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.model_selection.expand_grid"><code class="docutils literal notranslate"><span class="pre">expand_grid()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.model_selection.group_params"><code class="docutils literal notranslate"><span class="pre">group_params()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.plot">quapy.plot module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.plot.binary_bias_bins"><code class="docutils literal notranslate"><span class="pre">binary_bias_bins()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.plot.binary_bias_global"><code class="docutils literal notranslate"><span class="pre">binary_bias_global()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.plot.binary_diagonal"><code class="docutils literal notranslate"><span class="pre">binary_diagonal()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.plot.brokenbar_supremacy_by_drift"><code class="docutils literal notranslate"><span class="pre">brokenbar_supremacy_by_drift()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.plot.error_by_drift"><code class="docutils literal notranslate"><span class="pre">error_by_drift()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.protocol">quapy.protocol module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.APP"><code class="docutils literal notranslate"><span class="pre">APP</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.APP.prevalence_grid"><code class="docutils literal notranslate"><span class="pre">APP.prevalence_grid()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.APP.sample"><code class="docutils literal notranslate"><span class="pre">APP.sample()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.APP.samples_parameters"><code class="docutils literal notranslate"><span class="pre">APP.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.APP.total"><code class="docutils literal notranslate"><span class="pre">APP.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractProtocol"><code class="docutils literal notranslate"><span class="pre">AbstractProtocol</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractProtocol.total"><code class="docutils literal notranslate"><span class="pre">AbstractProtocol.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.collator"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.collator()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.random_state"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.random_state</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.sample"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.sample()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.samples_parameters"><code class="docutils literal notranslate"><span class="pre">AbstractStochasticSeededProtocol.samples_parameters()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.ArtificialPrevalenceProtocol"><code class="docutils literal notranslate"><span class="pre">ArtificialPrevalenceProtocol</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer"><code class="docutils literal notranslate"><span class="pre">DomainMixer</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer.sample"><code class="docutils literal notranslate"><span class="pre">DomainMixer.sample()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer.samples_parameters"><code class="docutils literal notranslate"><span class="pre">DomainMixer.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.DomainMixer.total"><code class="docutils literal notranslate"><span class="pre">DomainMixer.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.IterateProtocol"><code class="docutils literal notranslate"><span class="pre">IterateProtocol</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.IterateProtocol.total"><code class="docutils literal notranslate"><span class="pre">IterateProtocol.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.NPP"><code class="docutils literal notranslate"><span class="pre">NPP</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.NPP.sample"><code class="docutils literal notranslate"><span class="pre">NPP.sample()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.NPP.samples_parameters"><code class="docutils literal notranslate"><span class="pre">NPP.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.NPP.total"><code class="docutils literal notranslate"><span class="pre">NPP.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.NaturalPrevalenceProtocol"><code class="docutils literal notranslate"><span class="pre">NaturalPrevalenceProtocol</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.RETURN_TYPES"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.RETURN_TYPES</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_collator"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.get_collator()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_labelled_collection"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.get_labelled_collection()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.OnLabelledCollectionProtocol.on_preclassified_instances"><code class="docutils literal notranslate"><span class="pre">OnLabelledCollectionProtocol.on_preclassified_instances()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.UPP"><code class="docutils literal notranslate"><span class="pre">UPP</span></code></a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.UPP.sample"><code class="docutils literal notranslate"><span class="pre">UPP.sample()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.UPP.samples_parameters"><code class="docutils literal notranslate"><span class="pre">UPP.samples_parameters()</span></code></a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.html#quapy.protocol.UPP.total"><code class="docutils literal notranslate"><span class="pre">UPP.total()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.protocol.UniformPrevalenceProtocol"><code class="docutils literal notranslate"><span class="pre">UniformPrevalenceProtocol</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy.util">quapy.util module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.EarlyStop"><code class="docutils literal notranslate"><span class="pre">EarlyStop</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.create_if_not_exist"><code class="docutils literal notranslate"><span class="pre">create_if_not_exist()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.create_parent_dir"><code class="docutils literal notranslate"><span class="pre">create_parent_dir()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.download_file"><code class="docutils literal notranslate"><span class="pre">download_file()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.download_file_if_not_exists"><code class="docutils literal notranslate"><span class="pre">download_file_if_not_exists()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.get_quapy_home"><code class="docutils literal notranslate"><span class="pre">get_quapy_home()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.map_parallel"><code class="docutils literal notranslate"><span class="pre">map_parallel()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.parallel"><code class="docutils literal notranslate"><span class="pre">parallel()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.pickled_resource"><code class="docutils literal notranslate"><span class="pre">pickled_resource()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.save_text_file"><code class="docutils literal notranslate"><span class="pre">save_text_file()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.temp_seed"><code class="docutils literal notranslate"><span class="pre">temp_seed()</span></code></a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#quapy.util.timeout"><code class="docutils literal notranslate"><span class="pre">timeout()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quapy.html#module-quapy">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
|
|
@ -74,65 +281,34 @@
|
|||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||||
<a href="index.html" class="btn btn-neutral float-left" title="Welcome to QuaPy’s documentation!" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||||
<a href="quapy.html" class="btn btn-neutral float-right" title="quapy package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||||
</div>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="Plotting.html"
|
||||
title="previous chapter">Plotting</a></p>
|
||||
</section>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="quapy.html"
|
||||
title="next chapter">quapy package</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/modules.rst.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.html" title="quapy package"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="Plotting.html" title="Plotting"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">quapy</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Binary file not shown.
|
|
@ -1,51 +1,76 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Python Module Index — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Python Module Index — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="#" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Python Module Index</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
</head>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
<a href="index.html" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">quapy</a></li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="index.html">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item active">Python Module Index</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
|
||||
<h1>Python Module Index</h1>
|
||||
|
||||
|
|
@ -133,6 +158,21 @@
|
|||
<td>   
|
||||
<a href="quapy.method.html#module-quapy.method"><code class="xref">quapy.method</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="cg-1">
|
||||
<td></td>
|
||||
<td>   
|
||||
<a href="quapy.method.html#module-quapy.method._kdey"><code class="xref">quapy.method._kdey</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="cg-1">
|
||||
<td></td>
|
||||
<td>   
|
||||
<a href="quapy.method.html#module-quapy.method._neural"><code class="xref">quapy.method._neural</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="cg-1">
|
||||
<td></td>
|
||||
<td>   
|
||||
<a href="quapy.method.html#module-quapy.method._threshold_optim"><code class="xref">quapy.method._threshold_optim</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="cg-1">
|
||||
<td></td>
|
||||
<td>   
|
||||
|
|
@ -148,11 +188,6 @@
|
|||
<td>   
|
||||
<a href="quapy.method.html#module-quapy.method.meta"><code class="xref">quapy.method.meta</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="cg-1">
|
||||
<td></td>
|
||||
<td>   
|
||||
<a href="quapy.method.html#module-quapy.method.neural"><code class="xref">quapy.method.neural</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="cg-1">
|
||||
<td></td>
|
||||
<td>   
|
||||
|
|
@ -181,42 +216,31 @@
|
|||
</table>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="#" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Python Module Index</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,72 +1,109 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>quapy.classification package — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>quapy.classification package — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="quapy.data package" href="quapy.data.html" />
|
||||
<link rel="prev" title="quapy package" href="quapy.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.data.html" title="quapy.data package"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.html" title="quapy package"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-1"><a href="modules.html" >quapy</a> »</li>
|
||||
<li class="nav-item nav-item-2"><a href="quapy.html" accesskey="U">quapy package</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">quapy.classification package</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<link rel="prev" title="quapy package" href="quapy.html" />
|
||||
</head>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="quapy-classification-package">
|
||||
<h1>quapy.classification package<a class="headerlink" href="#quapy-classification-package" title="Permalink to this heading">¶</a></h1>
|
||||
<section id="submodules">
|
||||
<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading">¶</a></h2>
|
||||
</section>
|
||||
<section id="quapy-classification-calibration">
|
||||
<h2>quapy.classification.calibration<a class="headerlink" href="#quapy-classification-calibration" title="Permalink to this heading">¶</a></h2>
|
||||
<div class="versionadded">
|
||||
<p><span class="versionmodified added">New in version 0.1.7.</span></p>
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
<a href="index.html" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
<span class="target" id="module-quapy.classification.calibration"></span><dl class="py class">
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="modules.html">quapy</a><ul class="current">
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="quapy.html">quapy package</a><ul class="current">
|
||||
<li class="toctree-l3 current"><a class="reference internal" href="quapy.html#subpackages">Subpackages</a><ul class="current">
|
||||
<li class="toctree-l4 current"><a class="current reference internal" href="#">quapy.classification package</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.data.html">quapy.data package</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html">quapy.method package</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.error">quapy.error module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.evaluation">quapy.evaluation module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.functional">quapy.functional module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.model_selection">quapy.model_selection module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.plot">quapy.plot module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.protocol">quapy.protocol module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.util">quapy.util module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="index.html">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item"><a href="modules.html">quapy</a></li>
|
||||
<li class="breadcrumb-item"><a href="quapy.html">quapy package</a></li>
|
||||
<li class="breadcrumb-item active">quapy.classification package</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
<a href="_sources/quapy.classification.rst.txt" rel="nofollow"> View page source</a>
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<section id="quapy-classification-package">
|
||||
<h1>quapy.classification package<a class="headerlink" href="#quapy-classification-package" title="Link to this heading"></a></h1>
|
||||
<section id="submodules">
|
||||
<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading"></a></h2>
|
||||
</section>
|
||||
<section id="module-quapy.classification.calibration">
|
||||
<span id="quapy-classification-calibration-module"></span><h2>quapy.classification.calibration module<a class="headerlink" href="#module-quapy.classification.calibration" title="Link to this heading"></a></h2>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.BCTSCalibration">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">BCTSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.BCTSCalibration" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">BCTSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#BCTSCalibration"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.BCTSCalibration" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <a class="reference internal" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase" title="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase</span></code></a></p>
|
||||
<p>Applies the Bias-Corrected Temperature Scaling (BCTS) calibration method from <cite>abstention.calibration</cite>, as defined in
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>:</p>
|
||||
|
|
@ -87,7 +124,7 @@ training set afterwards. Default value is 5.</p></li>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.NBVSCalibration">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">NBVSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.NBVSCalibration" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">NBVSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#NBVSCalibration"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.NBVSCalibration" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <a class="reference internal" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase" title="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase</span></code></a></p>
|
||||
<p>Applies the No-Bias Vector Scaling (NBVS) calibration method from <cite>abstention.calibration</cite>, as defined in
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>:</p>
|
||||
|
|
@ -108,7 +145,7 @@ training set afterwards. Default value is 5.</p></li>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifier">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">RecalibratedProbabilisticClassifier</span></span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifier" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">RecalibratedProbabilisticClassifier</span></span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifier"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifier" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>Abstract class for (re)calibration method from <cite>abstention.calibration</cite>, as defined in
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari, A., Kundaje, A., & Shrikumar, A. (2020, November). Maximum likelihood with bias-corrected calibration
|
||||
|
|
@ -117,10 +154,10 @@ is hard-to-beat at label shift adaptation. In International Conference on Machin
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">RecalibratedProbabilisticClassifierBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">calibrator</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">RecalibratedProbabilisticClassifierBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">calibrator</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifierBase"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">BaseEstimator</span></code>, <a class="reference internal" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifier" title="quapy.classification.calibration.RecalibratedProbabilisticClassifier"><code class="xref py py-class docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifier</span></code></a></p>
|
||||
<p>Applies a (re)calibration method from <cite>abstention.calibration</cite>, as defined in
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>:</p>
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
|
|
@ -137,7 +174,7 @@ training set afterwards. Default value is 5.</p></li>
|
|||
</dl>
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.classes_">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">classes_</span></span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.classes_" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">classes_</span></span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.classes_" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns the classes on which the classifier has been trained on</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -148,7 +185,7 @@ training set afterwards. Default value is 5.</p></li>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit">
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifierBase.fit"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fits the calibration for the probabilistic classifier.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -165,7 +202,7 @@ training set afterwards. Default value is 5.</p></li>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_cv">
|
||||
<span class="sig-name descname"><span class="pre">fit_cv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_cv" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit_cv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifierBase.fit_cv"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_cv" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fits the calibration in a cross-validation manner, i.e., it generates posterior probabilities for all
|
||||
training instances via cross-validation, and then retrains the classifier on all training instances.
|
||||
The posterior probabilities thus generated are used for calibrating the outputs of the classifier.</p>
|
||||
|
|
@ -184,7 +221,7 @@ The posterior probabilities thus generated are used for calibrating the outputs
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_tr_val">
|
||||
<span class="sig-name descname"><span class="pre">fit_tr_val</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_tr_val" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit_tr_val</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifierBase.fit_tr_val"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_tr_val" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fits the calibration in a train/val-split manner, i.e.t, it partitions the training instances into a
|
||||
training and a validation set, and then uses the training samples to learn classifier which is then used
|
||||
to generate posterior probabilities for the held-out validation data. These posteriors are used to calibrate
|
||||
|
|
@ -204,7 +241,7 @@ the classifier. The classifier is not retrained on the whole dataset.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict">
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifierBase.predict"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts class labels for the data instances in <cite>X</cite></p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -218,7 +255,7 @@ the classifier. The classifier is not retrained on the whole dataset.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict_proba">
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict_proba" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#RecalibratedProbabilisticClassifierBase.predict_proba"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict_proba" title="Link to this definition"></a></dt>
|
||||
<dd><p>Generates posterior probabilities for the data instances in <cite>X</cite></p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -234,7 +271,7 @@ the classifier. The classifier is not retrained on the whole dataset.</p>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.TSCalibration">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">TSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.TSCalibration" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">TSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#TSCalibration"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.TSCalibration" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <a class="reference internal" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase" title="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase</span></code></a></p>
|
||||
<p>Applies the Temperature Scaling (TS) calibration method from <cite>abstention.calibration</cite>, as defined in
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>:</p>
|
||||
|
|
@ -255,7 +292,7 @@ training set afterwards. Default value is 5.</p></li>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.calibration.VSCalibration">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">VSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.calibration.VSCalibration" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.calibration.</span></span><span class="sig-name descname"><span class="pre">VSCalibration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">classifier</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/calibration.html#VSCalibration"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.calibration.VSCalibration" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <a class="reference internal" href="#quapy.classification.calibration.RecalibratedProbabilisticClassifierBase" title="quapy.classification.calibration.RecalibratedProbabilisticClassifierBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">RecalibratedProbabilisticClassifierBase</span></code></a></p>
|
||||
<p>Applies the Vector Scaling (VS) calibration method from <cite>abstention.calibration</cite>, as defined in
|
||||
<a class="reference external" href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>:</p>
|
||||
|
|
@ -276,10 +313,10 @@ training set afterwards. Default value is 5.</p></li>
|
|||
|
||||
</section>
|
||||
<section id="module-quapy.classification.methods">
|
||||
<span id="quapy-classification-methods"></span><h2>quapy.classification.methods<a class="headerlink" href="#module-quapy.classification.methods" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-classification-methods-module"></span><h2>quapy.classification.methods module<a class="headerlink" href="#module-quapy.classification.methods" title="Link to this heading"></a></h2>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.methods.</span></span><span class="sig-name descname"><span class="pre">LowRankLogisticRegression</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_components</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.methods.</span></span><span class="sig-name descname"><span class="pre">LowRankLogisticRegression</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_components</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">BaseEstimator</span></code></p>
|
||||
<p>An example of a classification method (i.e., an object that implements <cite>fit</cite>, <cite>predict</cite>, and <cite>predict_proba</cite>)
|
||||
that also generates embedded inputs (i.e., that implements <cite>transform</cite>), as those required for
|
||||
|
|
@ -298,7 +335,7 @@ while classification is performed using <code class="xref py py-class docutils l
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression.fit">
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.fit" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression.fit"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.fit" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fit the model according to the given training data. The fit consists of
|
||||
fitting <cite>TruncatedSVD</cite> and then <cite>LogisticRegression</cite> on the low-rank representation.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -316,21 +353,18 @@ fitting <cite>TruncatedSVD</cite> and then <cite>LogisticRegression</cite> on th
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression.get_params">
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">deep</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.get_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression.get_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.get_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Get hyper-parameters for this estimator.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>deep</strong> – compatibility with sklearn</p>
|
||||
</dd>
|
||||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>a dictionary with parameter names mapped to their values</p>
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>a dictionary with parameter names mapped to their values</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression.predict">
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.predict" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression.predict"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.predict" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts labels for the instances <cite>X</cite> embedded into the low-rank space.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -345,7 +379,7 @@ instances in <cite>X</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression.predict_proba">
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.predict_proba" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression.predict_proba"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.predict_proba" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts posterior probabilities for the instances <cite>X</cite> embedded into the low-rank space.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -359,7 +393,7 @@ instances in <cite>X</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression.set_params">
|
||||
<span class="sig-name descname"><span class="pre">set_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.set_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">set_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression.set_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.set_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Set the parameters of this estimator.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -372,7 +406,7 @@ and eventually also <cite>n_components</cite> for <cite>TruncatedSVD</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.methods.LowRankLogisticRegression.transform">
|
||||
<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.transform" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/methods.html#LowRankLogisticRegression.transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.methods.LowRankLogisticRegression.transform" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns the low-rank approximation of <cite>X</cite> with <cite>n_components</cite> dimensions, or <cite>X</cite> unaltered if
|
||||
<cite>n_components</cite> >= <cite>X.shape[1]</cite>.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -389,10 +423,10 @@ and eventually also <cite>n_components</cite> for <cite>TruncatedSVD</cite></p>
|
|||
|
||||
</section>
|
||||
<section id="module-quapy.classification.neural">
|
||||
<span id="quapy-classification-neural"></span><h2>quapy.classification.neural<a class="headerlink" href="#module-quapy.classification.neural" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-classification-neural-module"></span><h2>quapy.classification.neural module<a class="headerlink" href="#module-quapy.classification.neural" title="Link to this heading"></a></h2>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.CNNnet">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">CNNnet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vocabulary_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">256</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repr_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_heights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">[3,</span> <span class="pre">5,</span> <span class="pre">7]</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.CNNnet" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">CNNnet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vocabulary_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">256</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repr_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_heights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">[3,</span> <span class="pre">5,</span> <span class="pre">7]</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#CNNnet"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.CNNnet" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <a class="reference internal" href="#quapy.classification.neural.TextClassifierNet" title="quapy.classification.neural.TextClassifierNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">TextClassifierNet</span></code></a></p>
|
||||
<p>An implementation of <a class="reference internal" href="#quapy.classification.neural.TextClassifierNet" title="quapy.classification.neural.TextClassifierNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.classification.neural.TextClassifierNet</span></code></a> based on
|
||||
Convolutional Neural Networks.</p>
|
||||
|
|
@ -414,7 +448,7 @@ consecutive tokens that each kernel covers</p></li>
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.CNNnet.document_embedding">
|
||||
<span class="sig-name descname"><span class="pre">document_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.CNNnet.document_embedding" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">document_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#CNNnet.document_embedding"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.CNNnet.document_embedding" title="Link to this definition"></a></dt>
|
||||
<dd><p>Embeds documents (i.e., performs the forward pass up to the
|
||||
next-to-last layer).</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -432,7 +466,7 @@ dimensionality of the embedding</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.CNNnet.get_params">
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.CNNnet.get_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#CNNnet.get_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.CNNnet.get_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Get hyper-parameters for this estimator</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -441,14 +475,9 @@ dimensionality of the embedding</p>
|
|||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py attribute">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.CNNnet.training">
|
||||
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#quapy.classification.neural.CNNnet.training" title="Permalink to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.CNNnet.vocabulary_size">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.classification.neural.CNNnet.vocabulary_size" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.classification.neural.CNNnet.vocabulary_size" title="Link to this definition"></a></dt>
|
||||
<dd><p>Return the size of the vocabulary</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -461,7 +490,7 @@ dimensionality of the embedding</p>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.LSTMnet">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">LSTMnet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vocabulary_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">256</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repr_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lstm_class_nlayers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.LSTMnet" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">LSTMnet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vocabulary_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">256</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repr_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lstm_class_nlayers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#LSTMnet"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.LSTMnet" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <a class="reference internal" href="#quapy.classification.neural.TextClassifierNet" title="quapy.classification.neural.TextClassifierNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">TextClassifierNet</span></code></a></p>
|
||||
<p>An implementation of <a class="reference internal" href="#quapy.classification.neural.TextClassifierNet" title="quapy.classification.neural.TextClassifierNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.classification.neural.TextClassifierNet</span></code></a> based on
|
||||
Long Short Term Memory networks.</p>
|
||||
|
|
@ -480,7 +509,7 @@ Long Short Term Memory networks.</p>
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.LSTMnet.document_embedding">
|
||||
<span class="sig-name descname"><span class="pre">document_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.LSTMnet.document_embedding" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">document_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#LSTMnet.document_embedding"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.LSTMnet.document_embedding" title="Link to this definition"></a></dt>
|
||||
<dd><p>Embeds documents (i.e., performs the forward pass up to the
|
||||
next-to-last layer).</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -498,7 +527,7 @@ dimensionality of the embedding</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.LSTMnet.get_params">
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.LSTMnet.get_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#LSTMnet.get_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.LSTMnet.get_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Get hyper-parameters for this estimator</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -507,14 +536,9 @@ dimensionality of the embedding</p>
|
|||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py attribute">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.LSTMnet.training">
|
||||
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#quapy.classification.neural.LSTMnet.training" title="Permalink to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.LSTMnet.vocabulary_size">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.classification.neural.LSTMnet.vocabulary_size" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.classification.neural.LSTMnet.vocabulary_size" title="Link to this definition"></a></dt>
|
||||
<dd><p>Return the size of the vocabulary</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -527,7 +551,7 @@ dimensionality of the embedding</p>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">NeuralClassifierTrainer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">net</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.classification.neural.TextClassifierNet" title="quapy.classification.neural.TextClassifierNet"><span class="pre">TextClassifierNet</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">patience</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epochs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size_test</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">512</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">300</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpointpath</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'../checkpoint/classifier_net.dat'</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">NeuralClassifierTrainer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">net</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.classification.neural.TextClassifierNet" title="quapy.classification.neural.TextClassifierNet"><span class="pre">TextClassifierNet</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">patience</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epochs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size_test</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">512</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">300</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpointpath</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'../checkpoint/classifier_net.dat'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>Trains a neural network for text classification.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -550,7 +574,7 @@ according to the evaluation in the held-out validation split (default ‘../chec
|
|||
</dl>
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.device">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">device</span></span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.device" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">device</span></span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.device" title="Link to this definition"></a></dt>
|
||||
<dd><p>Gets the device in which the network is allocated</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -561,7 +585,7 @@ according to the evaluation in the held-out validation split (default ‘../chec
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.fit">
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.fit" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.fit"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.fit" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fits the model according to the given training data.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -579,7 +603,7 @@ according to the evaluation in the held-out validation split (default ‘../chec
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.get_params">
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.get_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.get_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.get_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Get hyper-parameters for this estimator</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -590,7 +614,7 @@ according to the evaluation in the held-out validation split (default ‘../chec
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.predict">
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.predict" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.predict"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.predict" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts labels for the instances</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -605,7 +629,7 @@ instances in <cite>X</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.predict_proba">
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.predict_proba" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.predict_proba"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.predict_proba" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts posterior probabilities for the instances</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -619,7 +643,7 @@ instances in <cite>X</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.reset_net_params">
|
||||
<span class="sig-name descname"><span class="pre">reset_net_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vocab_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.reset_net_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">reset_net_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vocab_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.reset_net_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.reset_net_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Reinitialize the network parameters</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -633,7 +657,7 @@ instances in <cite>X</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.set_params">
|
||||
<span class="sig-name descname"><span class="pre">set_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.set_params" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">set_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.set_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.set_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Set the parameters of this trainer and the learner it is training.
|
||||
In this current version, parameter names for the trainer and learner should
|
||||
be disjoint.</p>
|
||||
|
|
@ -646,7 +670,7 @@ be disjoint.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.NeuralClassifierTrainer.transform">
|
||||
<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.transform" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#NeuralClassifierTrainer.transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.NeuralClassifierTrainer.transform" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns the embeddings of the instances</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -663,12 +687,12 @@ where <cite>embed_size</cite> is defined by the classification network</p>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">TextClassifierNet</span></span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">TextClassifierNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code></p>
|
||||
<p>Abstract Text classifier (<cite>torch.nn.Module</cite>)</p>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.dimensions">
|
||||
<span class="sig-name descname"><span class="pre">dimensions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.dimensions" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">dimensions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet.dimensions"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.dimensions" title="Link to this definition"></a></dt>
|
||||
<dd><p>Gets the number of dimensions of the embedding space</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -679,7 +703,7 @@ where <cite>embed_size</cite> is defined by the classification network</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.document_embedding">
|
||||
<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">document_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.document_embedding" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">document_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet.document_embedding"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.document_embedding" title="Link to this definition"></a></dt>
|
||||
<dd><p>Embeds documents (i.e., performs the forward pass up to the
|
||||
next-to-last layer).</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -697,7 +721,7 @@ dimensionality of the embedding</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.forward">
|
||||
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.forward" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet.forward"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.forward" title="Link to this definition"></a></dt>
|
||||
<dd><p>Performs the forward pass.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -713,7 +737,7 @@ for each of the instances and classes</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.get_params">
|
||||
<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.get_params" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet.get_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.get_params" title="Link to this definition"></a></dt>
|
||||
<dd><p>Get hyper-parameters for this estimator</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -724,7 +748,7 @@ for each of the instances and classes</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.predict_proba">
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.predict_proba" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict_proba</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet.predict_proba"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.predict_proba" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts posterior probabilities for the instances in <cite>x</cite></p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -738,14 +762,9 @@ is length of the pad in the batch</p>
|
|||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py attribute">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.training">
|
||||
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.training" title="Permalink to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.vocabulary_size">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.vocabulary_size" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.vocabulary_size" title="Link to this definition"></a></dt>
|
||||
<dd><p>Return the size of the vocabulary</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -756,7 +775,7 @@ is length of the pad in the batch</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TextClassifierNet.xavier_uniform">
|
||||
<span class="sig-name descname"><span class="pre">xavier_uniform</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.xavier_uniform" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">xavier_uniform</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TextClassifierNet.xavier_uniform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TextClassifierNet.xavier_uniform" title="Link to this definition"></a></dt>
|
||||
<dd><p>Performs Xavier initialization of the network parameters</p>
|
||||
</dd></dl>
|
||||
|
||||
|
|
@ -764,7 +783,7 @@ is length of the pad in the batch</p>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TorchDataset">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">TorchDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TorchDataset" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.neural.</span></span><span class="sig-name descname"><span class="pre">TorchDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TorchDataset"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TorchDataset" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></p>
|
||||
<p>Transforms labelled instances into a Torch’s <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.utils.data.DataLoader</span></code> object</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -777,7 +796,7 @@ is length of the pad in the batch</p>
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.neural.TorchDataset.asDataloader">
|
||||
<span class="sig-name descname"><span class="pre">asDataloader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.neural.TorchDataset.asDataloader" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">asDataloader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/neural.html#TorchDataset.asDataloader"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.neural.TorchDataset.asDataloader" title="Link to this definition"></a></dt>
|
||||
<dd><p>Converts the labelled collection into a Torch DataLoader with dynamic padding for
|
||||
the batch</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -801,22 +820,20 @@ applied, meaning that if the longest document in the batch is shorter than
|
|||
|
||||
</section>
|
||||
<section id="module-quapy.classification.svmperf">
|
||||
<span id="quapy-classification-svmperf"></span><h2>quapy.classification.svmperf<a class="headerlink" href="#module-quapy.classification.svmperf" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-classification-svmperf-module"></span><h2>quapy.classification.svmperf module<a class="headerlink" href="#module-quapy.classification.svmperf" title="Link to this heading"></a></h2>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.classification.svmperf.SVMperf">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.svmperf.</span></span><span class="sig-name descname"><span class="pre">SVMperf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">svmperf_base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">C</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'01'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">host_folder</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.svmperf.SVMperf" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.classification.svmperf.</span></span><span class="sig-name descname"><span class="pre">SVMperf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">svmperf_base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">C</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'01'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">host_folder</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/svmperf.html#SVMperf"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.svmperf.SVMperf" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">BaseEstimator</span></code>, <code class="xref py py-class docutils literal notranslate"><span class="pre">ClassifierMixin</span></code></p>
|
||||
<p>A wrapper for the <a class="reference external" href="https://www.cs.cornell.edu/people/tj/svm_light/svm_perf.html">SVM-perf package</a> by Thorsten Joachims.
|
||||
When using losses for quantification, the source code has to be patched. See
|
||||
the <a class="reference external" href="https://hlt-isti.github.io/QuaPy/build/html/Installation.html#svm-perf-with-quantification-oriented-losses">installation documentation</a>
|
||||
for further details.</p>
|
||||
<p>References:</p>
|
||||
<blockquote>
|
||||
<div><ul class="simple">
|
||||
<p class="rubric">References</p>
|
||||
<ul class="simple">
|
||||
<li><p><a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/2700406?casa_token=8D2fHsGCVn0AAAAA:ZfThYOvrzWxMGfZYlQW_y8Cagg-o_l6X_PcF09mdETQ4Tu7jK98mxFbGSXp9ZSO14JkUIYuDGFG0">Esuli et al.2015</a></p></li>
|
||||
<li><p><a class="reference external" href="https://www.sciencedirect.com/science/article/abs/pii/S003132031400291X">Barranquero et al.2015</a></p></li>
|
||||
</ul>
|
||||
</div></blockquote>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
|
|
@ -831,7 +848,7 @@ for further details.</p>
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.svmperf.SVMperf.decision_function">
|
||||
<span class="sig-name descname"><span class="pre">decision_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.decision_function" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">decision_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/svmperf.html#SVMperf.decision_function"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.decision_function" title="Link to this definition"></a></dt>
|
||||
<dd><p>Evaluate the decision function for the samples in <cite>X</cite>.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -848,7 +865,7 @@ for further details.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.svmperf.SVMperf.fit">
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.fit" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/svmperf.html#SVMperf.fit"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.fit" title="Link to this definition"></a></dt>
|
||||
<dd><p>Trains the SVM for the multivariate performance loss</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -865,7 +882,7 @@ for further details.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.classification.svmperf.SVMperf.predict">
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.predict" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/classification/svmperf.html#SVMperf.predict"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.predict" title="Link to this definition"></a></dt>
|
||||
<dd><p>Predicts labels for the instances <cite>X</cite></p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -880,94 +897,46 @@ instances in <cite>X</cite></p>
|
|||
|
||||
<dl class="py attribute">
|
||||
<dt class="sig sig-object py" id="quapy.classification.svmperf.SVMperf.valid_losses">
|
||||
<span class="sig-name descname"><span class="pre">valid_losses</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">{'01':</span> <span class="pre">0,</span> <span class="pre">'f1':</span> <span class="pre">1,</span> <span class="pre">'kld':</span> <span class="pre">12,</span> <span class="pre">'mae':</span> <span class="pre">26,</span> <span class="pre">'mrae':</span> <span class="pre">27,</span> <span class="pre">'nkld':</span> <span class="pre">13,</span> <span class="pre">'q':</span> <span class="pre">22,</span> <span class="pre">'qacc':</span> <span class="pre">23,</span> <span class="pre">'qf1':</span> <span class="pre">24,</span> <span class="pre">'qgm':</span> <span class="pre">25}</span></em><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.valid_losses" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">valid_losses</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">{'01':</span> <span class="pre">0,</span> <span class="pre">'f1':</span> <span class="pre">1,</span> <span class="pre">'kld':</span> <span class="pre">12,</span> <span class="pre">'mae':</span> <span class="pre">26,</span> <span class="pre">'mrae':</span> <span class="pre">27,</span> <span class="pre">'nkld':</span> <span class="pre">13,</span> <span class="pre">'q':</span> <span class="pre">22,</span> <span class="pre">'qacc':</span> <span class="pre">23,</span> <span class="pre">'qf1':</span> <span class="pre">24,</span> <span class="pre">'qgm':</span> <span class="pre">25}</span></em><a class="headerlink" href="#quapy.classification.svmperf.SVMperf.valid_losses" title="Link to this definition"></a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
<section id="module-quapy.classification">
|
||||
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-quapy.classification" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-quapy.classification" title="Link to this heading"></a></h2>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">quapy.classification package</a><ul>
|
||||
<li><a class="reference internal" href="#submodules">Submodules</a></li>
|
||||
<li><a class="reference internal" href="#quapy-classification-calibration">quapy.classification.calibration</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.classification.methods">quapy.classification.methods</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.classification.neural">quapy.classification.neural</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.classification.svmperf">quapy.classification.svmperf</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.classification">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||||
<a href="quapy.html" class="btn btn-neutral float-left" title="quapy package" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||||
<a href="quapy.data.html" class="btn btn-neutral float-right" title="quapy.data package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||||
</div>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="quapy.html"
|
||||
title="previous chapter">quapy package</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="quapy.data.html"
|
||||
title="next chapter">quapy.data package</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/quapy.classification.rst.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.data.html" title="quapy.data package"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.html" title="quapy package"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-1"><a href="modules.html" >quapy</a> »</li>
|
||||
<li class="nav-item nav-item-2"><a href="quapy.html" >quapy package</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">quapy.classification package</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,69 +1,109 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>quapy.data package — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
|
||||
|
||||
<title>quapy.data package — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="quapy.method package" href="quapy.method.html" />
|
||||
<link rel="prev" title="quapy.classification package" href="quapy.classification.html" />
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.method.html" title="quapy.method package"
|
||||
accesskey="N">next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.classification.html" title="quapy.classification package"
|
||||
accesskey="P">previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-1"><a href="modules.html" >quapy</a> »</li>
|
||||
<li class="nav-item nav-item-2"><a href="quapy.html" accesskey="U">quapy package</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">quapy.data package</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<link rel="prev" title="quapy.classification package" href="quapy.classification.html" />
|
||||
</head>
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
<a href="index.html" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="modules.html">quapy</a><ul class="current">
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="quapy.html">quapy package</a><ul class="current">
|
||||
<li class="toctree-l3 current"><a class="reference internal" href="quapy.html#subpackages">Subpackages</a><ul class="current">
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.classification.html">quapy.classification package</a></li>
|
||||
<li class="toctree-l4 current"><a class="current reference internal" href="#">quapy.data package</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="quapy.method.html">quapy.method package</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.error">quapy.error module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.evaluation">quapy.evaluation module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.functional">quapy.functional module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.model_selection">quapy.model_selection module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.plot">quapy.plot module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.protocol">quapy.protocol module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy.util">quapy.util module</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quapy.html#module-quapy">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="index.html">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item"><a href="modules.html">quapy</a></li>
|
||||
<li class="breadcrumb-item"><a href="quapy.html">quapy package</a></li>
|
||||
<li class="breadcrumb-item active">quapy.data package</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
<a href="_sources/quapy.data.rst.txt" rel="nofollow"> View page source</a>
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<section id="quapy-data-package">
|
||||
<h1>quapy.data package<a class="headerlink" href="#quapy-data-package" title="Permalink to this heading">¶</a></h1>
|
||||
<h1>quapy.data package<a class="headerlink" href="#quapy-data-package" title="Link to this heading"></a></h1>
|
||||
<section id="submodules">
|
||||
<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading">¶</a></h2>
|
||||
<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading"></a></h2>
|
||||
</section>
|
||||
<section id="module-quapy.data.base">
|
||||
<span id="quapy-data-base"></span><h2>quapy.data.base<a class="headerlink" href="#module-quapy.data.base" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-data-base-module"></span><h2>quapy.data.base module<a class="headerlink" href="#module-quapy.data.base" title="Link to this heading"></a></h2>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">Dataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">test</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">vocabulary</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">dict</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">Dataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">test</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">vocabulary</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">dict</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">None</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#Dataset"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.Dataset" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>Abstraction of training and test <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> objects.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -78,7 +118,7 @@
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.SplitStratified">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">SplitStratified</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">collection</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">train_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.SplitStratified" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">SplitStratified</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">collection</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">train_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#Dataset.SplitStratified"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.Dataset.SplitStratified" title="Link to this definition"></a></dt>
|
||||
<dd><p>Generates a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> from a stratified split of a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> instance.
|
||||
See <a class="reference internal" href="#quapy.data.base.LabelledCollection.split_stratified" title="quapy.data.base.LabelledCollection.split_stratified"><code class="xref py py-meth docutils literal notranslate"><span class="pre">LabelledCollection.split_stratified()</span></code></a></p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -96,7 +136,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.spli
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.binary">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">binary</span></span><a class="headerlink" href="#quapy.data.base.Dataset.binary" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">binary</span></span><a class="headerlink" href="#quapy.data.base.Dataset.binary" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns True if the training collection is labelled according to two classes</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -107,7 +147,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.spli
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.classes_">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">classes_</span></span><a class="headerlink" href="#quapy.data.base.Dataset.classes_" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">classes_</span></span><a class="headerlink" href="#quapy.data.base.Dataset.classes_" title="Link to this definition"></a></dt>
|
||||
<dd><p>The classes according to which the training collection is labelled</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -118,7 +158,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.spli
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.kFCV">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">kFCV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">nfolds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nrepeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.kFCV" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">kFCV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">nfolds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nrepeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#Dataset.kFCV"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.Dataset.kFCV" title="Link to this definition"></a></dt>
|
||||
<dd><p>Generator of stratified folds to be used in k-fold cross validation. This function is only a wrapper around
|
||||
<a class="reference internal" href="#quapy.data.base.LabelledCollection.kFCV" title="quapy.data.base.LabelledCollection.kFCV"><code class="xref py py-meth docutils literal notranslate"><span class="pre">LabelledCollection.kFCV()</span></code></a> that returns <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> instances made of training and test folds.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -137,7 +177,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.spli
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.load">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">loader_kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.load" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">loader_kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#Dataset.load"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.Dataset.load" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a training and a test labelled set of data and convert it into a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> instance.
|
||||
The function in charge of reading the instances must be specified. This function can be a custom one, or any of
|
||||
the reading functions defined in <a class="reference internal" href="#module-quapy.data.reader" title="quapy.data.reader"><code class="xref py py-mod docutils literal notranslate"><span class="pre">quapy.data.reader</span></code></a> module.</p>
|
||||
|
|
@ -161,7 +201,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.load
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.n_classes">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">n_classes</span></span><a class="headerlink" href="#quapy.data.base.Dataset.n_classes" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">n_classes</span></span><a class="headerlink" href="#quapy.data.base.Dataset.n_classes" title="Link to this definition"></a></dt>
|
||||
<dd><p>The number of classes according to which the training collection is labelled</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -172,7 +212,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.load
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.reduce">
|
||||
<span class="sig-name descname"><span class="pre">reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_train</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_test</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.reduce" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_train</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_test</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#Dataset.reduce"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.Dataset.reduce" title="Link to this definition"></a></dt>
|
||||
<dd><p>Reduce the number of instances in place for quick experiments. Preserves the prevalence of each set.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -189,7 +229,7 @@ See <a class="reference internal" href="#quapy.data.base.LabelledCollection.load
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.stats">
|
||||
<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">show</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.stats" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">show</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#Dataset.stats"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.Dataset.stats" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns (and eventually prints) a dictionary with some stats of this dataset. E.g.,:</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'kindle'</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="n">data</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span>
|
||||
|
|
@ -212,7 +252,7 @@ the collection), <cite>prevs</cite> (the prevalence values for each class)</p>
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.train_test">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">train_test</span></span><a class="headerlink" href="#quapy.data.base.Dataset.train_test" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">train_test</span></span><a class="headerlink" href="#quapy.data.base.Dataset.train_test" title="Link to this definition"></a></dt>
|
||||
<dd><p>Alias to <cite>self.training</cite> and <cite>self.test</cite></p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -226,7 +266,7 @@ the collection), <cite>prevs</cite> (the prevalence values for each class)</p>
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.Dataset.vocabulary_size">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.data.base.Dataset.vocabulary_size" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.data.base.Dataset.vocabulary_size" title="Link to this definition"></a></dt>
|
||||
<dd><p>If the dataset is textual, and the vocabulary was indicated, returns the size of the vocabulary</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -239,7 +279,7 @@ the collection), <cite>prevs</cite> (the prevalence values for each class)</p>
|
|||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">LabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">LabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>A LabelledCollection is a set of objects each with a label attached to each of them.
|
||||
This class implements several sampling routines and other utilities.</p>
|
||||
|
|
@ -256,7 +296,7 @@ from the labels. The classes must be indicated in cases in which some of the lab
|
|||
</dl>
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.X">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">X</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.X" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">X</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.X" title="Link to this definition"></a></dt>
|
||||
<dd><p>An alias to self.instances</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -267,7 +307,7 @@ from the labels. The classes must be indicated in cases in which some of the lab
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.Xp">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">Xp</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.Xp" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">Xp</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.Xp" title="Link to this definition"></a></dt>
|
||||
<dd><p>Gets the instances and the true prevalence. This is useful when implementing evaluation protocols from
|
||||
a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> object.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -279,7 +319,7 @@ a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.Xy">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">Xy</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.Xy" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">Xy</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.Xy" title="Link to this definition"></a></dt>
|
||||
<dd><p>Gets the instances and labels. This is useful when working with <cite>sklearn</cite> estimators, e.g.:</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">svm</span> <span class="o">=</span> <span class="n">LinearSVC</span><span class="p">()</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="o">*</span><span class="n">my_collection</span><span class="o">.</span><span class="n">Xy</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
|
|
@ -293,7 +333,7 @@ a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.binary">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">binary</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.binary" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">binary</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.binary" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns True if the number of classes is 2</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -304,7 +344,7 @@ a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.counts">
|
||||
<span class="sig-name descname"><span class="pre">counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.counts" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.counts"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.counts" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns the number of instances for each of the classes in the codeframe.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -316,7 +356,7 @@ as listed by <cite>self.classes_</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.join">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Iterable</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.join" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Iterable</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.join"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.join" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns a new <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> as the union of the collections given in input.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -330,7 +370,7 @@ as listed by <cite>self.classes_</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.kFCV">
|
||||
<span class="sig-name descname"><span class="pre">kFCV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nfolds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nrepeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.kFCV" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">kFCV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nfolds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nrepeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.kFCV"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.kFCV" title="Link to this definition"></a></dt>
|
||||
<dd><p>Generator of stratified folds to be used in k-fold cross validation.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -348,7 +388,7 @@ as listed by <cite>self.classes_</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.load">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">loader_kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.load" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">loader_kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.load"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.load" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a labelled set of data and convert it into a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> instance. The function in charge
|
||||
of reading the instances must be specified. This function can be a custom one, or any of the reading functions
|
||||
defined in <a class="reference internal" href="#module-quapy.data.reader" title="quapy.data.reader"><code class="xref py py-mod docutils literal notranslate"><span class="pre">quapy.data.reader</span></code></a> module.</p>
|
||||
|
|
@ -371,7 +411,7 @@ these arguments are used to call <cite>loader_func(path, **loader_kwargs)</cite>
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.n_classes">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">n_classes</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.n_classes" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">n_classes</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.n_classes" title="Link to this definition"></a></dt>
|
||||
<dd><p>The number of classes</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -382,7 +422,7 @@ these arguments are used to call <cite>loader_func(path, **loader_kwargs)</cite>
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.p">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">p</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.p" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">p</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.p" title="Link to this definition"></a></dt>
|
||||
<dd><p>An alias to self.prevalence()</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -393,7 +433,7 @@ these arguments are used to call <cite>loader_func(path, **loader_kwargs)</cite>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.prevalence">
|
||||
<span class="sig-name descname"><span class="pre">prevalence</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.prevalence" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">prevalence</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.prevalence"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.prevalence" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns the prevalence, or relative frequency, of the classes in the codeframe.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -405,7 +445,7 @@ as listed by <cite>self.classes_</cite></p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling">
|
||||
<span class="sig-name descname"><span class="pre">sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.sampling"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling" title="Link to this definition"></a></dt>
|
||||
<dd><p>Return a random sample (an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a>) of desired size and desired prevalence
|
||||
values. For each class, the sampling is drawn without replacement if the requested prevalence is larger than
|
||||
the actual prevalence of the class, or with replacement otherwise.</p>
|
||||
|
|
@ -429,7 +469,7 @@ prevalence == <cite>prevs</cite> if the exact prevalence values can be met as pr
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling_from_index">
|
||||
<span class="sig-name descname"><span class="pre">sampling_from_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling_from_index" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">sampling_from_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.sampling_from_index"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling_from_index" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> whose elements are sampled from this collection using the
|
||||
index.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -444,7 +484,7 @@ index.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling_index">
|
||||
<span class="sig-name descname"><span class="pre">sampling_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling_index" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">sampling_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.sampling_index"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling_index" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns an index to be used to extract a random sample of desired size and desired prevalence values. If the
|
||||
prevalence values are not specified, then returns the index of a uniform sampling.
|
||||
For each class, the sampling is drawn with replacement if the requested prevalence is larger than
|
||||
|
|
@ -468,7 +508,7 @@ it is constrained. E.g., for binary collections, only the prevalence <cite>p</ci
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.split_random">
|
||||
<span class="sig-name descname"><span class="pre">split_random</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_prop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.split_random" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">split_random</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_prop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.split_random"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.split_random" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns two instances of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> split randomly from this collection, at desired
|
||||
proportion.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -489,7 +529,7 @@ second one with <cite>1-train_prop</cite> elements</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.split_stratified">
|
||||
<span class="sig-name descname"><span class="pre">split_stratified</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_prop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.split_stratified" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">split_stratified</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_prop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.split_stratified"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.split_stratified" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns two instances of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> split with stratification from this collection, at desired
|
||||
proportion.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -510,7 +550,7 @@ second one with <cite>1-train_prop</cite> elements</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.stats">
|
||||
<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">show</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.stats" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">show</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.stats"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.stats" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns (and eventually prints) a dictionary with some stats of this collection. E.g.,:</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">'kindle'</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="n">data</span><span class="o">.</span><span class="n">training</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span>
|
||||
|
|
@ -532,7 +572,7 @@ values for each class)</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.uniform_sampling">
|
||||
<span class="sig-name descname"><span class="pre">uniform_sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.uniform_sampling" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">uniform_sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.uniform_sampling"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.uniform_sampling" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns a uniform sample (an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a>) of desired size. The sampling is drawn
|
||||
with replacement if the requested size is greater than the number of instances, or without replacement
|
||||
otherwise.</p>
|
||||
|
|
@ -551,7 +591,7 @@ otherwise.</p>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.uniform_sampling_index">
|
||||
<span class="sig-name descname"><span class="pre">uniform_sampling_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.uniform_sampling_index" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">uniform_sampling_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/base.html#LabelledCollection.uniform_sampling_index"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.base.LabelledCollection.uniform_sampling_index" title="Link to this definition"></a></dt>
|
||||
<dd><p>Returns an index to be used to extract a uniform sample of desired size. The sampling is drawn
|
||||
with replacement if the requested size is greater than the number of instances, or without replacement
|
||||
otherwise.</p>
|
||||
|
|
@ -570,7 +610,7 @@ otherwise.</p>
|
|||
|
||||
<dl class="py property">
|
||||
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.y">
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">y</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.y" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">property</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">y</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.y" title="Link to this definition"></a></dt>
|
||||
<dd><p>An alias to self.labels</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -583,10 +623,42 @@ otherwise.</p>
|
|||
|
||||
</section>
|
||||
<section id="module-quapy.data.datasets">
|
||||
<span id="quapy-data-datasets"></span><h2>quapy.data.datasets<a class="headerlink" href="#module-quapy.data.datasets" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-data-datasets-module"></span><h2>quapy.data.datasets module<a class="headerlink" href="#module-quapy.data.datasets" title="Link to this heading"></a></h2>
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCIDataset">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCIDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_UCIDataset" title="Permalink to this definition">¶</a></dt>
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_IFCB">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_IFCB</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">single_sample_train</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_model_selection</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_IFCB"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_IFCB" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads the IFCB dataset for quantification from <a class="reference external" href="https://zenodo.org/records/10036244">Zenodo</a> (for more
|
||||
information on this dataset, please follow the zenodo link).
|
||||
This dataset is based on the data available publicly at
|
||||
<a class="reference external" href="https://github.com/hsosik/WHOI-Plankton">WHOI-Plankton repo</a>.
|
||||
The scripts for the processing are available at <a class="reference external" href="https://github.com/pglez82/IFCB_Zenodo">P. González’s repo</a>.
|
||||
Basically, this is the IFCB dataset with precomputed features for testing quantification algorithms.</p>
|
||||
<p>The datasets are downloaded only once, and stored for fast reuse.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>single_sample_train</strong> – a boolean. If true, it will return the train dataset as a
|
||||
<a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a> (all examples together).
|
||||
If false, a generator of training samples will be returned. Each example in the training set has an individual label.</p></li>
|
||||
<li><p><strong>for_model_selection</strong> – if True, then returns a split 30% of the training set (86 out of 286 samples) to be used for model selection;
|
||||
if False, then returns the full training set as training set and the test set as the test set</p></li>
|
||||
<li><p><strong>data_home</strong> – specify the quapy home directory where collections will be dumped (leave empty to use the default
|
||||
~/quay_data/ directory)</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>a tuple <cite>(train, test_gen)</cite> where <cite>train</cite> is an instance of
|
||||
<a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a>, if <cite>single_sample_train</cite> is true or
|
||||
<code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data._ifcb.IFCBTrainSamplesFromDir</span></code>, i.e. a sampling protocol that returns a series of samples
|
||||
labelled example by example. test_gen will be a <code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data._ifcb.IFCBTestSamples</span></code>,
|
||||
i.e., a sampling protocol that returns a series of samples labelled by prevalence.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCIBinaryDataset">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCIBinaryDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_UCIBinaryDataset"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_UCIBinaryDataset" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a UCI dataset as an instance of <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a>, as used in
|
||||
<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253516300628">Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
|
||||
|
|
@ -595,7 +667,7 @@ and
|
|||
<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego, P., Castano, A., Quevedo, J. R., & del Coz, J. J. (2019).
|
||||
Dynamic ensemble selection for quantification tasks.
|
||||
Information Fusion, 45, 1-15.</a>.
|
||||
The datasets do not come with a predefined train-test split (see <a class="reference internal" href="#quapy.data.datasets.fetch_UCILabelledCollection" title="quapy.data.datasets.fetch_UCILabelledCollection"><code class="xref py py-meth docutils literal notranslate"><span class="pre">fetch_UCILabelledCollection()</span></code></a> for further
|
||||
The datasets do not come with a predefined train-test split (see <code class="xref py py-meth docutils literal notranslate"><span class="pre">fetch_UCILabelledCollection()</span></code> for further
|
||||
information on how to use these collections), and so a train-test split is generated at desired proportion.
|
||||
The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI_DATASETS</cite></p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -615,8 +687,8 @@ The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI
|
|||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCILabelledCollection">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCILabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_UCILabelledCollection" title="Permalink to this definition">¶</a></dt>
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCIBinaryLabelledCollection">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCIBinaryLabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_UCIBinaryLabelledCollection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_UCIBinaryLabelledCollection" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a UCI collection as an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a>, as used in
|
||||
<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253516300628">Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
|
||||
|
|
@ -629,8 +701,8 @@ The datasets do not come with a predefined train-test split, and so Pérez-Gáll
|
|||
protocol, meaning that each collection was used to generate two rounds (hence the x2) of 5 fold cross validation.
|
||||
This can be reproduced by using <a class="reference internal" href="#quapy.data.base.Dataset.kFCV" title="quapy.data.base.Dataset.kFCV"><code class="xref py py-meth docutils literal notranslate"><span class="pre">quapy.data.base.Dataset.kFCV()</span></code></a>, e.g.:</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="gp">>>> </span><span class="n">collection</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCILabelledCollection</span><span class="p">(</span><span class="s2">"yeast"</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">Dataset</span><span class="o">.</span><span class="n">kFCV</span><span class="p">(</span><span class="n">collection</span><span class="p">,</span> <span class="n">nfolds</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">nrepeats</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
|
||||
<span class="gp">>>> </span><span class="n">collection</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCIBinaryLabelledCollection</span><span class="p">(</span><span class="s2">"yeast"</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">qp</span><span class="o">.</span><span class="n">train</span><span class="o">.</span><span class="n">Dataset</span><span class="o">.</span><span class="n">kFCV</span><span class="p">(</span><span class="n">collection</span><span class="p">,</span> <span class="n">nfolds</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">nrepeats</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
|
||||
<span class="gp">>>> </span> <span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
|
|
@ -646,14 +718,80 @@ This can be reproduced by using <a class="reference internal" href="#quapy.data.
|
|||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a> instance</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCIMulticlassDataset">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCIMulticlassDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_UCIMulticlassDataset"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_UCIMulticlassDataset" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a UCI multiclass dataset as an instance of <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a>.</p>
|
||||
<p>The list of available datasets is taken from <a class="reference external" href="https://archive.ics.uci.edu/">https://archive.ics.uci.edu/</a>, following these criteria:
|
||||
- It has more than 1000 instances
|
||||
- It is suited for classification
|
||||
- It has more than two classes
|
||||
- It is available for Python import (requires ucimlrepo package)</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="gp">>>> </span><span class="n">dataset</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCIMulticlassDataset</span><span class="p">(</span><span class="s2">"dry-bean"</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="n">train</span><span class="p">,</span> <span class="n">test</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">train_test</span>
|
||||
<span class="gp">>>> </span> <span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI_MULTICLASS_DATASETS</cite></p>
|
||||
<p>The datasets are downloaded only once and pickled into disk, saving time for consecutive calls.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>dataset_name</strong> – a dataset name</p></li>
|
||||
<li><p><strong>data_home</strong> – specify the quapy home directory where collections will be dumped (leave empty to use the default
|
||||
~/quay_data/ directory)</p></li>
|
||||
<li><p><strong>test_split</strong> – proportion of documents to be included in the test set. The rest conforms the training set</p></li>
|
||||
<li><p><strong>verbose</strong> – set to True (default is False) to get information (stats) about the dataset</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCIMulticlassLabelledCollection">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCIMulticlassLabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">LabelledCollection</span></a></span></span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_UCIMulticlassLabelledCollection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_UCIMulticlassLabelledCollection" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a UCI multiclass collection as an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a>.</p>
|
||||
<p>The list of available datasets is taken from <a class="reference external" href="https://archive.ics.uci.edu/">https://archive.ics.uci.edu/</a>, following these criteria:
|
||||
- It has more than 1000 instances
|
||||
- It is suited for classification
|
||||
- It has more than two classes
|
||||
- It is available for Python import (requires ucimlrepo package)</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
|
||||
<span class="gp">>>> </span><span class="n">collection</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCIMulticlassLabelledCollection</span><span class="p">(</span><span class="s2">"dry-bean"</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="n">X</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">collection</span><span class="o">.</span><span class="n">Xy</span>
|
||||
<span class="gp">>>> </span> <span class="o">...</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI_MULTICLASS_DATASETS</cite></p>
|
||||
<p>The datasets are downloaded only once and pickled into disk, saving time for consecutive calls.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>dataset_name</strong> – a dataset name</p></li>
|
||||
<li><p><strong>data_home</strong> – specify the quapy home directory where the dataset will be dumped (leave empty to use the default
|
||||
~/quay_data/ directory)</p></li>
|
||||
<li><p><strong>test_split</strong> – proportion of documents to be included in the test set. The rest conforms the training set</p></li>
|
||||
<li><p><strong>verbose</strong> – set to True (default is False) to get information (stats) about the dataset</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a> instance</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_lequa2022">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_lequa2022</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.datasets.fetch_lequa2022" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_lequa2022</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_lequa2022"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_lequa2022" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads the official datasets provided for the <a class="reference external" href="https://lequa2022.github.io/index">LeQua</a> competition.
|
||||
In brief, there are 4 tasks (T1A, T1B, T2A, T2B) having to do with text quantification
|
||||
problems. Tasks T1A and T1B provide documents in vector form, while T2A and T2B provide raw documents instead.
|
||||
|
|
@ -676,15 +814,15 @@ datasets.</p>
|
|||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>a tuple <cite>(train, val_gen, test_gen)</cite> where <cite>train</cite> is an instance of
|
||||
<a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a>, <cite>val_gen</cite> and <cite>test_gen</cite> are instances of
|
||||
<code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.protocol.SamplesFromDir</span></code>, i.e., are sampling protocols that return a series of samples
|
||||
labelled by prevalence.</p>
|
||||
<code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data._lequa2022.SamplesFromDir</span></code>, a subclass of <a class="reference internal" href="quapy.html#quapy.protocol.AbstractProtocol" title="quapy.protocol.AbstractProtocol"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.protocol.AbstractProtocol</span></code></a>,
|
||||
that return a series of samples stored in a directory which are labelled by prevalence.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_reviews">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_reviews</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tfidf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_reviews" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_reviews</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tfidf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_reviews"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_reviews" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a Reviews dataset as a Dataset instance, as used in
|
||||
<a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/3269206.3269287">Esuli, A., Moreo, A., and Sebastiani, F. “A recurrent neural network for sentiment quantification.”
|
||||
Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018.</a>.
|
||||
|
|
@ -710,7 +848,7 @@ faster subsequent invokations</p></li>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_twitter">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_twitter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_model_selection</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_twitter" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_twitter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_model_selection</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></span><a class="reference internal" href="_modules/quapy/data/datasets.html#fetch_twitter"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.fetch_twitter" title="Link to this definition"></a></dt>
|
||||
<dd><p>Loads a Twitter dataset as a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance, as used in:
|
||||
<a class="reference external" href="https://link.springer.com/content/pdf/10.1007/s13278-016-0327-z.pdf">Gao, W., Sebastiani, F.: From classification to quantification in tweet sentiment analysis.
|
||||
Social Network Analysis and Mining6(19), 1–22 (2016)</a>
|
||||
|
|
@ -741,15 +879,15 @@ faster subsequent invokations</p></li>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.datasets.warn">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">warn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.datasets.warn" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">warn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/datasets.html#warn"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.datasets.warn" title="Link to this definition"></a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</section>
|
||||
<section id="module-quapy.data.preprocessing">
|
||||
<span id="quapy-data-preprocessing"></span><h2>quapy.data.preprocessing<a class="headerlink" href="#module-quapy.data.preprocessing" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-data-preprocessing-module"></span><h2>quapy.data.preprocessing module<a class="headerlink" href="#module-quapy.data.preprocessing" title="Link to this heading"></a></h2>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer">
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">IndexTransformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">IndexTransformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#IndexTransformer"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer" title="Link to this definition"></a></dt>
|
||||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>This class implements a sklearn’s-style transformer that indexes text as numerical ids for the tokens it
|
||||
contains, and that would be generated by sklearn’s
|
||||
|
|
@ -763,7 +901,7 @@ contains, and that would be generated by sklearn’s
|
|||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.add_word">
|
||||
<span class="sig-name descname"><span class="pre">add_word</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">word</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nogaps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.add_word" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">add_word</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">word</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nogaps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#IndexTransformer.add_word"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.add_word" title="Link to this definition"></a></dt>
|
||||
<dd><p>Adds a new token (regardless of whether it has been found in the text or not), with dedicated id.
|
||||
Useful to define special tokens for codifying unknown words, or padding tokens.</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -784,7 +922,7 @@ precedent ids stored so far</p></li>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.fit">
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.fit" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#IndexTransformer.fit"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.fit" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fits the transformer, i.e., decides on the vocabulary, given a list of strings.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -798,7 +936,7 @@ precedent ids stored so far</p></li>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.fit_transform">
|
||||
<span class="sig-name descname"><span class="pre">fit_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.fit_transform" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">fit_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#IndexTransformer.fit_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.fit_transform" title="Link to this definition"></a></dt>
|
||||
<dd><p>Fits the transform on <cite>X</cite> and transforms it.</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -815,7 +953,7 @@ precedent ids stored so far</p></li>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.transform">
|
||||
<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.transform" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#IndexTransformer.transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.transform" title="Link to this definition"></a></dt>
|
||||
<dd><p>Transforms the strings in <cite>X</cite> as lists of numerical ids</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||||
|
|
@ -832,7 +970,7 @@ precedent ids stored so far</p></li>
|
|||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.vocabulary_size">
|
||||
<span class="sig-name descname"><span class="pre">vocabulary_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.vocabulary_size" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">vocabulary_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#IndexTransformer.vocabulary_size"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.vocabulary_size" title="Link to this definition"></a></dt>
|
||||
<dd><p>Gets the length of the vocabulary according to which the document tokens have been indexed</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||||
|
|
@ -845,7 +983,7 @@ precedent ids stored so far</p></li>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.index">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.index" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#index"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.index" title="Link to this definition"></a></dt>
|
||||
<dd><p>Indexes the tokens of a textual <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> of string documents.
|
||||
To index a document means to replace each different token by a unique numerical index.
|
||||
Rare words (i.e., words occurring less than <cite>min_df</cite> times) are replaced by a special token <cite>UNK</cite></p>
|
||||
|
|
@ -869,7 +1007,7 @@ are lists of str</p></li>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.reduce_columns">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">reduce_columns</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.reduce_columns" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">reduce_columns</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#reduce_columns"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.reduce_columns" title="Link to this definition"></a></dt>
|
||||
<dd><p>Reduces the dimensionality of the instances, represented as a <cite>csr_matrix</cite> (or any subtype of
|
||||
<cite>scipy.sparse.spmatrix</cite>), of training and test documents by removing the columns of words which are not present
|
||||
in at least <cite>min_df</cite> instances in the training set</p>
|
||||
|
|
@ -892,7 +1030,7 @@ in the training set have been removed</p>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.standardize">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">standardize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.standardize" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">standardize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#standardize"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.standardize" title="Link to this definition"></a></dt>
|
||||
<dd><p>Standardizes the real-valued columns of a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a>.
|
||||
Standardization, aka z-scoring, of a variable <cite>X</cite> comes down to subtracting the average and normalizing by the
|
||||
standard deviation.</p>
|
||||
|
|
@ -912,7 +1050,7 @@ standard deviation.</p>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.preprocessing.text2tfidf">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">text2tfidf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sublinear_tf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.text2tfidf" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">text2tfidf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sublinear_tf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/preprocessing.html#text2tfidf"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.preprocessing.text2tfidf" title="Link to this definition"></a></dt>
|
||||
<dd><p>Transforms a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> of textual instances into a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> of
|
||||
tfidf weighted sparse vectors</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -936,10 +1074,10 @@ current Dataset (if inplace=True) where the instances are stored in a <cite>csr_
|
|||
|
||||
</section>
|
||||
<section id="module-quapy.data.reader">
|
||||
<span id="quapy-data-reader"></span><h2>quapy.data.reader<a class="headerlink" href="#module-quapy.data.reader" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="quapy-data-reader-module"></span><h2>quapy.data.reader module<a class="headerlink" href="#module-quapy.data.reader" title="Link to this heading"></a></h2>
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.reader.binarize">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">binarize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_class</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.binarize" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">binarize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_class</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/reader.html#binarize"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.reader.binarize" title="Link to this definition"></a></dt>
|
||||
<dd><p>Binarizes a categorical array-like collection of labels towards the positive class <cite>pos_class</cite>. E.g.,:</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">binarize</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">pos_class</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
|
||||
<span class="gp">>>> </span><span class="n">array</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span>
|
||||
|
|
@ -961,7 +1099,7 @@ current Dataset (if inplace=True) where the instances are stored in a <cite>csr_
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.reader.from_csv">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">from_csv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'utf-8'</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.from_csv" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">from_csv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'utf-8'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/reader.html#from_csv"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.reader.from_csv" title="Link to this definition"></a></dt>
|
||||
<dd><p>Reads a csv file in which columns are separated by ‘,’.
|
||||
File format <label>,<feat1>,<feat2>,…,<featn></p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -979,7 +1117,7 @@ File format <label>,<feat1>,<feat2>,…,<featn></p>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.reader.from_sparse">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">from_sparse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.from_sparse" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">from_sparse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/reader.html#from_sparse"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.reader.from_sparse" title="Link to this definition"></a></dt>
|
||||
<dd><p>Reads a labelled collection of real-valued instances expressed in sparse format
|
||||
File format <-1 or 0 or 1>[s col(int):val(float)]</p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -994,7 +1132,7 @@ File format <-1 or 0 or 1>[s col(int):val(float)]</p>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.reader.from_text">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">from_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'utf-8'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class2int</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.from_text" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">from_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'utf-8'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class2int</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/reader.html#from_text"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.reader.from_text" title="Link to this definition"></a></dt>
|
||||
<dd><p>Reads a labelled colletion of documents.
|
||||
File fomart <0 or 1> <document></p>
|
||||
<dl class="field-list simple">
|
||||
|
|
@ -1013,7 +1151,7 @@ File fomart <0 or 1> <document></p>
|
|||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quapy.data.reader.reindex_labels">
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">reindex_labels</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.reindex_labels" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">reindex_labels</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quapy/data/reader.html#reindex_labels"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#quapy.data.reader.reindex_labels" title="Link to this definition"></a></dt>
|
||||
<dd><p>Re-indexes a list of labels as a list of indexes, and returns the classnames corresponding to the indexes.
|
||||
E.g.:</p>
|
||||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">reindex_labels</span><span class="p">([</span><span class="s1">'B'</span><span class="p">,</span> <span class="s1">'B'</span><span class="p">,</span> <span class="s1">'A'</span><span class="p">,</span> <span class="s1">'C'</span><span class="p">])</span>
|
||||
|
|
@ -1032,87 +1170,39 @@ E.g.:</p>
|
|||
|
||||
</section>
|
||||
<section id="module-quapy.data">
|
||||
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-quapy.data" title="Permalink to this heading">¶</a></h2>
|
||||
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-quapy.data" title="Link to this heading"></a></h2>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<div>
|
||||
<h3><a href="index.html">Table of Contents</a></h3>
|
||||
<ul>
|
||||
<li><a class="reference internal" href="#">quapy.data package</a><ul>
|
||||
<li><a class="reference internal" href="#submodules">Submodules</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.data.base">quapy.data.base</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.data.datasets">quapy.data.datasets</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.data.preprocessing">quapy.data.preprocessing</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.data.reader">quapy.data.reader</a></li>
|
||||
<li><a class="reference internal" href="#module-quapy.data">Module contents</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||||
<a href="quapy.classification.html" class="btn btn-neutral float-left" title="quapy.classification package" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||||
<a href="quapy.method.html" class="btn btn-neutral float-right" title="quapy.method package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||||
</div>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Previous topic</h4>
|
||||
<p class="topless"><a href="quapy.classification.html"
|
||||
title="previous chapter">quapy.classification package</a></p>
|
||||
</div>
|
||||
<div>
|
||||
<h4>Next topic</h4>
|
||||
<p class="topless"><a href="quapy.method.html"
|
||||
title="next chapter">quapy.method package</a></p>
|
||||
</div>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>This Page</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="_sources/quapy.data.rst.txt"
|
||||
rel="nofollow">Show Source</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div id="searchbox" style="display: none" role="search">
|
||||
<h3 id="searchlabel">Quick search</h3>
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="Go" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.method.html" title="quapy.method package"
|
||||
>next</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="quapy.classification.html" title="quapy.classification package"
|
||||
>previous</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-1"><a href="modules.html" >quapy</a> »</li>
|
||||
<li class="nav-item nav-item-2"><a href="quapy.html" >quapy package</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">quapy.data package</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -1,111 +1,121 @@
|
|||
<!DOCTYPE html>
|
||||
<html class="writer-html5" lang="en" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Search — QuaPy: A Python-based open-source framework for quantification 0.1.8 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=92fd9be5" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||||
|
||||
|
||||
<!doctype html>
|
||||
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Search — QuaPy 0.1.7 documentation</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/bizstyle.css" />
|
||||
|
||||
|
||||
|
||||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||||
<script src="_static/jquery.js"></script>
|
||||
<script src="_static/underscore.js"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||||
<script src="_static/doctools.js"></script>
|
||||
<script src="_static/sphinx_highlight.js"></script>
|
||||
<script src="_static/bizstyle.js"></script>
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/js/html5shiv.min.js"></script>
|
||||
<![endif]-->
|
||||
|
||||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||||
<script src="_static/documentation_options.js?v=22607128"></script>
|
||||
<script src="_static/doctools.js?v=9a2dae69"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="_static/js/theme.js"></script>
|
||||
<script src="_static/searchtools.js"></script>
|
||||
<script src="_static/language_data.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="#" />
|
||||
<script src="searchindex.js" defer></script>
|
||||
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
|
||||
<!--[if lt IE 9]>
|
||||
<script src="_static/css3-mediaqueries.js"></script>
|
||||
<![endif]-->
|
||||
<link rel="search" title="Search" href="#" />
|
||||
</head>
|
||||
|
||||
</head><body>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
accesskey="I">index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Search</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<body class="wy-body-for-nav">
|
||||
<div class="wy-grid-for-nav">
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1 id="search-documentation">Search</h1>
|
||||
|
||||
|
||||
|
||||
<a href="index.html" class="icon icon-home">
|
||||
QuaPy: A Python-based open-source framework for quantification
|
||||
</a>
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="#" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">quapy</a></li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="index.html">QuaPy: A Python-based open-source framework for quantification</a>
|
||||
</nav>
|
||||
|
||||
<div class="wy-nav-content">
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="Page navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||||
<li class="breadcrumb-item active">Search</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<noscript>
|
||||
<div class="admonition warning">
|
||||
<p>
|
||||
Please activate JavaScript to enable the search
|
||||
functionality.
|
||||
</p>
|
||||
<div id="fallback" class="admonition warning">
|
||||
<p class="last">
|
||||
Please activate JavaScript to enable the search functionality.
|
||||
</p>
|
||||
</div>
|
||||
</noscript>
|
||||
|
||||
|
||||
<p>
|
||||
Searching for multiple words only shows matches that contain
|
||||
all words.
|
||||
</p>
|
||||
|
||||
|
||||
<form action="" method="get">
|
||||
<input type="text" name="q" aria-labelledby="search-documentation" value="" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="search" />
|
||||
<span id="search-progress" style="padding-left: 10px"></span>
|
||||
</form>
|
||||
|
||||
|
||||
|
||||
|
||||
<div id="search-results">
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>© Copyright 2024, Alejandro Moreo.</p>
|
||||
</div>
|
||||
|
||||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
|
||||
</footer>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>Navigation</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="genindex.html" title="General Index"
|
||||
>index</a></li>
|
||||
<li class="right" >
|
||||
<a href="py-modindex.html" title="Python Module Index"
|
||||
>modules</a> |</li>
|
||||
<li class="nav-item nav-item-0"><a href="index.html">QuaPy 0.1.7 documentation</a> »</li>
|
||||
<li class="nav-item nav-item-this"><a href="">Search</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer" role="contentinfo">
|
||||
© Copyright 2021, Alejandro Moreo.
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
||||
</div>
|
||||
</body>
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
<script>
|
||||
jQuery(function() { Search.loadIndex("searchindex.js"); });
|
||||
</script>
|
||||
|
||||
<script id="searchindexloader"></script>
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
<meta http-equiv="refresh" content="0; url=./build/html/index.html" />
|
||||
|
|
@ -0,0 +1,74 @@
|
|||
from sklearn.linear_model import LogisticRegression
|
||||
from time import time
|
||||
import pandas as pd
|
||||
from tqdm import tqdm
|
||||
|
||||
import quapy as qp
|
||||
from quapy.protocol import APP
|
||||
from quapy.method.aggregative import HDy
|
||||
from quapy.method.non_aggregative import DMx
|
||||
|
||||
|
||||
"""
|
||||
This example is meant to experimentally compare HDy and HDx.
|
||||
The implementations of these methods adhere to the original design of the methods; in particular, this means that
|
||||
the number of bins is not an hyperparameter, but is something that the method explores internally (returning the
|
||||
median of the estimates as the final prevalence prediction), and the prevalence is not searched through any
|
||||
numerical optimization procedure, but simply as a linear search between 0 and 1 steppy by 0.01.
|
||||
See <https://www.sciencedirect.com/science/article/pii/S0020025512004069>`_ for further details
|
||||
"""
|
||||
|
||||
qp.environ['SAMPLE_SIZE']=100
|
||||
|
||||
|
||||
df = pd.DataFrame(columns=['method', 'dataset', 'MAE', 'MRAE', 'tr-time', 'te-time'])
|
||||
|
||||
|
||||
for dataset_name in tqdm(qp.datasets.UCI_BINARY_DATASETS, total=len(qp.datasets.UCI_BINARY_DATASETS)):
|
||||
if dataset_name in ['acute.a', 'acute.b', 'balance.2', 'iris.1']: continue
|
||||
|
||||
collection = qp.datasets.fetch_UCIBinaryLabelledCollection(dataset_name, verbose=False)
|
||||
train, test = collection.split_stratified()
|
||||
|
||||
# HDy............................................
|
||||
tinit = time()
|
||||
hdy = HDy(LogisticRegression()).fit(train)
|
||||
t_hdy_train = time()-tinit
|
||||
|
||||
tinit = time()
|
||||
hdy_report = qp.evaluation.evaluation_report(hdy, APP(test), error_metrics=['mae', 'mrae']).mean()
|
||||
t_hdy_test = time() - tinit
|
||||
df.loc[len(df)] = ['HDy', dataset_name, hdy_report['mae'], hdy_report['mrae'], t_hdy_train, t_hdy_test]
|
||||
|
||||
# HDx............................................
|
||||
tinit = time()
|
||||
hdx = DMx.HDx(n_jobs=-1).fit(train)
|
||||
t_hdx_train = time() - tinit
|
||||
|
||||
tinit = time()
|
||||
hdx_report = qp.evaluation.evaluation_report(hdx, APP(test), error_metrics=['mae', 'mrae']).mean()
|
||||
t_hdx_test = time() - tinit
|
||||
df.loc[len(df)] = ['HDx', dataset_name, hdx_report['mae'], hdx_report['mrae'], t_hdx_train, t_hdx_test]
|
||||
|
||||
# evaluation reports
|
||||
|
||||
print('\n'*3)
|
||||
print('='*80)
|
||||
print('Comparison in terms of performance')
|
||||
print('='*80)
|
||||
pv = df.pivot_table(index='dataset', columns='method', values=['MAE', 'MRAE'])
|
||||
print(pv)
|
||||
print('\nAveraged values:')
|
||||
print(pv.mean())
|
||||
|
||||
print('\n'*3)
|
||||
print('='*80)
|
||||
print('Comparison in terms of efficiency')
|
||||
print('='*80)
|
||||
pv = df.pivot_table(index='dataset', columns='method', values=['tr-time', 'te-time'])
|
||||
print(pv)
|
||||
print('\nAveraged values:')
|
||||
print(pv.mean())
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,93 @@
|
|||
import numpy as np
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
import quapy as qp
|
||||
from quapy.method.aggregative import PACC
|
||||
from quapy.data import LabelledCollection
|
||||
from quapy.protocol import AbstractStochasticSeededProtocol
|
||||
import quapy.functional as F
|
||||
|
||||
"""
|
||||
In this example, we create a custom protocol.
|
||||
The protocol generates samples of a Gaussian mixture model with random mixture parameter (the sample prevalence).
|
||||
Datapoints are univariate and we consider 2 classes only.
|
||||
"""
|
||||
class GaussianMixProtocol(AbstractStochasticSeededProtocol):
|
||||
# We need to extend AbstractStochasticSeededProtocol if we want the samples to be replicable
|
||||
|
||||
def __init__(self, mu_1:float, std_1:float, mu_2:float, std_2:float, num_samples, sample_size, random_state=0):
|
||||
super(GaussianMixProtocol, self).__init__(random_state) # this sets the random state
|
||||
self.mu_1 = mu_1
|
||||
self.std_1 = std_1
|
||||
self.mu_2 = mu_2
|
||||
self.std_2 = std_2
|
||||
self.num_samples = num_samples
|
||||
self.sample_size = sample_size
|
||||
|
||||
def samples_parameters(self):
|
||||
# This function is inherited and has to be overriden.
|
||||
# This function should return all the necessary parameters for producing the samples.
|
||||
# In this case, we consider returning a vector of seeds (one for each sample) and a vector of
|
||||
# randomly sampled prevalence values.
|
||||
# This function will be invoked within a context that sets the seed, so it will always return the
|
||||
# same parameters. In case you want different outcomes, then simply set random_state=None.
|
||||
rand_offset = np.random.randint(1000)
|
||||
sample_seeds = np.random.permutation(self.num_samples*2) + rand_offset
|
||||
random_prevs = np.random.rand(self.num_samples)
|
||||
params = np.hstack([sample_seeds.reshape(-1,2), random_prevs.reshape(-1,1)])
|
||||
# each row in params contains two seeds (for generating the negatives and the positives, respectively) and
|
||||
# the prevalence vector
|
||||
return params
|
||||
|
||||
def sample(self, params):
|
||||
# the params are two seeds and the positive prevalence of the sample
|
||||
seed0, seed1, pos_prev = params
|
||||
num_positives = int(pos_prev * self.sample_size)
|
||||
num_negatives = self.sample_size - num_positives
|
||||
with qp.util.temp_seed(int(seed0)):
|
||||
Xneg = np.random.normal(loc=self.mu_1, scale=self.std_1, size=num_negatives)
|
||||
with qp.util.temp_seed(int(seed1)):
|
||||
Xpos = np.random.normal(loc=self.mu_2, scale=self.std_2, size=num_positives)
|
||||
X = np.concatenate((Xneg,Xpos))
|
||||
np.random.shuffle(X)
|
||||
X = X.reshape(-1,1)
|
||||
prev = F.as_binary_prevalence(pos_prev)
|
||||
return X, prev
|
||||
|
||||
def total(self):
|
||||
# overriding this function will allow some methods display a meaningful progress bar
|
||||
return self.num_samples
|
||||
|
||||
|
||||
mu_1, std_1 = 0, 1
|
||||
mu_2, std_2 = 1, 1
|
||||
|
||||
gm = GaussianMixProtocol(mu_1=mu_1, std_1=std_1, mu_2=mu_2, std_2=std_2, num_samples=10, sample_size=50)
|
||||
|
||||
# let's see if the samples are replicated
|
||||
for i, (X, prev) in enumerate(gm()):
|
||||
if i>4: break
|
||||
print(f'sample-{i}: {F.strprev(prev)}, some covariates={X[:5].flatten()}...')
|
||||
|
||||
print()
|
||||
for i, (X, prev) in enumerate(gm()):
|
||||
if i > 4: break
|
||||
print(f'sample-{i}: {F.strprev(prev)}, some covariates={X[:5].flatten()}...')
|
||||
|
||||
# let's generate some training data
|
||||
# The samples are replicable, but by setting a temp seed we achieve repicable training as well
|
||||
with qp.util.temp_seed(0):
|
||||
Xneg = np.random.normal(loc=mu_1, scale=std_1, size=100)
|
||||
Xpos = np.random.normal(loc=mu_2, scale=std_2, size=100)
|
||||
X = np.concatenate([Xneg, Xpos]).reshape(-1,1)
|
||||
y = [0]*100 + [1]*100
|
||||
training = LabelledCollection(X, y)
|
||||
|
||||
pacc = PACC(LogisticRegression())
|
||||
pacc.fit(training)
|
||||
|
||||
|
||||
mae = qp.evaluation.evaluate(pacc, protocol=gm, error_metric='mae', verbose=True)
|
||||
print(f'PACC MAE={mae:.5f}')
|
||||
|
||||
|
||||
|
|
@ -2,7 +2,7 @@ import quapy as qp
|
|||
from quapy.data import LabelledCollection
|
||||
from quapy.method.base import BinaryQuantifier
|
||||
from quapy.model_selection import GridSearchQ
|
||||
from quapy.method.aggregative import AggregativeProbabilisticQuantifier
|
||||
from quapy.method.aggregative import AggregativeSoftQuantifier
|
||||
from quapy.protocol import APP
|
||||
import numpy as np
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
|
@ -15,7 +15,7 @@ from sklearn.linear_model import LogisticRegression
|
|||
# internal hyperparameter (let say, alpha) which is the decision threshold. Let's also assume the quantifier
|
||||
# is binary, for simplicity.
|
||||
|
||||
class MyQuantifier(AggregativeProbabilisticQuantifier, BinaryQuantifier):
|
||||
class MyQuantifier(AggregativeSoftQuantifier, BinaryQuantifier):
|
||||
def __init__(self, classifier, alpha=0.5):
|
||||
self.alpha = alpha
|
||||
# aggregative quantifiers have an internal self.classifier attribute
|
||||
|
|
|
|||
|
|
@ -0,0 +1,49 @@
|
|||
import numpy as np
|
||||
|
||||
import quapy as qp
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
from quapy.model_selection import GridSearchQ
|
||||
from quapy.evaluation import evaluation_report
|
||||
|
||||
|
||||
print('Quantifying the IFCB dataset with PACC\n')
|
||||
|
||||
# model selection
|
||||
print('loading dataset for model selection...', end='')
|
||||
train, val_gen = qp.datasets.fetch_IFCB(for_model_selection=True, single_sample_train=True)
|
||||
print('[done]')
|
||||
print(f'\ttraining size={len(train)}, features={train.X.shape[1]}, classes={train.n_classes}')
|
||||
print(f'\tvalidation samples={val_gen.total()}')
|
||||
|
||||
print('model selection starts')
|
||||
quantifier = qp.method.aggregative.PACC(LogisticRegression())
|
||||
|
||||
mod_sel = GridSearchQ(
|
||||
quantifier,
|
||||
param_grid={
|
||||
'classifier__C': np.logspace(-3,3,7),
|
||||
'classifier__class_weight': [None, 'balanced']
|
||||
},
|
||||
protocol=val_gen,
|
||||
refit=False,
|
||||
n_jobs=-1,
|
||||
verbose=True,
|
||||
raise_errors=True
|
||||
).fit(train)
|
||||
|
||||
print(f'model selection chose hyperparameters: {mod_sel.best_params_}')
|
||||
quantifier = mod_sel.best_model_
|
||||
|
||||
print('loading dataset for test...', end='')
|
||||
train, test_gen = qp.datasets.fetch_IFCB(for_model_selection=False, single_sample_train=True)
|
||||
print('[done]')
|
||||
print(f'\ttraining size={len(train)}, features={train.X.shape[1]}, classes={train.n_classes}')
|
||||
print(f'\ttest samples={test_gen.total()}')
|
||||
|
||||
print('training on the whole dataset before test')
|
||||
quantifier.fit(train)
|
||||
|
||||
print('testing...')
|
||||
report = evaluation_report(quantifier, protocol=test_gen, error_metrics=['mae'], verbose=True)
|
||||
print(report.mean())
|
||||
|
|
@ -1,57 +1,71 @@
|
|||
import quapy as qp
|
||||
from quapy.protocol import APP
|
||||
from quapy.method.aggregative import DistributionMatching
|
||||
from method._kdey import KDEyML
|
||||
from quapy.method.non_aggregative import DMx
|
||||
from quapy.protocol import APP, UPP
|
||||
from quapy.method.aggregative import DMy
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
from examples.comparing_gridsearch import OLD_GridSearchQ
|
||||
import numpy as np
|
||||
from time import time
|
||||
|
||||
"""
|
||||
In this example, we show how to perform model selection on a DistributionMatching quantifier.
|
||||
"""
|
||||
|
||||
model = DistributionMatching(LogisticRegression())
|
||||
model = KDEyML(LogisticRegression())
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 100
|
||||
qp.environ['N_JOBS'] = -1
|
||||
|
||||
training, test = qp.datasets.fetch_reviews('imdb', tfidf=True, min_df=5).train_test
|
||||
# training, test = qp.datasets.fetch_reviews('imdb', tfidf=True, min_df=5).train_test
|
||||
training, test = qp.datasets.fetch_UCIMulticlassDataset('letter').train_test
|
||||
|
||||
# The model will be returned by the fit method of GridSearchQ.
|
||||
# Every combination of hyper-parameters will be evaluated by confronting the
|
||||
# quantifier thus configured against a series of samples generated by means
|
||||
# of a sample generation protocol. For this example, we will use the
|
||||
# artificial-prevalence protocol (APP), that generates samples with prevalence
|
||||
# values in the entire range of values from a grid (e.g., [0, 0.1, 0.2, ..., 1]).
|
||||
# We devote 30% of the dataset for this exploration.
|
||||
training, validation = training.split_stratified(train_prop=0.7)
|
||||
protocol = APP(validation)
|
||||
with qp.util.temp_seed(0):
|
||||
|
||||
# We will explore a classification-dependent hyper-parameter (e.g., the 'C'
|
||||
# hyper-parameter of LogisticRegression) and a quantification-dependent hyper-parameter
|
||||
# (e.g., the number of bins in a DistributionMatching quantifier.
|
||||
# Classifier-dependent hyper-parameters have to be marked with a prefix "classifier__"
|
||||
# in order to let the quantifier know this hyper-parameter belongs to its underlying
|
||||
# classifier.
|
||||
param_grid = {
|
||||
'classifier__C': np.logspace(-3,3,7),
|
||||
'nbins': [8, 16, 32, 64],
|
||||
}
|
||||
# The model will be returned by the fit method of GridSearchQ.
|
||||
# Every combination of hyper-parameters will be evaluated by confronting the
|
||||
# quantifier thus configured against a series of samples generated by means
|
||||
# of a sample generation protocol. For this example, we will use the
|
||||
# artificial-prevalence protocol (APP), that generates samples with prevalence
|
||||
# values in the entire range of values from a grid (e.g., [0, 0.1, 0.2, ..., 1]).
|
||||
# We devote 30% of the dataset for this exploration.
|
||||
training, validation = training.split_stratified(train_prop=0.7)
|
||||
protocol = UPP(validation)
|
||||
|
||||
model = qp.model_selection.GridSearchQ(
|
||||
model=model,
|
||||
param_grid=param_grid,
|
||||
protocol=protocol,
|
||||
error='mae', # the error to optimize is the MAE (a quantification-oriented loss)
|
||||
refit=True, # retrain on the whole labelled set once done
|
||||
verbose=True # show information as the process goes on
|
||||
).fit(training)
|
||||
# We will explore a classification-dependent hyper-parameter (e.g., the 'C'
|
||||
# hyper-parameter of LogisticRegression) and a quantification-dependent hyper-parameter
|
||||
# (e.g., the number of bins in a DistributionMatching quantifier.
|
||||
# Classifier-dependent hyper-parameters have to be marked with a prefix "classifier__"
|
||||
# in order to let the quantifier know this hyper-parameter belongs to its underlying
|
||||
# classifier.
|
||||
param_grid = {
|
||||
'classifier__C': np.logspace(-3,3,7),
|
||||
'classifier__class_weight': ['balanced', None],
|
||||
'bandwidth': np.linspace(0.01, 0.2, 20),
|
||||
}
|
||||
|
||||
tinit = time()
|
||||
|
||||
# model = OLD_GridSearchQ(
|
||||
model = qp.model_selection.GridSearchQ(
|
||||
model=model,
|
||||
param_grid=param_grid,
|
||||
protocol=protocol,
|
||||
error='mae', # the error to optimize is the MAE (a quantification-oriented loss)
|
||||
refit=False, # retrain on the whole labelled set once done
|
||||
# raise_errors=False,
|
||||
verbose=True # show information as the process goes on
|
||||
).fit(training)
|
||||
|
||||
tend = time()
|
||||
|
||||
print(f'model selection ended: best hyper-parameters={model.best_params_}')
|
||||
model = model.best_model_
|
||||
|
||||
# evaluation in terms of MAE
|
||||
# we use the same evaluation protocol (APP) on the test set
|
||||
mae_score = qp.evaluation.evaluate(model, protocol=APP(test), error_metric='mae')
|
||||
mae_score = qp.evaluation.evaluate(model, protocol=UPP(test), error_metric='mae')
|
||||
|
||||
print(f'MAE={mae_score:.5f}')
|
||||
|
||||
print(f'model selection took {tend-tinit:.1f}s')
|
||||
|
||||
|
|
|
|||
|
|
@ -84,7 +84,7 @@ def run(experiment):
|
|||
optim_loss, dataset_name, (model_name, model, hyperparams) = experiment
|
||||
if dataset_name in ['acute.a', 'acute.b', 'iris.1']: return
|
||||
|
||||
collection = qp.datasets.fetch_UCILabelledCollection(dataset_name)
|
||||
collection = qp.datasets.fetch_UCIBinaryLabelledCollection(dataset_name)
|
||||
for run, data in enumerate(qp.data.Dataset.kFCV(collection, nfolds=5, nrepeats=1)):
|
||||
if is_already_computed(dataset_name, model_name, run=run, optim_loss=optim_loss):
|
||||
print(f'result for dataset={dataset_name} model={model_name} loss={optim_loss} run={run+1}/5 already computed.')
|
||||
|
|
@ -104,7 +104,7 @@ def run(experiment):
|
|||
timeout=60*60,
|
||||
verbose=True
|
||||
)
|
||||
model_selection.fit(data.training)
|
||||
model_selection.fit(train)
|
||||
model = model_selection.best_model()
|
||||
best_params = model_selection.best_params_
|
||||
else:
|
||||
|
|
@ -141,7 +141,7 @@ if __name__ == '__main__':
|
|||
qp.environ['SVMPERF_HOME'] = args.svmperfpath
|
||||
|
||||
optim_losses = ['mae']
|
||||
datasets = qp.datasets.UCI_DATASETS
|
||||
datasets = qp.datasets.UCI_BINARY_DATASETS
|
||||
|
||||
models = quantification_models()
|
||||
qp.util.parallel(run, itertools.product(optim_losses, datasets, models), n_jobs=N_JOBS)
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ from . import util
|
|||
from . import model_selection
|
||||
from . import classification
|
||||
|
||||
__version__ = '0.1.7'
|
||||
__version__ = '0.1.8'
|
||||
|
||||
environ = {
|
||||
'SAMPLE_SIZE': None,
|
||||
|
|
|
|||
|
|
@ -24,7 +24,8 @@ class RecalibratedProbabilisticClassifier:
|
|||
class RecalibratedProbabilisticClassifierBase(BaseEstimator, RecalibratedProbabilisticClassifier):
|
||||
"""
|
||||
Applies a (re)calibration method from `abstention.calibration`, as defined in
|
||||
`Alexandari et al. paper <http://proceedings.mlr.press/v119/alexandari20a.html>`_:
|
||||
`Alexandari et al. paper <http://proceedings.mlr.press/v119/alexandari20a.html>`_.
|
||||
|
||||
|
||||
:param classifier: a scikit-learn probabilistic classifier
|
||||
:param calibrator: the calibration object (an instance of abstention.calibration.CalibratorFactory)
|
||||
|
|
@ -59,7 +60,7 @@ class RecalibratedProbabilisticClassifierBase(BaseEstimator, RecalibratedProbabi
|
|||
elif isinstance(k, float):
|
||||
if not (0 < k < 1):
|
||||
raise ValueError('wrong value for val_split: the proportion of validation documents must be in (0,1)')
|
||||
return self.fit_cv(X, y)
|
||||
return self.fit_tr_val(X, y)
|
||||
|
||||
def fit_cv(self, X, y):
|
||||
"""
|
||||
|
|
@ -94,7 +95,7 @@ class RecalibratedProbabilisticClassifierBase(BaseEstimator, RecalibratedProbabi
|
|||
self.classifier.fit(Xtr, ytr)
|
||||
posteriors = self.classifier.predict_proba(Xva)
|
||||
nclasses = len(np.unique(yva))
|
||||
self.calibrator = self.calibrator(posteriors, np.eye(nclasses)[yva], posterior_supplied=True)
|
||||
self.calibration_function = self.calibrator(posteriors, np.eye(nclasses)[yva], posterior_supplied=True)
|
||||
return self
|
||||
|
||||
def predict(self, X):
|
||||
|
|
|
|||
|
|
@ -0,0 +1,104 @@
|
|||
import os
|
||||
import pandas as pd
|
||||
import math
|
||||
|
||||
from quapy.data import LabelledCollection
|
||||
from quapy.protocol import AbstractProtocol
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def get_sample_list(path_dir):
|
||||
"""Gets a sample list finding the csv files in a directory
|
||||
|
||||
Args:
|
||||
path_dir (_type_): directory to look for samples
|
||||
|
||||
Returns:
|
||||
_type_: list of samples
|
||||
"""
|
||||
samples = []
|
||||
for filename in sorted(os.listdir(path_dir)):
|
||||
if filename.endswith('.csv'):
|
||||
samples.append(filename)
|
||||
return samples
|
||||
|
||||
|
||||
def generate_modelselection_split(samples, split=0.3):
|
||||
"""This function generates a train/test split for model selection
|
||||
without the use of random numbers so the split is always the same
|
||||
|
||||
Args:
|
||||
samples (_type_): list of samples
|
||||
split (float, optional): percentage saved for test. Defaults to 0.3.
|
||||
|
||||
Returns:
|
||||
_type_: list of samples to use as train and list of samples to use as test
|
||||
"""
|
||||
num_items_to_pick = math.ceil(len(samples) * split)
|
||||
step_size = math.floor(len(samples) / num_items_to_pick)
|
||||
test_indices = [i * step_size for i in range(num_items_to_pick)]
|
||||
test = [samples[i] for i in test_indices]
|
||||
train = [item for i, item in enumerate(samples) if i not in test_indices]
|
||||
return train, test
|
||||
|
||||
|
||||
class IFCBTrainSamplesFromDir(AbstractProtocol):
|
||||
|
||||
def __init__(self, path_dir:str, classes: list, samples: list = None):
|
||||
self.path_dir = path_dir
|
||||
self.classes = classes
|
||||
self.samples = []
|
||||
if samples is not None:
|
||||
self.samples = samples
|
||||
else:
|
||||
self.samples = get_sample_list(path_dir)
|
||||
|
||||
def __call__(self):
|
||||
for sample in self.samples:
|
||||
s = pd.read_csv(os.path.join(self.path_dir,sample))
|
||||
# all columns but the first where we get the class
|
||||
X = s.iloc[:, 1:].to_numpy()
|
||||
y = s.iloc[:, 0].to_numpy()
|
||||
yield LabelledCollection(X, y, classes=self.classes)
|
||||
|
||||
def total(self):
|
||||
"""
|
||||
Returns the total number of samples that the protocol generates.
|
||||
|
||||
:return: The number of training samples to generate.
|
||||
"""
|
||||
return len(self.samples)
|
||||
|
||||
|
||||
class IFCBTestSamples(AbstractProtocol):
|
||||
|
||||
def __init__(self, path_dir:str, test_prevalences: pd.DataFrame, samples: list = None, classes: list=None):
|
||||
self.path_dir = path_dir
|
||||
self.test_prevalences = test_prevalences
|
||||
self.classes = classes
|
||||
if samples is not None:
|
||||
self.samples = samples
|
||||
else:
|
||||
self.samples = get_sample_list(path_dir)
|
||||
|
||||
def __call__(self):
|
||||
for test_sample in self.samples:
|
||||
s = pd.read_csv(os.path.join(self.path_dir,test_sample))
|
||||
if self.test_prevalences is not None:
|
||||
X = s
|
||||
# If we are working with the test samples, we have a dataframe with the prevalences and no labels for the test
|
||||
prevalences = self.test_prevalences.loc[self.test_prevalences['sample']==Path(test_sample).stem].to_numpy()[:,1:].flatten().astype(float)
|
||||
else:
|
||||
X = s.iloc[:, 1:].to_numpy()
|
||||
y = s.iloc[:,0]
|
||||
# In this case we compute the sample prevalences from the labels
|
||||
prevalences = y[y.isin(self.classes)].value_counts().reindex(self.classes, fill_value=0).to_numpy()/len(s)
|
||||
yield X, prevalences
|
||||
|
||||
def total(self):
|
||||
"""
|
||||
Returns the total number of samples that the protocol generates.
|
||||
|
||||
:return: The number of training samples to generate.
|
||||
"""
|
||||
return len(self.samples)
|
||||
|
|
@ -6,9 +6,7 @@ import os
|
|||
import zipfile
|
||||
from os.path import join
|
||||
import pandas as pd
|
||||
|
||||
from ucimlrepo import fetch_ucirepo
|
||||
|
||||
from ucimlrepo import fetch_ucirepo
|
||||
from quapy.data.base import Dataset, LabelledCollection
|
||||
from quapy.data.preprocessing import text2tfidf, reduce_columns
|
||||
from quapy.data.reader import *
|
||||
|
|
@ -22,29 +20,29 @@ TWITTER_SENTIMENT_DATASETS_TEST = ['gasp', 'hcr', 'omd', 'sanders',
|
|||
TWITTER_SENTIMENT_DATASETS_TRAIN = ['gasp', 'hcr', 'omd', 'sanders',
|
||||
'semeval', 'semeval16',
|
||||
'sst', 'wa', 'wb']
|
||||
UCI_DATASETS = ['acute.a', 'acute.b',
|
||||
UCI_BINARY_DATASETS = ['acute.a', 'acute.b',
|
||||
'balance.1', 'balance.2', 'balance.3',
|
||||
'breast-cancer',
|
||||
'cmc.1', 'cmc.2', 'cmc.3',
|
||||
'ctg.1', 'ctg.2', 'ctg.3',
|
||||
#'diabetes', # <-- I haven't found this one...
|
||||
#'diabetes', # <-- I haven't found this one...
|
||||
'german',
|
||||
'haberman',
|
||||
'ionosphere',
|
||||
'iris.1', 'iris.2', 'iris.3',
|
||||
'mammographic',
|
||||
'pageblocks.5',
|
||||
#'phoneme', # <-- I haven't found this one...
|
||||
'semeion',
|
||||
'sonar',
|
||||
'spambase',
|
||||
'spectf',
|
||||
'tictactoe',
|
||||
'transfusion',
|
||||
'wdbc',
|
||||
'wine.1', 'wine.2', 'wine.3',
|
||||
'wine-q-red', 'wine-q-white',
|
||||
'yeast']
|
||||
'pageblocks.5',
|
||||
#'phoneme', # <-- I haven't found this one...
|
||||
'semeion',
|
||||
'sonar',
|
||||
'spambase',
|
||||
'spectf',
|
||||
'tictactoe',
|
||||
'transfusion',
|
||||
'wdbc',
|
||||
'wine.1', 'wine.2', 'wine.3',
|
||||
'wine-q-red', 'wine-q-white',
|
||||
'yeast']
|
||||
|
||||
UCI_MULTICLASS_DATASETS = ['dry-bean',
|
||||
'wine-quality',
|
||||
|
|
@ -189,7 +187,7 @@ def fetch_twitter(dataset_name, for_model_selection=False, min_df=None, data_hom
|
|||
return data
|
||||
|
||||
|
||||
def fetch_UCIDataset(dataset_name, data_home=None, test_split=0.3, verbose=False) -> Dataset:
|
||||
def fetch_UCIBinaryDataset(dataset_name, data_home=None, test_split=0.3, verbose=False) -> Dataset:
|
||||
"""
|
||||
Loads a UCI dataset as an instance of :class:`quapy.data.base.Dataset`, as used in
|
||||
`Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
|
|
@ -210,11 +208,11 @@ def fetch_UCIDataset(dataset_name, data_home=None, test_split=0.3, verbose=False
|
|||
:param verbose: set to True (default is False) to get information (from the UCI ML repository) about the datasets
|
||||
:return: a :class:`quapy.data.base.Dataset` instance
|
||||
"""
|
||||
data = fetch_UCILabelledCollection(dataset_name, data_home, verbose)
|
||||
data = fetch_UCIBinaryLabelledCollection(dataset_name, data_home, verbose)
|
||||
return Dataset(*data.split_stratified(1 - test_split, random_state=0))
|
||||
|
||||
|
||||
def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) -> LabelledCollection:
|
||||
def fetch_UCIBinaryLabelledCollection(dataset_name, data_home=None, verbose=False) -> LabelledCollection:
|
||||
"""
|
||||
Loads a UCI collection as an instance of :class:`quapy.data.base.LabelledCollection`, as used in
|
||||
`Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
|
||||
|
|
@ -229,8 +227,8 @@ def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) ->
|
|||
This can be reproduced by using :meth:`quapy.data.base.Dataset.kFCV`, e.g.:
|
||||
|
||||
>>> import quapy as qp
|
||||
>>> collection = qp.datasets.fetch_UCILabelledCollection("yeast")
|
||||
>>> for data in qp.domains.Dataset.kFCV(collection, nfolds=5, nrepeats=2):
|
||||
>>> collection = qp.datasets.fetch_UCIBinaryLabelledCollection("yeast")
|
||||
>>> for data in qp.train.Dataset.kFCV(collection, nfolds=5, nrepeats=2):
|
||||
>>> ...
|
||||
|
||||
The list of valid dataset names can be accessed in `quapy.data.datasets.UCI_DATASETS`
|
||||
|
|
@ -243,9 +241,9 @@ def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) ->
|
|||
:return: a :class:`quapy.data.base.LabelledCollection` instance
|
||||
"""
|
||||
|
||||
assert dataset_name in UCI_DATASETS, \
|
||||
assert dataset_name in UCI_BINARY_DATASETS, \
|
||||
f'Name {dataset_name} does not match any known dataset from the UCI Machine Learning datasets repository. ' \
|
||||
f'Valid ones are {UCI_DATASETS}'
|
||||
f'Valid ones are {UCI_BINARY_DATASETS}'
|
||||
if data_home is None:
|
||||
data_home = get_quapy_home()
|
||||
|
||||
|
|
@ -371,7 +369,8 @@ def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) ->
|
|||
elif verbose:
|
||||
print('no file description available')
|
||||
|
||||
print(f'Loading {dataset_name} ({fullname})')
|
||||
if verbose:
|
||||
print(f'Loading {dataset_name} ({fullname})')
|
||||
if identifier == 'acute':
|
||||
df = pd.read_csv(data_path, header=None, encoding='utf-16', sep='\t')
|
||||
|
||||
|
|
@ -552,7 +551,8 @@ def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) ->
|
|||
y = binarize(y, pos_class='NUC')
|
||||
|
||||
data = LabelledCollection(X, y)
|
||||
data.stats()
|
||||
if verbose:
|
||||
data.stats()
|
||||
return data
|
||||
|
||||
|
||||
|
|
@ -686,8 +686,8 @@ def fetch_lequa2022(task, data_home=None):
|
|||
~/quay_data/ directory)
|
||||
:return: a tuple `(train, val_gen, test_gen)` where `train` is an instance of
|
||||
:class:`quapy.data.base.LabelledCollection`, `val_gen` and `test_gen` are instances of
|
||||
:class:`quapy.protocol.SamplesFromDir`, i.e., are sampling protocols that return a series of samples
|
||||
labelled by prevalence.
|
||||
:class:`quapy.data._lequa2022.SamplesFromDir`, a subclass of :class:`quapy.protocol.AbstractProtocol`,
|
||||
that return a series of samples stored in a directory which are labelled by prevalence.
|
||||
"""
|
||||
|
||||
from quapy.data._lequa2022 import load_raw_documents, load_vector_documents, SamplesFromDir
|
||||
|
|
@ -734,3 +734,83 @@ def fetch_lequa2022(task, data_home=None):
|
|||
|
||||
return train, val_gen, test_gen
|
||||
|
||||
|
||||
def fetch_IFCB(single_sample_train=True, for_model_selection=False, data_home=None):
|
||||
"""
|
||||
Loads the IFCB dataset for quantification from `Zenodo <https://zenodo.org/records/10036244>`_ (for more
|
||||
information on this dataset, please follow the zenodo link).
|
||||
This dataset is based on the data available publicly at
|
||||
`WHOI-Plankton repo <https://github.com/hsosik/WHOI-Plankton>`_.
|
||||
The scripts for the processing are available at `P. González's repo <https://github.com/pglez82/IFCB_Zenodo>`_.
|
||||
Basically, this is the IFCB dataset with precomputed features for testing quantification algorithms.
|
||||
|
||||
The datasets are downloaded only once, and stored for fast reuse.
|
||||
|
||||
:param single_sample_train: a boolean. If true, it will return the train dataset as a
|
||||
:class:`quapy.data.base.LabelledCollection` (all examples together).
|
||||
If false, a generator of training samples will be returned. Each example in the training set has an individual label.
|
||||
:param for_model_selection: if True, then returns a split 30% of the training set (86 out of 286 samples) to be used for model selection;
|
||||
if False, then returns the full training set as training set and the test set as the test set
|
||||
:param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
|
||||
~/quay_data/ directory)
|
||||
:return: a tuple `(train, test_gen)` where `train` is an instance of
|
||||
:class:`quapy.data.base.LabelledCollection`, if `single_sample_train` is true or
|
||||
:class:`quapy.data._ifcb.IFCBTrainSamplesFromDir`, i.e. a sampling protocol that returns a series of samples
|
||||
labelled example by example. test_gen will be a :class:`quapy.data._ifcb.IFCBTestSamples`,
|
||||
i.e., a sampling protocol that returns a series of samples labelled by prevalence.
|
||||
"""
|
||||
|
||||
from quapy.data._ifcb import IFCBTrainSamplesFromDir, IFCBTestSamples, get_sample_list, generate_modelselection_split
|
||||
|
||||
if data_home is None:
|
||||
data_home = get_quapy_home()
|
||||
|
||||
URL_TRAIN=f'https://zenodo.org/records/10036244/files/IFCB.train.zip'
|
||||
URL_TEST=f'https://zenodo.org/records/10036244/files/IFCB.test.zip'
|
||||
URL_TEST_PREV=f'https://zenodo.org/records/10036244/files/IFCB.test_prevalences.zip'
|
||||
|
||||
ifcb_dir = join(data_home, 'ifcb')
|
||||
os.makedirs(ifcb_dir, exist_ok=True)
|
||||
|
||||
def download_unzip_and_remove(unzipped_path, url):
|
||||
tmp_path = join(ifcb_dir, 'ifcb_tmp.zip')
|
||||
download_file_if_not_exists(url, tmp_path)
|
||||
with zipfile.ZipFile(tmp_path) as file:
|
||||
file.extractall(unzipped_path)
|
||||
os.remove(tmp_path)
|
||||
|
||||
if not os.path.exists(os.path.join(ifcb_dir,'train')):
|
||||
download_unzip_and_remove(ifcb_dir, URL_TRAIN)
|
||||
if not os.path.exists(os.path.join(ifcb_dir,'test')):
|
||||
download_unzip_and_remove(ifcb_dir, URL_TEST)
|
||||
if not os.path.exists(os.path.join(ifcb_dir,'test_prevalences.csv')):
|
||||
download_unzip_and_remove(ifcb_dir, URL_TEST_PREV)
|
||||
|
||||
# Load test prevalences and classes
|
||||
test_true_prev_path = join(ifcb_dir, 'test_prevalences.csv')
|
||||
test_true_prev = pd.read_csv(test_true_prev_path)
|
||||
classes = test_true_prev.columns[1:]
|
||||
|
||||
#Load train and test samples
|
||||
train_samples_path = join(ifcb_dir,'train')
|
||||
test_samples_path = join(ifcb_dir,'test')
|
||||
|
||||
if for_model_selection:
|
||||
# In this case, return 70% of training data as the training set and 30% as the test set
|
||||
samples = get_sample_list(train_samples_path)
|
||||
train, test = generate_modelselection_split(samples, split=0.3)
|
||||
train_gen = IFCBTrainSamplesFromDir(path_dir=train_samples_path, classes=classes, samples=train)
|
||||
|
||||
# Test prevalence is computed from class labels
|
||||
test_gen = IFCBTestSamples(path_dir=train_samples_path, test_prevalences=None, samples=test, classes=classes)
|
||||
else:
|
||||
# In this case, we use all training samples as the training set and the test samples as the test set
|
||||
train_gen = IFCBTrainSamplesFromDir(path_dir=train_samples_path, classes=classes)
|
||||
test_gen = IFCBTestSamples(path_dir=test_samples_path, test_prevalences=test_true_prev)
|
||||
|
||||
# In the case the user wants it, join all the train samples in one LabelledCollection
|
||||
if single_sample_train:
|
||||
train = LabelledCollection.join(*[lc for lc in train_gen()])
|
||||
return train, test_gen
|
||||
else:
|
||||
return train_gen, test_gen
|
||||
|
|
|
|||
|
|
@ -70,6 +70,32 @@ def ae(prevs, prevs_hat):
|
|||
return abs(prevs_hat - prevs).mean(axis=-1)
|
||||
|
||||
|
||||
def nae(prevs, prevs_hat):
|
||||
"""Computes the normalized absolute error between the two prevalence vectors.
|
||||
Normalized absolute error between two prevalence vectors :math:`p` and :math:`\\hat{p}` is computed as
|
||||
:math:`NAE(p,\\hat{p})=\\frac{AE(p,\\hat{p})}{z_{AE}}`,
|
||||
where :math:`z_{AE}=\\frac{2(1-\\min_{y\\in \\mathcal{Y}} p(y))}{|\\mathcal{Y}|}`, and :math:`\\mathcal{Y}`
|
||||
are the classes of interest.
|
||||
|
||||
:param prevs: array-like of shape `(n_classes,)` with the true prevalence values
|
||||
:param prevs_hat: array-like of shape `(n_classes,)` with the predicted prevalence values
|
||||
:return: normalized absolute error
|
||||
"""
|
||||
assert prevs.shape == prevs_hat.shape, f'wrong shape {prevs.shape} vs. {prevs_hat.shape}'
|
||||
return abs(prevs_hat - prevs).sum(axis=-1)/(2*(1-prevs.min(axis=-1)))
|
||||
|
||||
|
||||
def mnae(prevs, prevs_hat):
|
||||
"""Computes the mean normalized absolute error (see :meth:`quapy.error.nae`) across the sample pairs.
|
||||
|
||||
:param prevs: array-like of shape `(n_samples, n_classes,)` with the true prevalence values
|
||||
:param prevs_hat: array-like of shape `(n_samples, n_classes,)` with the predicted
|
||||
prevalence values
|
||||
:return: mean normalized absolute error
|
||||
"""
|
||||
return nae(prevs, prevs_hat).mean()
|
||||
|
||||
|
||||
def mse(prevs, prevs_hat):
|
||||
"""Computes the mean squared error (see :meth:`quapy.error.se`) across the sample pairs.
|
||||
|
||||
|
|
@ -216,6 +242,49 @@ def rae(prevs, prevs_hat, eps=None):
|
|||
return (abs(prevs - prevs_hat) / prevs).mean(axis=-1)
|
||||
|
||||
|
||||
def nrae(prevs, prevs_hat, eps=None):
|
||||
"""Computes the normalized absolute relative error between the two prevalence vectors.
|
||||
Relative absolute error between two prevalence vectors :math:`p` and :math:`\\hat{p}`
|
||||
is computed as
|
||||
:math:`NRAE(p,\\hat{p})= \\frac{RAE(p,\\hat{p})}{z_{RAE}}`,
|
||||
where
|
||||
:math:`z_{RAE} = \\frac{|\\mathcal{Y}|-1+\\frac{1-\\min_{y\\in \\mathcal{Y}} p(y)}{\\min_{y\\in \\mathcal{Y}} p(y)}}{|\\mathcal{Y}|}`
|
||||
and :math:`\\mathcal{Y}` are the classes of interest.
|
||||
The distributions are smoothed using the `eps` factor (see :meth:`quapy.error.smooth`).
|
||||
|
||||
:param prevs: array-like of shape `(n_classes,)` with the true prevalence values
|
||||
:param prevs_hat: array-like of shape `(n_classes,)` with the predicted prevalence values
|
||||
:param eps: smoothing factor. `nrae` is not defined in cases in which the true distribution
|
||||
contains zeros; `eps` is typically set to be :math:`\\frac{1}{2T}`, with :math:`T` the
|
||||
sample size. If `eps=None`, the sample size will be taken from the environment variable
|
||||
`SAMPLE_SIZE` (which has thus to be set beforehand).
|
||||
:return: normalized relative absolute error
|
||||
"""
|
||||
eps = __check_eps(eps)
|
||||
prevs = smooth(prevs, eps)
|
||||
prevs_hat = smooth(prevs_hat, eps)
|
||||
min_p = prevs.min(axis=-1)
|
||||
return (abs(prevs - prevs_hat) / prevs).sum(axis=-1)/(prevs.shape[-1]-1+(1-min_p)/min_p)
|
||||
|
||||
|
||||
def mnrae(prevs, prevs_hat, eps=None):
|
||||
"""Computes the mean normalized relative absolute error (see :meth:`quapy.error.nrae`) across
|
||||
the sample pairs. The distributions are smoothed using the `eps` factor (see
|
||||
:meth:`quapy.error.smooth`).
|
||||
|
||||
:param prevs: array-like of shape `(n_samples, n_classes,)` with the true
|
||||
prevalence values
|
||||
:param prevs_hat: array-like of shape `(n_samples, n_classes,)` with the predicted
|
||||
prevalence values
|
||||
:param eps: smoothing factor. `mnrae` is not defined in cases in which the true
|
||||
distribution contains zeros; `eps` is typically set to be :math:`\\frac{1}{2T}`,
|
||||
with :math:`T` the sample size. If `eps=None`, the sample size will be taken from
|
||||
the environment variable `SAMPLE_SIZE` (which has thus to be set beforehand).
|
||||
:return: mean normalized relative absolute error
|
||||
"""
|
||||
return nrae(prevs, prevs_hat, eps).mean()
|
||||
|
||||
|
||||
def smooth(prevs, eps):
|
||||
""" Smooths a prevalence distribution with :math:`\\epsilon` (`eps`) as:
|
||||
:math:`\\underline{p}(y)=\\frac{\\epsilon+p(y)}{\\epsilon|\\mathcal{Y}|+
|
||||
|
|
@ -239,9 +308,9 @@ def __check_eps(eps=None):
|
|||
|
||||
|
||||
CLASSIFICATION_ERROR = {f1e, acce}
|
||||
QUANTIFICATION_ERROR = {mae, mrae, mse, mkld, mnkld}
|
||||
QUANTIFICATION_ERROR_SINGLE = {ae, rae, se, kld, nkld}
|
||||
QUANTIFICATION_ERROR_SMOOTH = {kld, nkld, rae, mkld, mnkld, mrae}
|
||||
QUANTIFICATION_ERROR = {mae, mnae, mrae, mnrae, mse, mkld, mnkld}
|
||||
QUANTIFICATION_ERROR_SINGLE = {ae, nae, rae, nrae, se, kld, nkld}
|
||||
QUANTIFICATION_ERROR_SMOOTH = {kld, nkld, rae, nrae, mkld, mnkld, mrae}
|
||||
CLASSIFICATION_ERROR_NAMES = {func.__name__ for func in CLASSIFICATION_ERROR}
|
||||
QUANTIFICATION_ERROR_NAMES = {func.__name__ for func in QUANTIFICATION_ERROR}
|
||||
QUANTIFICATION_ERROR_SINGLE_NAMES = {func.__name__ for func in QUANTIFICATION_ERROR_SINGLE}
|
||||
|
|
@ -255,3 +324,7 @@ mean_absolute_error = mae
|
|||
absolute_error = ae
|
||||
mean_relative_absolute_error = mrae
|
||||
relative_absolute_error = rae
|
||||
normalized_absolute_error = nae
|
||||
normalized_relative_absolute_error = nrae
|
||||
mean_normalized_absolute_error = mnae
|
||||
mean_normalized_relative_absolute_error = mnrae
|
||||
|
|
|
|||
|
|
@ -118,14 +118,15 @@ def _prevalence_report(true_prevs, estim_prevs, error_metrics: Iterable[Union[st
|
|||
assert all(hasattr(e, '__call__') for e in error_funcs), 'invalid error functions'
|
||||
error_names = [e.__name__ for e in error_funcs]
|
||||
|
||||
df = pd.DataFrame(columns=['true-prev', 'estim-prev'] + error_names)
|
||||
row_entries = []
|
||||
for true_prev, estim_prev in zip(true_prevs, estim_prevs):
|
||||
series = {'true-prev': true_prev, 'estim-prev': estim_prev}
|
||||
for error_name, error_metric in zip(error_names, error_funcs):
|
||||
score = error_metric(true_prev, estim_prev)
|
||||
series[error_name] = score
|
||||
df = df.append(series, ignore_index=True)
|
||||
row_entries.append(series)
|
||||
|
||||
df = pd.DataFrame.from_records(row_entries)
|
||||
return df
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
import itertools
|
||||
from collections import defaultdict
|
||||
from typing import Union, Callable
|
||||
|
||||
import scipy
|
||||
import numpy as np
|
||||
|
||||
|
|
@ -64,7 +66,25 @@ def prevalence_from_probabilities(posteriors, binarize: bool = False):
|
|||
return prevalences
|
||||
|
||||
|
||||
def HellingerDistance(P, Q):
|
||||
def as_binary_prevalence(positive_prevalence: Union[float, np.ndarray], clip_if_necessary=False):
|
||||
"""
|
||||
Helper that, given a float representing the prevalence for the positive class, returns a np.ndarray of two
|
||||
values representing a binary distribution.
|
||||
|
||||
:param positive_prevalence: prevalence for the positive class
|
||||
:param clip_if_necessary: if True, clips the value in [0,1] in order to guarantee the resulting distribution
|
||||
is valid. If False, it then checks that the value is in the valid range, and raises an error if not.
|
||||
:return: np.ndarray of shape `(2,)`
|
||||
"""
|
||||
if clip_if_necessary:
|
||||
positive_prevalence = np.clip(positive_prevalence, 0, 1)
|
||||
else:
|
||||
assert 0 <= positive_prevalence <= 1, 'the value provided is not a valid prevalence for the positive class'
|
||||
return np.asarray([1-positive_prevalence, positive_prevalence]).T
|
||||
|
||||
|
||||
|
||||
def HellingerDistance(P, Q) -> float:
|
||||
"""
|
||||
Computes the Hellingher Distance (HD) between (discretized) distributions `P` and `Q`.
|
||||
The HD for two discrete distributions of `k` bins is defined as:
|
||||
|
|
@ -276,3 +296,70 @@ def check_prevalence_vector(p, raise_exception=False, toleranze=1e-08):
|
|||
return False
|
||||
return True
|
||||
|
||||
|
||||
def get_divergence(divergence: Union[str, Callable]):
|
||||
if isinstance(divergence, str):
|
||||
if divergence=='HD':
|
||||
return HellingerDistance
|
||||
elif divergence=='topsoe':
|
||||
return TopsoeDistance
|
||||
else:
|
||||
raise ValueError(f'unknown divergence {divergence}')
|
||||
elif callable(divergence):
|
||||
return divergence
|
||||
else:
|
||||
raise ValueError(f'argument "divergence" not understood; use a str or a callable function')
|
||||
|
||||
|
||||
def argmin_prevalence(loss, n_classes, method='optim_minimize'):
|
||||
if method == 'optim_minimize':
|
||||
return optim_minimize(loss, n_classes)
|
||||
elif method == 'linear_search':
|
||||
return linear_search(loss, n_classes)
|
||||
elif method == 'ternary_search':
|
||||
raise NotImplementedError()
|
||||
else:
|
||||
raise NotImplementedError()
|
||||
|
||||
|
||||
def optim_minimize(loss, n_classes):
|
||||
"""
|
||||
Searches for the optimal prevalence values, i.e., an `n_classes`-dimensional vector of the (`n_classes`-1)-simplex
|
||||
that yields the smallest lost. This optimization is carried out by means of a constrained search using scipy's
|
||||
SLSQP routine.
|
||||
|
||||
:param loss: (callable) the function to minimize
|
||||
:param n_classes: (int) the number of classes, i.e., the dimensionality of the prevalence vector
|
||||
:return: (ndarray) the best prevalence vector found
|
||||
"""
|
||||
from scipy import optimize
|
||||
|
||||
# the initial point is set as the uniform distribution
|
||||
uniform_distribution = np.full(fill_value=1 / n_classes, shape=(n_classes,))
|
||||
|
||||
# solutions are bounded to those contained in the unit-simplex
|
||||
bounds = tuple((0, 1) for _ in range(n_classes)) # values in [0,1]
|
||||
constraints = ({'type': 'eq', 'fun': lambda x: 1 - sum(x)}) # values summing up to 1
|
||||
r = optimize.minimize(loss, x0=uniform_distribution, method='SLSQP', bounds=bounds, constraints=constraints)
|
||||
return r.x
|
||||
|
||||
|
||||
def linear_search(loss, n_classes):
|
||||
"""
|
||||
Performs a linear search for the best prevalence value in binary problems. The search is carried out by exploring
|
||||
the range [0,1] stepping by 0.01. This search is inefficient, and is added only for completeness (some of the
|
||||
early methods in quantification literature used it, e.g., HDy). A most powerful alternative is `optim_minimize`.
|
||||
|
||||
:param loss: (callable) the function to minimize
|
||||
:param n_classes: (int) the number of classes, i.e., the dimensionality of the prevalence vector
|
||||
:return: (ndarray) the best prevalence vector found
|
||||
"""
|
||||
assert n_classes==2, 'linear search is only available for binary problems'
|
||||
|
||||
prev_selected, min_score = None, None
|
||||
for prev in prevalence_linspace(n_prevalences=100, repeats=1, smooth_limits_epsilon=0.0):
|
||||
score = loss(np.asarray([1 - prev, prev]))
|
||||
if min_score is None or score < min_score:
|
||||
prev_selected, min_score = prev, score
|
||||
|
||||
return np.asarray([1 - prev_selected, prev_selected])
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
from . import aggregative
|
||||
from . import base
|
||||
from . import meta
|
||||
from . import aggregative
|
||||
from . import non_aggregative
|
||||
from . import meta
|
||||
|
||||
AGGREGATIVE_METHODS = {
|
||||
aggregative.CC,
|
||||
|
|
@ -17,6 +17,9 @@ AGGREGATIVE_METHODS = {
|
|||
aggregative.MAX,
|
||||
aggregative.MS,
|
||||
aggregative.MS2,
|
||||
aggregative.KDEyML,
|
||||
aggregative.KDEyCS,
|
||||
aggregative.KDEyHD,
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,359 @@
|
|||
from typing import Union
|
||||
import numpy as np
|
||||
from sklearn.base import BaseEstimator
|
||||
from sklearn.neighbors import KernelDensity
|
||||
|
||||
import quapy as qp
|
||||
from quapy.data import LabelledCollection
|
||||
from quapy.method.aggregative import AggregativeSoftQuantifier
|
||||
import quapy.functional as F
|
||||
|
||||
from sklearn.metrics.pairwise import rbf_kernel
|
||||
|
||||
|
||||
class KDEBase:
|
||||
"""
|
||||
Common ancestor for KDE-based methods. Implements some common routines.
|
||||
"""
|
||||
|
||||
BANDWIDTH_METHOD = ['scott', 'silverman']
|
||||
|
||||
@classmethod
|
||||
def _check_bandwidth(cls, bandwidth):
|
||||
"""
|
||||
Checks that the bandwidth parameter is correct
|
||||
|
||||
:param bandwidth: either a string (see BANDWIDTH_METHOD) or a float
|
||||
:return: nothing, but raises an exception for invalid values
|
||||
"""
|
||||
assert bandwidth in KDEBase.BANDWIDTH_METHOD or isinstance(bandwidth, float), \
|
||||
f'invalid bandwidth, valid ones are {KDEBase.BANDWIDTH_METHOD} or float values'
|
||||
if isinstance(bandwidth, float):
|
||||
assert 0 < bandwidth < 1, "the bandwith for KDEy should be in (0,1), since this method models the unit simplex"
|
||||
|
||||
def get_kde_function(self, X, bandwidth):
|
||||
"""
|
||||
Wraps the KDE function from scikit-learn.
|
||||
|
||||
:param X: data for which the density function is to be estimated
|
||||
:param bandwidth: the bandwidth of the kernel
|
||||
:return: a scikit-learn's KernelDensity object
|
||||
"""
|
||||
return KernelDensity(bandwidth=bandwidth).fit(X)
|
||||
|
||||
def pdf(self, kde, X):
|
||||
"""
|
||||
Wraps the density evalution of scikit-learn's KDE. Scikit-learn returns log-scores (s), so this
|
||||
function returns :math:`e^{s}`
|
||||
|
||||
:param kde: a previously fit KDE function
|
||||
:param X: the data for which the density is to be estimated
|
||||
:return: np.ndarray with the densities
|
||||
"""
|
||||
return np.exp(kde.score_samples(X))
|
||||
|
||||
def get_mixture_components(self, X, y, n_classes, bandwidth):
|
||||
"""
|
||||
Returns an array containing the mixture components, i.e., the KDE functions for each class.
|
||||
|
||||
:param X: the data containing the covariates
|
||||
:param y: the class labels
|
||||
:param n_classes: integer, the number of classes
|
||||
:param bandwidth: float, the bandwidth of the kernel
|
||||
:return: a list of KernelDensity objects, each fitted with the corresponding class-specific covariates
|
||||
"""
|
||||
return [self.get_kde_function(X[y == cat], bandwidth) for cat in range(n_classes)]
|
||||
|
||||
|
||||
|
||||
class KDEyML(AggregativeSoftQuantifier, KDEBase):
|
||||
"""
|
||||
Kernel Density Estimation model for quantification (KDEy) relying on the Kullback-Leibler divergence (KLD) as
|
||||
the divergence measure to be minimized. This method was first proposed in the paper
|
||||
`Kernel Density Estimation for Multiclass Quantification <https://arxiv.org/abs/2401.00490>`_, in which
|
||||
the authors show that minimizing the distribution mathing criterion for KLD is akin to performing
|
||||
maximum likelihood (ML).
|
||||
|
||||
The distribution matching optimization problem comes down to solving:
|
||||
|
||||
:math:`\\hat{\\alpha} = \\arg\\min_{\\alpha\\in\\Delta^{n-1}} \\mathcal{D}(\\boldsymbol{p}_{\\alpha}||q_{\\widetilde{U}})`
|
||||
|
||||
where :math:`p_{\\alpha}` is the mixture of class-specific KDEs with mixture parameter (hence class prevalence)
|
||||
:math:`\\alpha` defined by
|
||||
|
||||
:math:`\\boldsymbol{p}_{\\alpha}(\\widetilde{x}) = \\sum_{i=1}^n \\alpha_i p_{\\widetilde{L}_i}(\\widetilde{x})`
|
||||
|
||||
where :math:`p_X(\\boldsymbol{x}) = \\frac{1}{|X|} \\sum_{x_i\\in X} K\\left(\\frac{x-x_i}{h}\\right)` is the
|
||||
KDE function that uses the datapoints in X as the kernel centers.
|
||||
|
||||
In KDEy-ML, the divergence is taken to be the Kullback-Leibler Divergence. This is equivalent to solving:
|
||||
:math:`\\hat{\\alpha} = \\arg\\min_{\\alpha\\in\\Delta^{n-1}} -
|
||||
\\mathbb{E}_{q_{\\widetilde{U}}} \\left[ \\log \\boldsymbol{p}_{\\alpha}(\\widetilde{x}) \\right]`
|
||||
|
||||
which corresponds to the maximum likelihood estimate.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a binary classifier.
|
||||
:param val_split: specifies the data used for generating classifier predictions. This specification
|
||||
can be made as float in (0, 1) indicating the proportion of stratified held-out validation set to
|
||||
be extracted from the training set; or as an integer (default 5), indicating that the predictions
|
||||
are to be generated in a `k`-fold cross-validation manner (with this integer indicating the value
|
||||
for `k`); or as a collection defining the specific set of data to use for validation.
|
||||
Alternatively, this set can be specified at fit time by indicating the exact set of data
|
||||
on which the predictions are to be generated.
|
||||
:param bandwidth: float, the bandwidth of the Kernel
|
||||
:param n_jobs: number of parallel workers
|
||||
:param random_state: a seed to be set before fitting any base quantifier (default None)
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=10, bandwidth=0.1, n_jobs=None, random_state=None):
|
||||
self._check_bandwidth(bandwidth)
|
||||
self.classifier = classifier
|
||||
self.val_split = val_split
|
||||
self.bandwidth = bandwidth
|
||||
self.n_jobs = n_jobs
|
||||
self.random_state=random_state
|
||||
|
||||
def aggregation_fit(self, classif_predictions: LabelledCollection, data: LabelledCollection):
|
||||
self.mix_densities = self.get_mixture_components(*classif_predictions.Xy, data.n_classes, self.bandwidth)
|
||||
return self
|
||||
|
||||
def aggregate(self, posteriors: np.ndarray):
|
||||
"""
|
||||
Searches for the mixture model parameter (the sought prevalence values) that maximizes the likelihood
|
||||
of the data (i.e., that minimizes the negative log-likelihood)
|
||||
|
||||
:param posteriors: instances in the sample converted into posterior probabilities
|
||||
:return: a vector of class prevalence estimates
|
||||
"""
|
||||
np.random.RandomState(self.random_state)
|
||||
epsilon = 1e-10
|
||||
n_classes = len(self.mix_densities)
|
||||
test_densities = [self.pdf(kde_i, posteriors) for kde_i in self.mix_densities]
|
||||
|
||||
def neg_loglikelihood(prev):
|
||||
test_mixture_likelihood = sum(prev_i * dens_i for prev_i, dens_i in zip (prev, test_densities))
|
||||
test_loglikelihood = np.log(test_mixture_likelihood + epsilon)
|
||||
return -np.sum(test_loglikelihood)
|
||||
|
||||
return F.optim_minimize(neg_loglikelihood, n_classes)
|
||||
|
||||
|
||||
class KDEyHD(AggregativeSoftQuantifier, KDEBase):
|
||||
"""
|
||||
Kernel Density Estimation model for quantification (KDEy) relying on the squared Hellinger Disntace (HD) as
|
||||
the divergence measure to be minimized. This method was first proposed in the paper
|
||||
`Kernel Density Estimation for Multiclass Quantification <https://arxiv.org/abs/2401.00490>`_, in which
|
||||
the authors proposed a Monte Carlo approach for minimizing the divergence.
|
||||
|
||||
The distribution matching optimization problem comes down to solving:
|
||||
|
||||
:math:`\\hat{\\alpha} = \\arg\\min_{\\alpha\\in\\Delta^{n-1}} \\mathcal{D}(\\boldsymbol{p}_{\\alpha}||q_{\\widetilde{U}})`
|
||||
|
||||
where :math:`p_{\\alpha}` is the mixture of class-specific KDEs with mixture parameter (hence class prevalence)
|
||||
:math:`\\alpha` defined by
|
||||
|
||||
:math:`\\boldsymbol{p}_{\\alpha}(\\widetilde{x}) = \\sum_{i=1}^n \\alpha_i p_{\\widetilde{L}_i}(\\widetilde{x})`
|
||||
|
||||
where :math:`p_X(\\boldsymbol{x}) = \\frac{1}{|X|} \\sum_{x_i\\in X} K\\left(\\frac{x-x_i}{h}\\right)` is the
|
||||
KDE function that uses the datapoints in X as the kernel centers.
|
||||
|
||||
In KDEy-HD, the divergence is taken to be the squared Hellinger Distance, an f-divergence with corresponding
|
||||
f-generator function given by:
|
||||
|
||||
:math:`f(u)=(\\sqrt{u}-1)^2`
|
||||
|
||||
The authors proposed a Monte Carlo solution that relies on importance sampling:
|
||||
|
||||
:math:`\\hat{D}_f(p||q)= \\frac{1}{t} \\sum_{i=1}^t f\\left(\\frac{p(x_i)}{q(x_i)}\\right) \\frac{q(x_i)}{r(x_i)}`
|
||||
|
||||
where the datapoints (trials) :math:`x_1,\\ldots,x_t\\sim_{\\mathrm{iid}} r` with :math:`r` the
|
||||
uniform distribution.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a binary classifier.
|
||||
:param val_split: specifies the data used for generating classifier predictions. This specification
|
||||
can be made as float in (0, 1) indicating the proportion of stratified held-out validation set to
|
||||
be extracted from the training set; or as an integer (default 5), indicating that the predictions
|
||||
are to be generated in a `k`-fold cross-validation manner (with this integer indicating the value
|
||||
for `k`); or as a collection defining the specific set of data to use for validation.
|
||||
Alternatively, this set can be specified at fit time by indicating the exact set of data
|
||||
on which the predictions are to be generated.
|
||||
:param bandwidth: float, the bandwidth of the Kernel
|
||||
:param n_jobs: number of parallel workers
|
||||
:param random_state: a seed to be set before fitting any base quantifier (default None)
|
||||
:param montecarlo_trials: number of Monte Carlo trials (default 10000)
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=10, divergence: str='HD',
|
||||
bandwidth=0.1, n_jobs=None, random_state=None, montecarlo_trials=10000):
|
||||
|
||||
self._check_bandwidth(bandwidth)
|
||||
self.classifier = classifier
|
||||
self.val_split = val_split
|
||||
self.divergence = divergence
|
||||
self.bandwidth = bandwidth
|
||||
self.n_jobs = n_jobs
|
||||
self.random_state=random_state
|
||||
self.montecarlo_trials = montecarlo_trials
|
||||
|
||||
def aggregation_fit(self, classif_predictions: LabelledCollection, data: LabelledCollection):
|
||||
self.mix_densities = self.get_mixture_components(*classif_predictions.Xy, data.n_classes, self.bandwidth)
|
||||
|
||||
N = self.montecarlo_trials
|
||||
rs = self.random_state
|
||||
n = data.n_classes
|
||||
self.reference_samples = np.vstack([kde_i.sample(N//n, random_state=rs) for kde_i in self.mix_densities])
|
||||
self.reference_classwise_densities = np.asarray([self.pdf(kde_j, self.reference_samples) for kde_j in self.mix_densities])
|
||||
self.reference_density = np.mean(self.reference_classwise_densities, axis=0) # equiv. to (uniform @ self.reference_classwise_densities)
|
||||
|
||||
return self
|
||||
|
||||
def aggregate(self, posteriors: np.ndarray):
|
||||
# we retain all n*N examples (sampled from a mixture with uniform parameter), and then
|
||||
# apply importance sampling (IS). In this version we compute D(p_alpha||q) with IS
|
||||
n_classes = len(self.mix_densities)
|
||||
|
||||
test_kde = self.get_kde_function(posteriors, self.bandwidth)
|
||||
test_densities = self.pdf(test_kde, self.reference_samples)
|
||||
|
||||
def f_squared_hellinger(u):
|
||||
return (np.sqrt(u)-1)**2
|
||||
|
||||
# todo: this will fail when self.divergence is a callable, and is not the right place to do it anyway
|
||||
if self.divergence.lower() == 'hd':
|
||||
f = f_squared_hellinger
|
||||
else:
|
||||
raise ValueError('only squared HD is currently implemented')
|
||||
|
||||
epsilon = 1e-10
|
||||
qs = test_densities + epsilon
|
||||
rs = self.reference_density + epsilon
|
||||
iw = qs/rs #importance weights
|
||||
p_class = self.reference_classwise_densities + epsilon
|
||||
fracs = p_class/qs
|
||||
|
||||
def divergence(prev):
|
||||
# ps / qs = (prev @ p_class) / qs = prev @ (p_class / qs) = prev @ fracs
|
||||
ps_div_qs = prev @ fracs
|
||||
return np.mean( f(ps_div_qs) * iw )
|
||||
|
||||
return F.optim_minimize(divergence, n_classes)
|
||||
|
||||
|
||||
class KDEyCS(AggregativeSoftQuantifier):
|
||||
"""
|
||||
Kernel Density Estimation model for quantification (KDEy) relying on the Cauchy-Schwarz divergence (CS) as
|
||||
the divergence measure to be minimized. This method was first proposed in the paper
|
||||
`Kernel Density Estimation for Multiclass Quantification <https://arxiv.org/abs/2401.00490>`_, in which
|
||||
the authors proposed a Monte Carlo approach for minimizing the divergence.
|
||||
|
||||
The distribution matching optimization problem comes down to solving:
|
||||
|
||||
:math:`\\hat{\\alpha} = \\arg\\min_{\\alpha\\in\\Delta^{n-1}} \\mathcal{D}(\\boldsymbol{p}_{\\alpha}||q_{\\widetilde{U}})`
|
||||
|
||||
where :math:`p_{\\alpha}` is the mixture of class-specific KDEs with mixture parameter (hence class prevalence)
|
||||
:math:`\\alpha` defined by
|
||||
|
||||
:math:`\\boldsymbol{p}_{\\alpha}(\\widetilde{x}) = \\sum_{i=1}^n \\alpha_i p_{\\widetilde{L}_i}(\\widetilde{x})`
|
||||
|
||||
where :math:`p_X(\\boldsymbol{x}) = \\frac{1}{|X|} \\sum_{x_i\\in X} K\\left(\\frac{x-x_i}{h}\\right)` is the
|
||||
KDE function that uses the datapoints in X as the kernel centers.
|
||||
|
||||
In KDEy-CS, the divergence is taken to be the Cauchy-Schwarz divergence given by:
|
||||
|
||||
:math:`\\mathcal{D}_{\\mathrm{CS}}(p||q)=-\\log\\left(\\frac{\\int p(x)q(x)dx}{\\sqrt{\\int p(x)^2dx \\int q(x)^2dx}}\\right)`
|
||||
|
||||
The authors showed that this distribution matching admits a closed-form solution
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a binary classifier.
|
||||
:param val_split: specifies the data used for generating classifier predictions. This specification
|
||||
can be made as float in (0, 1) indicating the proportion of stratified held-out validation set to
|
||||
be extracted from the training set; or as an integer (default 5), indicating that the predictions
|
||||
are to be generated in a `k`-fold cross-validation manner (with this integer indicating the value
|
||||
for `k`); or as a collection defining the specific set of data to use for validation.
|
||||
Alternatively, this set can be specified at fit time by indicating the exact set of data
|
||||
on which the predictions are to be generated.
|
||||
:param bandwidth: float, the bandwidth of the Kernel
|
||||
:param n_jobs: number of parallel workers
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=10, bandwidth=0.1, n_jobs=None):
|
||||
KDEBase._check_bandwidth(bandwidth)
|
||||
self.classifier = classifier
|
||||
self.val_split = val_split
|
||||
self.bandwidth = bandwidth
|
||||
self.n_jobs = n_jobs
|
||||
|
||||
def gram_matrix_mix_sum(self, X, Y=None):
|
||||
# this adapts the output of the rbf_kernel function (pairwise evaluations of Gaussian kernels k(x,y))
|
||||
# to contain pairwise evaluations of N(x|mu,Sigma1+Sigma2) with mu=y and Sigma1 and Sigma2 are
|
||||
# two "scalar matrices" (h^2)*I each, so Sigma1+Sigma2 has scalar 2(h^2) (h is the bandwidth)
|
||||
h = self.bandwidth
|
||||
variance = 2 * (h**2)
|
||||
nD = X.shape[1]
|
||||
gamma = 1/(2*variance)
|
||||
norm_factor = 1/np.sqrt(((2*np.pi)**nD) * (variance**(nD)))
|
||||
gram = norm_factor * rbf_kernel(X, Y, gamma=gamma)
|
||||
return gram.sum()
|
||||
|
||||
def aggregation_fit(self, classif_predictions: LabelledCollection, data: LabelledCollection):
|
||||
|
||||
P, y = classif_predictions.Xy
|
||||
n = data.n_classes
|
||||
|
||||
assert all(sorted(np.unique(y)) == np.arange(n)), \
|
||||
'label name gaps not allowed in current implementation'
|
||||
|
||||
# counts_inv keeps track of the relative weight of each datapoint within its class
|
||||
# (i.e., the weight in its KDE model)
|
||||
counts_inv = 1 / (data.counts())
|
||||
|
||||
# tr_tr_sums corresponds to symbol \overline{B} in the paper
|
||||
tr_tr_sums = np.zeros(shape=(n,n), dtype=float)
|
||||
for i in range(n):
|
||||
for j in range(n):
|
||||
if i > j:
|
||||
tr_tr_sums[i,j] = tr_tr_sums[j,i]
|
||||
else:
|
||||
block = self.gram_matrix_mix_sum(P[y == i], P[y == j] if i!=j else None)
|
||||
tr_tr_sums[i, j] = block
|
||||
|
||||
# keep track of these data structures for the test phase
|
||||
self.Ptr = P
|
||||
self.ytr = y
|
||||
self.tr_tr_sums = tr_tr_sums
|
||||
self.counts_inv = counts_inv
|
||||
|
||||
return self
|
||||
|
||||
|
||||
def aggregate(self, posteriors: np.ndarray):
|
||||
Ptr = self.Ptr
|
||||
Pte = posteriors
|
||||
y = self.ytr
|
||||
tr_tr_sums = self.tr_tr_sums
|
||||
|
||||
M, nD = Pte.shape
|
||||
Minv = (1/M) # t in the paper
|
||||
n = Ptr.shape[1]
|
||||
|
||||
# becomes a constant that does not affect the optimization, no need to compute it
|
||||
# partC = 0.5*np.log(self.gram_matrix_mix_sum(Pte) * Kinv * Kinv)
|
||||
|
||||
# tr_te_sums corresponds to \overline{a}*(1/Li)*(1/M) in the paper (note the constants
|
||||
# are already aggregated to tr_te_sums, so these multiplications are not carried out
|
||||
# at each iteration of the optimization phase)
|
||||
tr_te_sums = np.zeros(shape=n, dtype=float)
|
||||
for i in range(n):
|
||||
tr_te_sums[i] = self.gram_matrix_mix_sum(Ptr[y==i], Pte)
|
||||
|
||||
def divergence(alpha):
|
||||
# called \overline{r} in the paper
|
||||
alpha_ratio = alpha * self.counts_inv
|
||||
|
||||
# recal that tr_te_sums already accounts for the constant terms (1/Li)*(1/M)
|
||||
partA = -np.log((alpha_ratio @ tr_te_sums) * Minv)
|
||||
partB = 0.5 * np.log(alpha_ratio @ tr_tr_sums @ alpha_ratio)
|
||||
return partA + partB #+ partC
|
||||
|
||||
return F.optim_minimize(divergence, n)
|
||||
|
||||
|
|
@ -29,7 +29,7 @@ class QuaNetTrainer(BaseQuantifier):
|
|||
>>>
|
||||
>>> # load the kindle dataset as text, and convert words to numerical indexes
|
||||
>>> dataset = qp.datasets.fetch_reviews('kindle', pickle=True)
|
||||
>>> qp.domains.preprocessing.index(dataset, min_df=5, inplace=True)
|
||||
>>> qp.train.preprocessing.index(dataset, min_df=5, inplace=True)
|
||||
>>>
|
||||
>>> # the text classifier is a CNN trained by NeuralClassifierTrainer
|
||||
>>> cnn = CNNnet(dataset.vocabulary_size, dataset.n_classes)
|
||||
|
|
@ -194,7 +194,7 @@ class QuaNetTrainer(BaseQuantifier):
|
|||
label_predictions = np.argmax(posteriors, axis=-1)
|
||||
prevs_estim = []
|
||||
for quantifier in self.quantifiers.values():
|
||||
predictions = posteriors if isinstance(quantifier, AggregativeProbabilisticQuantifier) else label_predictions
|
||||
predictions = posteriors if isinstance(quantifier, AggregativeSoftQuantifier) else label_predictions
|
||||
prevs_estim.extend(quantifier.aggregate(predictions))
|
||||
|
||||
# there is no real need for adding static estims like the TPR or FPR from training since those are constant
|
||||
|
|
@ -0,0 +1,261 @@
|
|||
from abc import abstractmethod
|
||||
|
||||
import numpy as np
|
||||
from sklearn.base import BaseEstimator
|
||||
import quapy as qp
|
||||
import quapy.functional as F
|
||||
from quapy.data import LabelledCollection
|
||||
from quapy.method.aggregative import BinaryAggregativeQuantifier
|
||||
|
||||
|
||||
class ThresholdOptimization(BinaryAggregativeQuantifier):
|
||||
"""
|
||||
Abstract class of Threshold Optimization variants for :class:`ACC` as proposed by
|
||||
`Forman 2006 <https://dl.acm.org/doi/abs/10.1145/1150402.1150423>`_ and
|
||||
`Forman 2008 <https://link.springer.com/article/10.1007/s10618-008-0097-y>`_.
|
||||
The goal is to bring improved stability to the denominator of the adjustment.
|
||||
The different variants are based on different heuristics for choosing a decision threshold
|
||||
that would allow for more true positives and many more false positives, on the grounds this
|
||||
would deliver larger denominators.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a classifier
|
||||
:param val_split: indicates the proportion of data to be used as a stratified held-out validation set in which the
|
||||
misclassification rates are to be estimated.
|
||||
This parameter can be indicated as a real value (between 0 and 1), representing a proportion of
|
||||
validation data, or as an integer, indicating that the misclassification rates should be estimated via
|
||||
`k`-fold cross validation (this integer stands for the number of folds `k`, defaults 5), or as a
|
||||
:class:`quapy.data.base.LabelledCollection` (the split itself).
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=5, n_jobs=None):
|
||||
self.classifier = classifier
|
||||
self.val_split = val_split
|
||||
self.n_jobs = qp._get_njobs(n_jobs)
|
||||
|
||||
@abstractmethod
|
||||
def condition(self, tpr, fpr) -> float:
|
||||
"""
|
||||
Implements the criterion according to which the threshold should be selected.
|
||||
This function should return the (float) score to be minimized.
|
||||
|
||||
:param tpr: float, true positive rate
|
||||
:param fpr: float, false positive rate
|
||||
:return: float, a score for the given `tpr` and `fpr`
|
||||
"""
|
||||
...
|
||||
|
||||
def discard(self, tpr, fpr) -> bool:
|
||||
"""
|
||||
Indicates whether a combination of tpr and fpr should be discarded
|
||||
|
||||
:param tpr: float, true positive rate
|
||||
:param fpr: float, false positive rate
|
||||
:return: true if the combination is to be discarded, false otherwise
|
||||
"""
|
||||
return (tpr - fpr) == 0
|
||||
|
||||
|
||||
def _eval_candidate_thresholds(self, decision_scores, y):
|
||||
"""
|
||||
Seeks for the best `tpr` and `fpr` according to the score obtained at different
|
||||
decision thresholds. The scoring function is implemented in function `_condition`.
|
||||
|
||||
:param decision_scores: array-like with the classification scores
|
||||
:param y: predicted labels for the validation set (or for the training set via `k`-fold cross validation)
|
||||
:return: best `tpr` and `fpr` and `threshold` according to `_condition`
|
||||
"""
|
||||
candidate_thresholds = np.unique(decision_scores)
|
||||
|
||||
candidates = []
|
||||
scores = []
|
||||
for candidate_threshold in candidate_thresholds:
|
||||
y_ = self.classes_[1 * (decision_scores >= candidate_threshold)]
|
||||
TP, FP, FN, TN = self._compute_table(y, y_)
|
||||
tpr = self._compute_tpr(TP, FN)
|
||||
fpr = self._compute_fpr(FP, TN)
|
||||
if not self.discard(tpr, fpr):
|
||||
candidate_score = self.condition(tpr, fpr)
|
||||
candidates.append([tpr, fpr, candidate_threshold])
|
||||
scores.append(candidate_score)
|
||||
|
||||
if len(candidates) == 0:
|
||||
# if no candidate gives rise to a valid combination of tpr and fpr, this method defaults to the standard
|
||||
# classify & count; this is akin to assign tpr=1, fpr=0, threshold=0
|
||||
tpr, fpr, threshold = 1, 0, 0
|
||||
candidates.append([tpr, fpr, threshold])
|
||||
scores.append(0)
|
||||
|
||||
candidates = np.asarray(candidates)
|
||||
candidates = candidates[np.argsort(scores)] # sort candidates by candidate_score
|
||||
|
||||
return candidates
|
||||
|
||||
def aggregate_with_threshold(self, classif_predictions, tprs, fprs, thresholds):
|
||||
# This function performs the adjusted count for given tpr, fpr, and threshold.
|
||||
# Note that, due to broadcasting, tprs, fprs, and thresholds could be arrays of length > 1
|
||||
prevs_estims = np.mean(classif_predictions[:, None] >= thresholds, axis=0)
|
||||
prevs_estims = (prevs_estims - fprs) / (tprs - fprs)
|
||||
prevs_estims = F.as_binary_prevalence(prevs_estims, clip_if_necessary=True)
|
||||
return prevs_estims.squeeze()
|
||||
|
||||
def _compute_table(self, y, y_):
|
||||
TP = np.logical_and(y == y_, y == self.pos_label).sum()
|
||||
FP = np.logical_and(y != y_, y == self.neg_label).sum()
|
||||
FN = np.logical_and(y != y_, y == self.pos_label).sum()
|
||||
TN = np.logical_and(y == y_, y == self.neg_label).sum()
|
||||
return TP, FP, FN, TN
|
||||
|
||||
def _compute_tpr(self, TP, FP):
|
||||
if TP + FP == 0:
|
||||
return 1
|
||||
return TP / (TP + FP)
|
||||
|
||||
def _compute_fpr(self, FP, TN):
|
||||
if FP + TN == 0:
|
||||
return 0
|
||||
return FP / (FP + TN)
|
||||
|
||||
def aggregation_fit(self, classif_predictions: LabelledCollection, data: LabelledCollection):
|
||||
decision_scores, y = classif_predictions.Xy
|
||||
# the standard behavior is to keep the best threshold only
|
||||
self.tpr, self.fpr, self.threshold = self._eval_candidate_thresholds(decision_scores, y)[0]
|
||||
return self
|
||||
|
||||
def aggregate(self, classif_predictions: np.ndarray):
|
||||
# the standard behavior is to compute the adjusted count using the best threshold found
|
||||
return self.aggregate_with_threshold(classif_predictions, self.tpr, self.fpr, self.threshold)
|
||||
|
||||
|
||||
class T50(ThresholdOptimization):
|
||||
"""
|
||||
Threshold Optimization variant for :class:`ACC` as proposed by
|
||||
`Forman 2006 <https://dl.acm.org/doi/abs/10.1145/1150402.1150423>`_ and
|
||||
`Forman 2008 <https://link.springer.com/article/10.1007/s10618-008-0097-y>`_ that looks
|
||||
for the threshold that makes `tpr` closest to 0.5.
|
||||
The goal is to bring improved stability to the denominator of the adjustment.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a classifier
|
||||
:param val_split: indicates the proportion of data to be used as a stratified held-out validation set in which the
|
||||
misclassification rates are to be estimated.
|
||||
This parameter can be indicated as a real value (between 0 and 1), representing a proportion of
|
||||
validation data, or as an integer, indicating that the misclassification rates should be estimated via
|
||||
`k`-fold cross validation (this integer stands for the number of folds `k`, defaults 5), or as a
|
||||
:class:`quapy.data.base.LabelledCollection` (the split itself).
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=5):
|
||||
super().__init__(classifier, val_split)
|
||||
|
||||
def condition(self, tpr, fpr) -> float:
|
||||
return abs(tpr - 0.5)
|
||||
|
||||
|
||||
class MAX(ThresholdOptimization):
|
||||
"""
|
||||
Threshold Optimization variant for :class:`ACC` as proposed by
|
||||
`Forman 2006 <https://dl.acm.org/doi/abs/10.1145/1150402.1150423>`_ and
|
||||
`Forman 2008 <https://link.springer.com/article/10.1007/s10618-008-0097-y>`_ that looks
|
||||
for the threshold that maximizes `tpr-fpr`.
|
||||
The goal is to bring improved stability to the denominator of the adjustment.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a classifier
|
||||
:param val_split: indicates the proportion of data to be used as a stratified held-out validation set in which the
|
||||
misclassification rates are to be estimated.
|
||||
This parameter can be indicated as a real value (between 0 and 1), representing a proportion of
|
||||
validation data, or as an integer, indicating that the misclassification rates should be estimated via
|
||||
`k`-fold cross validation (this integer stands for the number of folds `k`, defaults 5), or as a
|
||||
:class:`quapy.data.base.LabelledCollection` (the split itself).
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=5):
|
||||
super().__init__(classifier, val_split)
|
||||
|
||||
def condition(self, tpr, fpr) -> float:
|
||||
# MAX strives to maximize (tpr - fpr), which is equivalent to minimize (fpr - tpr)
|
||||
return (fpr - tpr)
|
||||
|
||||
|
||||
class X(ThresholdOptimization):
|
||||
"""
|
||||
Threshold Optimization variant for :class:`ACC` as proposed by
|
||||
`Forman 2006 <https://dl.acm.org/doi/abs/10.1145/1150402.1150423>`_ and
|
||||
`Forman 2008 <https://link.springer.com/article/10.1007/s10618-008-0097-y>`_ that looks
|
||||
for the threshold that yields `tpr=1-fpr`.
|
||||
The goal is to bring improved stability to the denominator of the adjustment.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a classifier
|
||||
:param val_split: indicates the proportion of data to be used as a stratified held-out validation set in which the
|
||||
misclassification rates are to be estimated.
|
||||
This parameter can be indicated as a real value (between 0 and 1), representing a proportion of
|
||||
validation data, or as an integer, indicating that the misclassification rates should be estimated via
|
||||
`k`-fold cross validation (this integer stands for the number of folds `k`, defaults 5), or as a
|
||||
:class:`quapy.data.base.LabelledCollection` (the split itself).
|
||||
"""
|
||||
|
||||
def __init__(self, classifier: BaseEstimator, val_split=5):
|
||||
super().__init__(classifier, val_split)
|
||||
|
||||
def condition(self, tpr, fpr) -> float:
|
||||
return abs(1 - (tpr + fpr))
|
||||
|
||||
|
||||
class MS(ThresholdOptimization):
|
||||
"""
|
||||
Median Sweep. Threshold Optimization variant for :class:`ACC` as proposed by
|
||||
`Forman 2006 <https://dl.acm.org/doi/abs/10.1145/1150402.1150423>`_ and
|
||||
`Forman 2008 <https://link.springer.com/article/10.1007/s10618-008-0097-y>`_ that generates
|
||||
class prevalence estimates for all decision thresholds and returns the median of them all.
|
||||
The goal is to bring improved stability to the denominator of the adjustment.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a classifier
|
||||
:param val_split: indicates the proportion of data to be used as a stratified held-out validation set in which the
|
||||
misclassification rates are to be estimated.
|
||||
This parameter can be indicated as a real value (between 0 and 1), representing a proportion of
|
||||
validation data, or as an integer, indicating that the misclassification rates should be estimated via
|
||||
`k`-fold cross validation (this integer stands for the number of folds `k`, defaults 5), or as a
|
||||
:class:`quapy.data.base.LabelledCollection` (the split itself).
|
||||
"""
|
||||
def __init__(self, classifier: BaseEstimator, val_split=5):
|
||||
super().__init__(classifier, val_split)
|
||||
|
||||
def condition(self, tpr, fpr) -> float:
|
||||
return 1
|
||||
|
||||
def aggregation_fit(self, classif_predictions: LabelledCollection, data: LabelledCollection):
|
||||
decision_scores, y = classif_predictions.Xy
|
||||
# keeps all candidates
|
||||
tprs_fprs_thresholds = self._eval_candidate_thresholds(decision_scores, y)
|
||||
self.tprs = tprs_fprs_thresholds[:, 0]
|
||||
self.fprs = tprs_fprs_thresholds[:, 1]
|
||||
self.thresholds = tprs_fprs_thresholds[:, 2]
|
||||
return self
|
||||
|
||||
def aggregate(self, classif_predictions: np.ndarray):
|
||||
prevalences = self.aggregate_with_threshold(classif_predictions, self.tprs, self.fprs, self.thresholds)
|
||||
if prevalences.ndim==2:
|
||||
prevalences = np.median(prevalences, axis=0)
|
||||
return prevalences
|
||||
|
||||
|
||||
class MS2(MS):
|
||||
"""
|
||||
Median Sweep 2. Threshold Optimization variant for :class:`ACC` as proposed by
|
||||
`Forman 2006 <https://dl.acm.org/doi/abs/10.1145/1150402.1150423>`_ and
|
||||
`Forman 2008 <https://link.springer.com/article/10.1007/s10618-008-0097-y>`_ that generates
|
||||
class prevalence estimates for all decision thresholds and returns the median of for cases in
|
||||
which `tpr-fpr>0.25`
|
||||
The goal is to bring improved stability to the denominator of the adjustment.
|
||||
|
||||
:param classifier: a sklearn's Estimator that generates a classifier
|
||||
:param val_split: indicates the proportion of data to be used as a stratified held-out validation set in which the
|
||||
misclassification rates are to be estimated.
|
||||
This parameter can be indicated as a real value (between 0 and 1), representing a proportion of
|
||||
validation data, or as an integer, indicating that the misclassification rates should be estimated via
|
||||
`k`-fold cross validation (this integer stands for the number of folds `k`, defaults 5), or as a
|
||||
:class:`quapy.data.base.LabelledCollection` (the split itself).
|
||||
"""
|
||||
def __init__(self, classifier: BaseEstimator, val_split=5):
|
||||
super().__init__(classifier, val_split)
|
||||
|
||||
def discard(self, tpr, fpr) -> bool:
|
||||
return (tpr-fpr) <= 0.25
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -63,7 +63,7 @@ def newOneVsAll(binary_quantifier, n_jobs=None):
|
|||
return OneVsAllGeneric(binary_quantifier, n_jobs)
|
||||
|
||||
|
||||
class OneVsAllGeneric(OneVsAll,BaseQuantifier):
|
||||
class OneVsAllGeneric(OneVsAll, BaseQuantifier):
|
||||
"""
|
||||
Allows any binary quantifier to perform quantification on single-label datasets. The method maintains one binary
|
||||
quantifier for each class, and then l1-normalizes the outputs so that the class prevelence values sum up to 1.
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
import itertools
|
||||
from copy import deepcopy
|
||||
from typing import Union
|
||||
import numpy as np
|
||||
|
|
@ -10,20 +11,183 @@ import quapy as qp
|
|||
from quapy import functional as F
|
||||
from quapy.data import LabelledCollection
|
||||
from quapy.model_selection import GridSearchQ
|
||||
from quapy.method.base import BaseQuantifier, BinaryQuantifier
|
||||
from quapy.method.aggregative import CC, ACC, PACC, HDy, EMQ, AggregativeQuantifier
|
||||
|
||||
try:
|
||||
from . import neural
|
||||
from . import _neural
|
||||
except ModuleNotFoundError:
|
||||
neural = None
|
||||
from .base import BaseQuantifier
|
||||
from quapy.method.aggregative import CC, ACC, PACC, HDy, EMQ
|
||||
_neural = None
|
||||
|
||||
if neural:
|
||||
QuaNet = neural.QuaNetTrainer
|
||||
|
||||
if _neural:
|
||||
QuaNet = _neural.QuaNetTrainer
|
||||
else:
|
||||
QuaNet = "QuaNet is not available due to missing torch package"
|
||||
|
||||
|
||||
class MedianEstimator2(BinaryQuantifier):
|
||||
"""
|
||||
This method is a meta-quantifier that returns, as the estimated class prevalence values, the median of the
|
||||
estimation returned by differently (hyper)parameterized base quantifiers.
|
||||
The median of unit-vectors is only guaranteed to be a unit-vector for n=2 dimensions,
|
||||
i.e., in cases of binary quantification.
|
||||
|
||||
:param base_quantifier: the base, binary quantifier
|
||||
:param random_state: a seed to be set before fitting any base quantifier (default None)
|
||||
:param param_grid: the grid or parameters towards which the median will be computed
|
||||
:param n_jobs: number of parllel workes
|
||||
"""
|
||||
def __init__(self, base_quantifier: BinaryQuantifier, param_grid: dict, random_state=None, n_jobs=None):
|
||||
self.base_quantifier = base_quantifier
|
||||
self.param_grid = param_grid
|
||||
self.random_state = random_state
|
||||
self.n_jobs = qp._get_njobs(n_jobs)
|
||||
|
||||
def get_params(self, deep=True):
|
||||
return self.base_quantifier.get_params(deep)
|
||||
|
||||
def set_params(self, **params):
|
||||
self.base_quantifier.set_params(**params)
|
||||
|
||||
def _delayed_fit(self, args):
|
||||
with qp.util.temp_seed(self.random_state):
|
||||
params, training = args
|
||||
model = deepcopy(self.base_quantifier)
|
||||
model.set_params(**params)
|
||||
model.fit(training)
|
||||
return model
|
||||
|
||||
def fit(self, training: LabelledCollection):
|
||||
self._check_binary(training, self.__class__.__name__)
|
||||
|
||||
configs = qp.model_selection.expand_grid(self.param_grid)
|
||||
self.models = qp.util.parallel(
|
||||
self._delayed_fit,
|
||||
((params, training) for params in configs),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs
|
||||
)
|
||||
return self
|
||||
|
||||
def _delayed_predict(self, args):
|
||||
model, instances = args
|
||||
return model.quantify(instances)
|
||||
|
||||
def quantify(self, instances):
|
||||
prev_preds = qp.util.parallel(
|
||||
self._delayed_predict,
|
||||
((model, instances) for model in self.models),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs
|
||||
)
|
||||
prev_preds = np.asarray(prev_preds)
|
||||
return np.median(prev_preds, axis=0)
|
||||
|
||||
|
||||
class MedianEstimator(BinaryQuantifier):
|
||||
"""
|
||||
This method is a meta-quantifier that returns, as the estimated class prevalence values, the median of the
|
||||
estimation returned by differently (hyper)parameterized base quantifiers.
|
||||
The median of unit-vectors is only guaranteed to be a unit-vector for n=2 dimensions,
|
||||
i.e., in cases of binary quantification.
|
||||
|
||||
:param base_quantifier: the base, binary quantifier
|
||||
:param random_state: a seed to be set before fitting any base quantifier (default None)
|
||||
:param param_grid: the grid or parameters towards which the median will be computed
|
||||
:param n_jobs: number of parllel workes
|
||||
"""
|
||||
def __init__(self, base_quantifier: BinaryQuantifier, param_grid: dict, random_state=None, n_jobs=None):
|
||||
self.base_quantifier = base_quantifier
|
||||
self.param_grid = param_grid
|
||||
self.random_state = random_state
|
||||
self.n_jobs = qp._get_njobs(n_jobs)
|
||||
|
||||
def get_params(self, deep=True):
|
||||
return self.base_quantifier.get_params(deep)
|
||||
|
||||
def set_params(self, **params):
|
||||
self.base_quantifier.set_params(**params)
|
||||
|
||||
def _delayed_fit(self, args):
|
||||
with qp.util.temp_seed(self.random_state):
|
||||
params, training = args
|
||||
model = deepcopy(self.base_quantifier)
|
||||
model.set_params(**params)
|
||||
model.fit(training)
|
||||
return model
|
||||
|
||||
def _delayed_fit_classifier(self, args):
|
||||
with qp.util.temp_seed(self.random_state):
|
||||
cls_params, training = args
|
||||
model = deepcopy(self.base_quantifier)
|
||||
model.set_params(**cls_params)
|
||||
predictions = model.classifier_fit_predict(training, predict_on=model.val_split)
|
||||
return (model, predictions)
|
||||
|
||||
def _delayed_fit_aggregation(self, args):
|
||||
with qp.util.temp_seed(self.random_state):
|
||||
((model, predictions), q_params), training = args
|
||||
model = deepcopy(model)
|
||||
model.set_params(**q_params)
|
||||
model.aggregation_fit(predictions, training)
|
||||
return model
|
||||
|
||||
|
||||
def fit(self, training: LabelledCollection):
|
||||
self._check_binary(training, self.__class__.__name__)
|
||||
|
||||
if isinstance(self.base_quantifier, AggregativeQuantifier):
|
||||
cls_configs, q_configs = qp.model_selection.group_params(self.param_grid)
|
||||
|
||||
if len(cls_configs) > 1:
|
||||
models_preds = qp.util.parallel(
|
||||
self._delayed_fit_classifier,
|
||||
((params, training) for params in cls_configs),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs,
|
||||
asarray=False
|
||||
)
|
||||
else:
|
||||
model = self.base_quantifier
|
||||
model.set_params(**cls_configs[0])
|
||||
predictions = model.classifier_fit_predict(training, predict_on=model.val_split)
|
||||
models_preds = [(model, predictions)]
|
||||
|
||||
self.models = qp.util.parallel(
|
||||
self._delayed_fit_aggregation,
|
||||
((setup, training) for setup in itertools.product(models_preds, q_configs)),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs,
|
||||
asarray=False
|
||||
)
|
||||
else:
|
||||
configs = qp.model_selection.expand_grid(self.param_grid)
|
||||
self.models = qp.util.parallel(
|
||||
self._delayed_fit,
|
||||
((params, training) for params in configs),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs,
|
||||
asarray=False
|
||||
)
|
||||
return self
|
||||
|
||||
def _delayed_predict(self, args):
|
||||
model, instances = args
|
||||
return model.quantify(instances)
|
||||
|
||||
def quantify(self, instances):
|
||||
prev_preds = qp.util.parallel(
|
||||
self._delayed_predict,
|
||||
((model, instances) for model in self.models),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs,
|
||||
asarray=False
|
||||
)
|
||||
prev_preds = np.asarray(prev_preds)
|
||||
return np.median(prev_preds, axis=0)
|
||||
|
||||
|
||||
class Ensemble(BaseQuantifier):
|
||||
VALID_POLICIES = {'ave', 'ptr', 'ds'} | qp.error.QUANTIFICATION_ERROR_NAMES
|
||||
|
||||
|
|
@ -94,9 +258,10 @@ class Ensemble(BaseQuantifier):
|
|||
print('[Ensemble]' + msg)
|
||||
|
||||
def fit(self, data: qp.data.LabelledCollection, val_split: Union[qp.data.LabelledCollection, float] = None):
|
||||
self._sout('Fit')
|
||||
|
||||
if self.policy == 'ds' and not data.binary:
|
||||
raise ValueError(f'ds policy is only defined for binary quantification, but this dataset is not binary')
|
||||
|
||||
if val_split is None:
|
||||
val_split = self.val_split
|
||||
|
||||
|
|
@ -119,6 +284,7 @@ class Ensemble(BaseQuantifier):
|
|||
self.ensemble = qp.util.parallel(
|
||||
_delayed_new_instance,
|
||||
tqdm(args, desc='fitting ensamble', total=self.size) if self.verbose else args,
|
||||
asarray=False,
|
||||
n_jobs=self.n_jobs)
|
||||
|
||||
# static selection policy (the name of a quantification-oriented error function to minimize)
|
||||
|
|
@ -200,30 +366,31 @@ class Ensemble(BaseQuantifier):
|
|||
|
||||
def _ds_policy_get_posteriors(self, data: LabelledCollection):
|
||||
"""
|
||||
In the original article, this procedure is not described in a sufficient level of detail. The paper only says
|
||||
In the original article, there are some aspects regarding this method that are not mentioned. The paper says
|
||||
that the distribution of posterior probabilities from training and test examples is compared by means of the
|
||||
Hellinger Distance. However, how these posterior probabilities are generated is not specified. In the article,
|
||||
a Logistic Regressor (LR) is used as the classifier device and that could be used for this purpose. However, in
|
||||
general, a Quantifier is not necessarily an instance of Aggreggative Probabilistic Quantifiers, and so, that the
|
||||
quantifier builds on top of a probabilistic classifier cannot be given for granted. Additionally, it would not
|
||||
be correct to generate the posterior probabilities for training documents that have concurred in training the
|
||||
be correct to generate the posterior probabilities for training instances that have concurred in training the
|
||||
classifier that generates them.
|
||||
|
||||
This function thus generates the posterior probabilities for all training documents in a cross-validation way,
|
||||
using a LR with hyperparameters that have previously been optimized via grid search in 5FCV.
|
||||
:return P,f, where P is a ndarray containing the posterior probabilities of the training data, generated via
|
||||
cross-validation and using an optimized LR, and the function to be used in order to generate posterior
|
||||
probabilities for test instances.
|
||||
using LR with hyperparameters that have previously been optimized via grid search in 5FCV.
|
||||
|
||||
:param data: a LabelledCollection
|
||||
:return: (P,f,) where P is an ndarray containing the posterior probabilities of the training data, generated via
|
||||
cross-validation and using an optimized LR, and the function to be used in order to generate posterior
|
||||
probabilities for test instances.
|
||||
"""
|
||||
|
||||
X, y = data.Xy
|
||||
lr_base = LogisticRegression(class_weight='balanced', max_iter=1000)
|
||||
|
||||
optim = GridSearchCV(
|
||||
lr_base, param_grid={'C': np.logspace(-4, 4, 9)}, cv=5, n_jobs=self.n_jobs, refit=True
|
||||
).fit(X, y)
|
||||
param_grid = {'C': np.logspace(-4, 4, 9)}
|
||||
optim = GridSearchCV(lr_base, param_grid=param_grid, cv=5, n_jobs=self.n_jobs, refit=True).fit(X, y)
|
||||
|
||||
posteriors = cross_val_predict(
|
||||
optim.best_estimator_, X, y, cv=5, n_jobs=self.n_jobs, method='predict_proba'
|
||||
)
|
||||
posteriors = cross_val_predict(optim.best_estimator_, X, y, cv=5, n_jobs=self.n_jobs, method='predict_proba')
|
||||
posteriors_generator = optim.best_estimator_.predict_proba
|
||||
|
||||
return posteriors, posteriors_generator
|
||||
|
|
@ -294,8 +461,10 @@ def _delayed_new_instance(args):
|
|||
|
||||
tr_prevalence = sample.prevalence()
|
||||
tr_distribution = get_probability_distribution(posteriors[sample_index]) if (posteriors is not None) else None
|
||||
|
||||
if verbose:
|
||||
print(f'\t\--fit-ended for prev {F.strprev(prev)}')
|
||||
|
||||
return (model, tr_prevalence, tr_distribution, sample if keep_samples else None)
|
||||
|
||||
|
||||
|
|
@ -306,8 +475,9 @@ def _delayed_quantify(args):
|
|||
|
||||
def _draw_simplex(ndim, min_val, max_trials=100):
|
||||
"""
|
||||
returns a uniform sampling from the ndim-dimensional simplex but guarantees that all dimensions
|
||||
Returns a uniform sampling from the ndim-dimensional simplex but guarantees that all dimensions
|
||||
are >= min_class_prev (for min_val>0, this makes the sampling not truly uniform)
|
||||
|
||||
:param ndim: number of dimensions of the simplex
|
||||
:param min_val: minimum class prevalence allowed. If less than 1/ndim a ValueError will be throw since
|
||||
there is no possible solution.
|
||||
|
|
|
|||
|
|
@ -1,5 +1,10 @@
|
|||
from typing import Union, Callable
|
||||
import numpy as np
|
||||
|
||||
from quapy.functional import get_divergence
|
||||
from quapy.data import LabelledCollection
|
||||
from .base import BaseQuantifier
|
||||
from quapy.method.base import BaseQuantifier, BinaryQuantifier
|
||||
import quapy.functional as F
|
||||
|
||||
|
||||
class MaximumLikelihoodPrevalenceEstimation(BaseQuantifier):
|
||||
|
|
@ -33,3 +38,126 @@ class MaximumLikelihoodPrevalenceEstimation(BaseQuantifier):
|
|||
"""
|
||||
return self.estimated_prevalence
|
||||
|
||||
|
||||
class DMx(BaseQuantifier):
|
||||
"""
|
||||
Generic Distribution Matching quantifier for binary or multiclass quantification based on the space of covariates.
|
||||
This implementation takes the number of bins, the divergence, and the possibility to work on CDF as hyperparameters.
|
||||
|
||||
:param nbins: number of bins used to discretize the distributions (default 8)
|
||||
:param divergence: a string representing a divergence measure (currently, "HD" and "topsoe" are implemented)
|
||||
or a callable function taking two ndarrays of the same dimension as input (default "HD", meaning Hellinger
|
||||
Distance)
|
||||
:param cdf: whether to use CDF instead of PDF (default False)
|
||||
:param n_jobs: number of parallel workers (default None)
|
||||
"""
|
||||
|
||||
def __init__(self, nbins=8, divergence: Union[str, Callable]='HD', cdf=False, search='optim_minimize', n_jobs=None):
|
||||
self.nbins = nbins
|
||||
self.divergence = divergence
|
||||
self.cdf = cdf
|
||||
self.search = search
|
||||
self.n_jobs = n_jobs
|
||||
|
||||
@classmethod
|
||||
def HDx(cls, n_jobs=None):
|
||||
"""
|
||||
`Hellinger Distance x <https://www.sciencedirect.com/science/article/pii/S0020025512004069>`_ (HDx).
|
||||
HDx is a method for training binary quantifiers, that models quantification as the problem of
|
||||
minimizing the average divergence (in terms of the Hellinger Distance) across the feature-specific normalized
|
||||
histograms of two representations, one for the unlabelled examples, and another generated from the training
|
||||
examples as a mixture model of the class-specific representations. The parameters of the mixture thus represent
|
||||
the estimates of the class prevalence values.
|
||||
|
||||
The method computes all matchings for nbins in [10, 20, ..., 110] and reports the mean of the median.
|
||||
The best prevalence is searched via linear search, from 0 to 1 stepping by 0.01.
|
||||
|
||||
:param n_jobs: number of parallel workers
|
||||
:return: an instance of this class setup to mimick the performance of the HDx as originally proposed by
|
||||
González-Castro, Alaiz-Rodríguez, Alegre (2013)
|
||||
"""
|
||||
from quapy.method.meta import MedianEstimator
|
||||
|
||||
dmx = DMx(divergence='HD', cdf=False, search='linear_search')
|
||||
nbins = {'nbins': np.linspace(10, 110, 11, dtype=int)}
|
||||
hdx = MedianEstimator(base_quantifier=dmx, param_grid=nbins, n_jobs=n_jobs)
|
||||
return hdx
|
||||
|
||||
def __get_distributions(self, X):
|
||||
|
||||
histograms = []
|
||||
for feat_idx in range(self.nfeats):
|
||||
feature = X[:, feat_idx]
|
||||
feat_range = self.feat_ranges[feat_idx]
|
||||
hist = np.histogram(feature, bins=self.nbins, range=feat_range)[0]
|
||||
norm_hist = hist / hist.sum()
|
||||
histograms.append(norm_hist)
|
||||
distributions = np.vstack(histograms)
|
||||
|
||||
if self.cdf:
|
||||
distributions = np.cumsum(distributions, axis=1)
|
||||
|
||||
return distributions
|
||||
|
||||
def fit(self, data: LabelledCollection):
|
||||
"""
|
||||
Generates the validation distributions out of the training data (covariates).
|
||||
The validation distributions have shape `(n, nfeats, nbins)`, with `n` the number of classes, `nfeats`
|
||||
the number of features, and `nbins` the number of bins.
|
||||
In particular, let `V` be the validation distributions; then `di=V[i]` are the distributions obtained from
|
||||
training data labelled with class `i`; while `dij = di[j]` is the discrete distribution for feature j in
|
||||
training data labelled with class `i`, and `dij[k]` is the fraction of instances with a value in the `k`-th bin.
|
||||
|
||||
:param data: the training set
|
||||
"""
|
||||
X, y = data.Xy
|
||||
|
||||
self.nfeats = X.shape[1]
|
||||
self.feat_ranges = _get_features_range(X)
|
||||
|
||||
self.validation_distribution = np.asarray(
|
||||
[self.__get_distributions(X[y==cat]) for cat in range(data.n_classes)]
|
||||
)
|
||||
|
||||
return self
|
||||
|
||||
def quantify(self, instances):
|
||||
"""
|
||||
Searches for the mixture model parameter (the sought prevalence values) that yields a validation distribution
|
||||
(the mixture) that best matches the test distribution, in terms of the divergence measure of choice.
|
||||
The matching is computed as the average dissimilarity (in terms of the dissimilarity measure of choice)
|
||||
between all feature-specific discrete distributions.
|
||||
|
||||
:param instances: instances in the sample
|
||||
:return: a vector of class prevalence estimates
|
||||
"""
|
||||
|
||||
assert instances.shape[1] == self.nfeats, f'wrong shape; expected {self.nfeats}, found {instances.shape[1]}'
|
||||
|
||||
test_distribution = self.__get_distributions(instances)
|
||||
divergence = get_divergence(self.divergence)
|
||||
n_classes, n_feats, nbins = self.validation_distribution.shape
|
||||
def loss(prev):
|
||||
prev = np.expand_dims(prev, axis=0)
|
||||
mixture_distribution = (prev @ self.validation_distribution.reshape(n_classes,-1)).reshape(n_feats, -1)
|
||||
divs = [divergence(test_distribution[feat], mixture_distribution[feat]) for feat in range(n_feats)]
|
||||
return np.mean(divs)
|
||||
|
||||
return F.argmin_prevalence(loss, n_classes, method=self.search)
|
||||
|
||||
|
||||
|
||||
def _get_features_range(X):
|
||||
feat_ranges = []
|
||||
ncols = X.shape[1]
|
||||
for col_idx in range(ncols):
|
||||
feature = X[:,col_idx]
|
||||
feat_ranges.append((np.min(feature), np.max(feature)))
|
||||
return feat_ranges
|
||||
|
||||
|
||||
#---------------------------------------------------------------
|
||||
# aliases
|
||||
#---------------------------------------------------------------
|
||||
|
||||
DistributionMatchingX = DMx
|
||||
|
|
@ -1,7 +1,9 @@
|
|||
import itertools
|
||||
import signal
|
||||
from copy import deepcopy
|
||||
from enum import Enum
|
||||
from typing import Union, Callable
|
||||
from functools import wraps
|
||||
|
||||
import numpy as np
|
||||
from sklearn import clone
|
||||
|
|
@ -10,10 +12,37 @@ import quapy as qp
|
|||
from quapy import evaluation
|
||||
from quapy.protocol import AbstractProtocol, OnLabelledCollectionProtocol
|
||||
from quapy.data.base import LabelledCollection
|
||||
from quapy.method.aggregative import BaseQuantifier
|
||||
from quapy.method.aggregative import BaseQuantifier, AggregativeQuantifier
|
||||
from quapy.util import timeout
|
||||
from time import time
|
||||
|
||||
|
||||
class Status(Enum):
|
||||
SUCCESS = 1
|
||||
TIMEOUT = 2
|
||||
INVALID = 3
|
||||
ERROR = 4
|
||||
|
||||
|
||||
class ConfigStatus:
|
||||
def __init__(self, params, status, msg=''):
|
||||
self.params = params
|
||||
self.status = status
|
||||
self.msg = msg
|
||||
|
||||
def __str__(self):
|
||||
return f':params:{self.params} :status:{self.status} ' + self.msg
|
||||
|
||||
def __repr__(self):
|
||||
return str(self)
|
||||
|
||||
def success(self):
|
||||
return self.status == Status.SUCCESS
|
||||
|
||||
def failed(self):
|
||||
return self.status != Status.SUCCESS
|
||||
|
||||
|
||||
class GridSearchQ(BaseQuantifier):
|
||||
"""Grid Search optimization targeting a quantification-oriented metric.
|
||||
|
||||
|
|
@ -26,11 +55,14 @@ class GridSearchQ(BaseQuantifier):
|
|||
:param protocol: a sample generation protocol, an instance of :class:`quapy.protocol.AbstractProtocol`
|
||||
:param error: an error function (callable) or a string indicating the name of an error function (valid ones
|
||||
are those in :class:`quapy.error.QUANTIFICATION_ERROR`
|
||||
:param refit: whether or not to refit the model on the whole labelled collection (training+validation) with
|
||||
:param refit: whether to refit the model on the whole labelled collection (training+validation) with
|
||||
the best chosen hyperparameter combination. Ignored if protocol='gen'
|
||||
:param timeout: establishes a timer (in seconds) for each of the hyperparameters configurations being tested.
|
||||
Whenever a run takes longer than this timer, that configuration will be ignored. If all configurations end up
|
||||
being ignored, a TimeoutError exception is raised. If -1 (default) then no time bound is set.
|
||||
:param raise_errors: boolean, if True then raises an exception when a param combination yields any error, if
|
||||
otherwise is False (default), then the combination is marked with an error status, but the process goes on.
|
||||
However, if no configuration yields a valid model, then a ValueError exception will be raised.
|
||||
:param verbose: set to True to get information through the stdout
|
||||
"""
|
||||
|
||||
|
|
@ -42,6 +74,7 @@ class GridSearchQ(BaseQuantifier):
|
|||
refit=True,
|
||||
timeout=-1,
|
||||
n_jobs=None,
|
||||
raise_errors=False,
|
||||
verbose=False):
|
||||
|
||||
self.model = model
|
||||
|
|
@ -50,6 +83,7 @@ class GridSearchQ(BaseQuantifier):
|
|||
self.refit = refit
|
||||
self.timeout = timeout
|
||||
self.n_jobs = qp._get_njobs(n_jobs)
|
||||
self.raise_errors = raise_errors
|
||||
self.verbose = verbose
|
||||
self.__check_error(error)
|
||||
assert isinstance(protocol, AbstractProtocol), 'unknown protocol'
|
||||
|
|
@ -69,6 +103,113 @@ class GridSearchQ(BaseQuantifier):
|
|||
raise ValueError(f'unexpected error type; must either be a callable function or a str representing\n'
|
||||
f'the name of an error function in {qp.error.QUANTIFICATION_ERROR_NAMES}')
|
||||
|
||||
def _prepare_classifier(self, cls_params):
|
||||
model = deepcopy(self.model)
|
||||
|
||||
def job(cls_params):
|
||||
model.set_params(**cls_params)
|
||||
predictions = model.classifier_fit_predict(self._training)
|
||||
return predictions
|
||||
|
||||
predictions, status, took = self._error_handler(job, cls_params)
|
||||
self._sout(f'[classifier fit] hyperparams={cls_params} [took {took:.3f}s]')
|
||||
return model, predictions, status, took
|
||||
|
||||
def _prepare_aggregation(self, args):
|
||||
model, predictions, cls_took, cls_params, q_params = args
|
||||
model = deepcopy(model)
|
||||
params = {**cls_params, **q_params}
|
||||
|
||||
def job(q_params):
|
||||
model.set_params(**q_params)
|
||||
model.aggregation_fit(predictions, self._training)
|
||||
score = evaluation.evaluate(model, protocol=self.protocol, error_metric=self.error)
|
||||
return score
|
||||
|
||||
score, status, aggr_took = self._error_handler(job, q_params)
|
||||
self._print_status(params, score, status, aggr_took)
|
||||
return model, params, score, status, (cls_took+aggr_took)
|
||||
|
||||
def _prepare_nonaggr_model(self, params):
|
||||
model = deepcopy(self.model)
|
||||
|
||||
def job(params):
|
||||
model.set_params(**params)
|
||||
model.fit(self._training)
|
||||
score = evaluation.evaluate(model, protocol=self.protocol, error_metric=self.error)
|
||||
return score
|
||||
|
||||
score, status, took = self._error_handler(job, params)
|
||||
self._print_status(params, score, status, took)
|
||||
return model, params, score, status, took
|
||||
|
||||
def _break_down_fit(self):
|
||||
"""
|
||||
Decides whether to break down the fit phase in two (classifier-fit followed by aggregation-fit).
|
||||
In order to do so, some conditions should be met: a) the quantifier is of type aggregative,
|
||||
b) the set of hyperparameters can be split into two disjoint non-empty groups.
|
||||
|
||||
:return: True if the conditions are met, False otherwise
|
||||
"""
|
||||
if not isinstance(self.model, AggregativeQuantifier):
|
||||
return False
|
||||
cls_configs, q_configs = group_params(self.param_grid)
|
||||
if (len(cls_configs) == 1) or (len(q_configs)==1):
|
||||
return False
|
||||
return True
|
||||
|
||||
def _compute_scores_aggregative(self, training):
|
||||
# break down the set of hyperparameters into two: classifier-specific, quantifier-specific
|
||||
cls_configs, q_configs = group_params(self.param_grid)
|
||||
|
||||
# train all classifiers and get the predictions
|
||||
self._training = training
|
||||
cls_outs = qp.util.parallel(
|
||||
self._prepare_classifier,
|
||||
cls_configs,
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs
|
||||
)
|
||||
|
||||
# filter out classifier configurations that yielded any error
|
||||
success_outs = []
|
||||
for (model, predictions, status, took), cls_config in zip(cls_outs, cls_configs):
|
||||
if status.success():
|
||||
success_outs.append((model, predictions, took, cls_config))
|
||||
else:
|
||||
self.error_collector.append(status)
|
||||
|
||||
if len(success_outs) == 0:
|
||||
raise ValueError('No valid configuration found for the classifier!')
|
||||
|
||||
# explore the quantifier-specific hyperparameters for each valid training configuration
|
||||
aggr_configs = [(*out, q_config) for out, q_config in itertools.product(success_outs, q_configs)]
|
||||
aggr_outs = qp.util.parallel(
|
||||
self._prepare_aggregation,
|
||||
aggr_configs,
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs
|
||||
)
|
||||
|
||||
return aggr_outs
|
||||
|
||||
def _compute_scores_nonaggregative(self, training):
|
||||
configs = expand_grid(self.param_grid)
|
||||
self._training = training
|
||||
scores = qp.util.parallel(
|
||||
self._prepare_nonaggr_model,
|
||||
configs,
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs
|
||||
)
|
||||
return scores
|
||||
|
||||
def _print_status(self, params, score, status, took):
|
||||
if status.success():
|
||||
self._sout(f'hyperparams=[{params}]\t got {self.error.__name__} = {score:.5f} [took {took:.3f}s]')
|
||||
else:
|
||||
self._sout(f'error={status}')
|
||||
|
||||
def fit(self, training: LabelledCollection):
|
||||
""" Learning routine. Fits methods with all combinations of hyperparameters and selects the one minimizing
|
||||
the error metric.
|
||||
|
|
@ -76,97 +217,63 @@ class GridSearchQ(BaseQuantifier):
|
|||
:param training: the training set on which to optimize the hyperparameters
|
||||
:return: self
|
||||
"""
|
||||
params_keys = list(self.param_grid.keys())
|
||||
params_values = list(self.param_grid.values())
|
||||
|
||||
protocol = self.protocol
|
||||
|
||||
self.param_scores_ = {}
|
||||
self.best_score_ = None
|
||||
if self.refit and not isinstance(self.protocol, OnLabelledCollectionProtocol):
|
||||
raise RuntimeWarning(
|
||||
f'"refit" was requested, but the protocol does not implement '
|
||||
f'the {OnLabelledCollectionProtocol.__name__} interface'
|
||||
)
|
||||
|
||||
tinit = time()
|
||||
|
||||
hyper = [dict({k: val[i] for i, k in enumerate(params_keys)}) for val in itertools.product(*params_values)]
|
||||
self._sout(f'starting model selection with {self.n_jobs =}')
|
||||
#pass a seed to parallel so it is set in clild processes
|
||||
scores = qp.util.parallel(
|
||||
self._delayed_eval,
|
||||
((params, training) for params in hyper),
|
||||
seed=qp.environ.get('_R_SEED', None),
|
||||
n_jobs=self.n_jobs
|
||||
)
|
||||
self.error_collector = []
|
||||
|
||||
for params, score, model in scores:
|
||||
if score is not None:
|
||||
self._sout(f'starting model selection with n_jobs={self.n_jobs}')
|
||||
if self._break_down_fit():
|
||||
results = self._compute_scores_aggregative(training)
|
||||
else:
|
||||
results = self._compute_scores_nonaggregative(training)
|
||||
|
||||
self.param_scores_ = {}
|
||||
self.best_score_ = None
|
||||
for model, params, score, status, took in results:
|
||||
if status.success():
|
||||
if self.best_score_ is None or score < self.best_score_:
|
||||
self.best_score_ = score
|
||||
self.best_params_ = params
|
||||
self.best_model_ = model
|
||||
self.param_scores_[str(params)] = score
|
||||
else:
|
||||
self.param_scores_[str(params)] = 'timeout'
|
||||
self.param_scores_[str(params)] = status.status
|
||||
self.error_collector.append(status)
|
||||
|
||||
tend = time()-tinit
|
||||
|
||||
if self.best_score_ is None:
|
||||
raise TimeoutError('no combination of hyperparameters seem to work')
|
||||
raise ValueError('no combination of hyperparameters seemed to work')
|
||||
|
||||
self._sout(f'optimization finished: best params {self.best_params_} (score={self.best_score_:.5f}) '
|
||||
f'[took {tend:.4f}s]')
|
||||
|
||||
no_errors = len(self.error_collector)
|
||||
if no_errors>0:
|
||||
self._sout(f'warning: {no_errors} errors found')
|
||||
for err in self.error_collector:
|
||||
self._sout(f'\t{str(err)}')
|
||||
|
||||
if self.refit:
|
||||
if isinstance(protocol, OnLabelledCollectionProtocol):
|
||||
if isinstance(self.protocol, OnLabelledCollectionProtocol):
|
||||
tinit = time()
|
||||
self._sout(f'refitting on the whole development set')
|
||||
self.best_model_.fit(training + protocol.get_labelled_collection())
|
||||
self.best_model_.fit(training + self.protocol.get_labelled_collection())
|
||||
tend = time() - tinit
|
||||
self.refit_time_ = tend
|
||||
else:
|
||||
raise RuntimeWarning(f'"refit" was requested, but the protocol does not '
|
||||
f'implement the {OnLabelledCollectionProtocol.__name__} interface')
|
||||
# already checked
|
||||
raise RuntimeWarning(f'the model cannot be refit on the whole dataset')
|
||||
|
||||
return self
|
||||
|
||||
def _delayed_eval(self, args):
|
||||
params, training = args
|
||||
|
||||
protocol = self.protocol
|
||||
error = self.error
|
||||
|
||||
if self.timeout > 0:
|
||||
def handler(signum, frame):
|
||||
raise TimeoutError()
|
||||
|
||||
signal.signal(signal.SIGALRM, handler)
|
||||
|
||||
tinit = time()
|
||||
|
||||
if self.timeout > 0:
|
||||
signal.alarm(self.timeout)
|
||||
|
||||
try:
|
||||
model = deepcopy(self.model)
|
||||
# overrides default parameters with the parameters being explored at this iteration
|
||||
model.set_params(**params)
|
||||
model.fit(training)
|
||||
score = evaluation.evaluate(model, protocol=protocol, error_metric=error)
|
||||
|
||||
ttime = time()-tinit
|
||||
self._sout(f'hyperparams={params}\t got {error.__name__} score {score:.5f} [took {ttime:.4f}s]')
|
||||
|
||||
if self.timeout > 0:
|
||||
signal.alarm(0)
|
||||
except TimeoutError:
|
||||
self._sout(f'timeout ({self.timeout}s) reached for config {params}')
|
||||
score = None
|
||||
except ValueError as e:
|
||||
self._sout(f'the combination of hyperparameters {params} is invalid')
|
||||
raise e
|
||||
except Exception as e:
|
||||
self._sout(f'something went wrong for config {params}; skipping:')
|
||||
self._sout(f'\tException: {e}')
|
||||
score = None
|
||||
|
||||
return params, score, model
|
||||
|
||||
|
||||
def quantify(self, instances):
|
||||
"""Estimate class prevalence values using the best model found after calling the :meth:`fit` method.
|
||||
|
||||
|
|
@ -203,7 +310,42 @@ class GridSearchQ(BaseQuantifier):
|
|||
return self.best_model_
|
||||
raise ValueError('best_model called before fit')
|
||||
|
||||
def _error_handler(self, func, params):
|
||||
"""
|
||||
Endorses one job with two returned values: the status, and the time of execution
|
||||
|
||||
:param func: the function to be called
|
||||
:param params: parameters of the function
|
||||
:return: `tuple(out, status, time)` where `out` is the function output,
|
||||
`status` is an enum value from `Status`, and `time` is the time it
|
||||
took to complete the call
|
||||
"""
|
||||
|
||||
output = None
|
||||
|
||||
def _handle(status, exception):
|
||||
if self.raise_errors:
|
||||
raise exception
|
||||
else:
|
||||
return ConfigStatus(params, status)
|
||||
|
||||
try:
|
||||
with timeout(self.timeout):
|
||||
tinit = time()
|
||||
output = func(params)
|
||||
status = ConfigStatus(params, Status.SUCCESS)
|
||||
|
||||
except TimeoutError as e:
|
||||
status = _handle(Status.TIMEOUT, e)
|
||||
|
||||
except ValueError as e:
|
||||
status = _handle(Status.INVALID, e)
|
||||
|
||||
except Exception as e:
|
||||
status = _handle(Status.ERROR, e)
|
||||
|
||||
took = time() - tinit
|
||||
return output, status, took
|
||||
|
||||
|
||||
def cross_val_predict(quantifier: BaseQuantifier, data: LabelledCollection, nfolds=3, random_state=0):
|
||||
|
|
@ -223,9 +365,49 @@ def cross_val_predict(quantifier: BaseQuantifier, data: LabelledCollection, nfol
|
|||
for train, test in data.kFCV(nfolds=nfolds, random_state=random_state):
|
||||
quantifier.fit(train)
|
||||
fold_prev = quantifier.quantify(test.X)
|
||||
rel_size = len(test.X)/len(data)
|
||||
rel_size = 1. * len(test) / len(data)
|
||||
total_prev += fold_prev*rel_size
|
||||
|
||||
return total_prev
|
||||
|
||||
|
||||
def expand_grid(param_grid: dict):
|
||||
"""
|
||||
Expands a param_grid dictionary as a list of configurations.
|
||||
Example:
|
||||
|
||||
>>> combinations = expand_grid({'A': [1, 10, 100], 'B': [True, False]})
|
||||
>>> print(combinations)
|
||||
>>> [{'A': 1, 'B': True}, {'A': 1, 'B': False}, {'A': 10, 'B': True}, {'A': 10, 'B': False}, {'A': 100, 'B': True}, {'A': 100, 'B': False}]
|
||||
|
||||
:param param_grid: dictionary with keys representing hyper-parameter names, and values representing the range
|
||||
to explore for that hyper-parameter
|
||||
:return: a list of configurations, i.e., combinations of hyper-parameter assignments in the grid.
|
||||
"""
|
||||
params_keys = list(param_grid.keys())
|
||||
params_values = list(param_grid.values())
|
||||
configs = [{k: combs[i] for i, k in enumerate(params_keys)} for combs in itertools.product(*params_values)]
|
||||
return configs
|
||||
|
||||
|
||||
def group_params(param_grid: dict):
|
||||
"""
|
||||
Partitions a param_grid dictionary as two lists of configurations, one for the classifier-specific
|
||||
hyper-parameters, and another for que quantifier-specific hyper-parameters
|
||||
|
||||
:param param_grid: dictionary with keys representing hyper-parameter names, and values representing the range
|
||||
to explore for that hyper-parameter
|
||||
:return: two expanded grids of configurations, one for the classifier, another for the quantifier
|
||||
"""
|
||||
classifier_params, quantifier_params = {}, {}
|
||||
for key, values in param_grid.items():
|
||||
if key.startswith('classifier__') or key == 'val_split':
|
||||
classifier_params[key] = values
|
||||
else:
|
||||
quantifier_params[key] = values
|
||||
|
||||
classifier_configs = expand_grid(classifier_params)
|
||||
quantifier_configs = expand_grid(quantifier_params)
|
||||
|
||||
return classifier_configs, quantifier_configs
|
||||
|
||||
|
|
|
|||
|
|
@ -236,7 +236,7 @@ class APP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol):
|
|||
raise RuntimeError(
|
||||
f"Abort: the number of samples that will be generated by {self.__class__.__name__} ({n}) "
|
||||
f"exceeds the maximum number of allowed samples ({sanity_check = }). Set 'sanity_check' to "
|
||||
f"None for bypassing this check, or to a higher number.")
|
||||
f"None, or to a higher number, for bypassing this check.")
|
||||
|
||||
self.collator = OnLabelledCollectionProtocol.get_collator(return_type)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
import pytest
|
||||
|
||||
from quapy.data.datasets import REVIEWS_SENTIMENT_DATASETS, TWITTER_SENTIMENT_DATASETS_TEST, \
|
||||
TWITTER_SENTIMENT_DATASETS_TRAIN, UCI_DATASETS, LEQUA2022_TASKS, \
|
||||
fetch_reviews, fetch_twitter, fetch_UCIDataset, fetch_lequa2022
|
||||
TWITTER_SENTIMENT_DATASETS_TRAIN, UCI_BINARY_DATASETS, LEQUA2022_TASKS, UCI_MULTICLASS_DATASETS,\
|
||||
fetch_reviews, fetch_twitter, fetch_UCIBinaryDataset, fetch_lequa2022, fetch_UCIMulticlassLabelledCollection
|
||||
|
||||
|
||||
@pytest.mark.parametrize('dataset_name', REVIEWS_SENTIMENT_DATASETS)
|
||||
|
|
@ -29,10 +29,10 @@ def test_fetch_twitter(dataset_name):
|
|||
print('Test set stats')
|
||||
|
||||
|
||||
@pytest.mark.parametrize('dataset_name', UCI_DATASETS)
|
||||
@pytest.mark.parametrize('dataset_name', UCI_BINARY_DATASETS)
|
||||
def test_fetch_UCIDataset(dataset_name):
|
||||
try:
|
||||
dataset = fetch_UCIDataset(dataset_name)
|
||||
dataset = fetch_UCIBinaryDataset(dataset_name)
|
||||
except FileNotFoundError as fnfe:
|
||||
if dataset_name == 'pageblocks.5' and fnfe.args[0].find(
|
||||
'If this is the first time you attempt to load this dataset') > 0:
|
||||
|
|
@ -44,6 +44,15 @@ def test_fetch_UCIDataset(dataset_name):
|
|||
print('Test set stats')
|
||||
|
||||
|
||||
@pytest.mark.parametrize('dataset_name', UCI_MULTICLASS_DATASETS)
|
||||
def test_fetch_UCIMultiDataset(dataset_name):
|
||||
dataset = fetch_UCIMulticlassLabelledCollection(dataset_name)
|
||||
print(f'Dataset {dataset_name}')
|
||||
print('Training set stats')
|
||||
dataset.stats()
|
||||
print('Test set stats')
|
||||
|
||||
|
||||
@pytest.mark.parametrize('dataset_name', LEQUA2022_TASKS)
|
||||
def test_fetch_lequa2022(dataset_name):
|
||||
train, gen_val, gen_test = fetch_lequa2022(dataset_name)
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ import quapy as qp
|
|||
from sklearn.linear_model import LogisticRegression
|
||||
from time import time
|
||||
|
||||
from error import QUANTIFICATION_ERROR_SINGLE, QUANTIFICATION_ERROR, QUANTIFICATION_ERROR_NAMES, \
|
||||
from quapy.error import QUANTIFICATION_ERROR_SINGLE, QUANTIFICATION_ERROR, QUANTIFICATION_ERROR_NAMES, \
|
||||
QUANTIFICATION_ERROR_SINGLE_NAMES
|
||||
from quapy.method.aggregative import EMQ, PCC
|
||||
from quapy.method.base import BaseQuantifier
|
||||
|
|
|
|||
|
|
@ -1,12 +1,8 @@
|
|||
import unittest
|
||||
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
import quapy as qp
|
||||
from quapy.method.aggregative import *
|
||||
|
||||
|
||||
|
||||
class HierarchyTestCase(unittest.TestCase):
|
||||
|
||||
def test_aggregative(self):
|
||||
|
|
@ -22,9 +18,11 @@ class HierarchyTestCase(unittest.TestCase):
|
|||
def test_probabilistic(self):
|
||||
lr = LogisticRegression()
|
||||
for m in [CC(lr), ACC(lr)]:
|
||||
self.assertEqual(isinstance(m, AggregativeProbabilisticQuantifier), False)
|
||||
self.assertEqual(isinstance(m, AggregativeCrispQuantifier), True)
|
||||
self.assertEqual(isinstance(m, AggregativeSoftQuantifier), False)
|
||||
for m in [PCC(lr), PACC(lr)]:
|
||||
self.assertEqual(isinstance(m, AggregativeProbabilisticQuantifier), True)
|
||||
self.assertEqual(isinstance(m, AggregativeCrispQuantifier), False)
|
||||
self.assertEqual(isinstance(m, AggregativeSoftQuantifier), True)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
|
|
|||
|
|
@ -1,25 +1,29 @@
|
|||
import numpy
|
||||
import numpy as np
|
||||
import pytest
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
from sklearn.svm import LinearSVC
|
||||
|
||||
import method.aggregative
|
||||
import quapy as qp
|
||||
from quapy.model_selection import GridSearchQ
|
||||
from quapy.method.base import BinaryQuantifier
|
||||
from quapy.data import Dataset, LabelledCollection
|
||||
from quapy.method import AGGREGATIVE_METHODS, NON_AGGREGATIVE_METHODS
|
||||
from quapy.method.aggregative import ACC, PACC, HDy
|
||||
from quapy.method.meta import Ensemble
|
||||
from quapy.protocol import APP
|
||||
from quapy.method.aggregative import DMy
|
||||
from quapy.method.meta import MedianEstimator
|
||||
|
||||
datasets = [pytest.param(qp.datasets.fetch_twitter('hcr', pickle=True), id='hcr'),
|
||||
pytest.param(qp.datasets.fetch_UCIDataset('ionosphere'), id='ionosphere')]
|
||||
# datasets = [pytest.param(qp.datasets.fetch_twitter('hcr', pickle=True), id='hcr'),
|
||||
# pytest.param(qp.datasets.fetch_UCIDataset('ionosphere'), id='ionosphere')]
|
||||
|
||||
tinydatasets = [pytest.param(qp.datasets.fetch_twitter('hcr', pickle=True).reduce(), id='tiny_hcr'),
|
||||
pytest.param(qp.datasets.fetch_UCIDataset('ionosphere').reduce(), id='tiny_ionosphere')]
|
||||
pytest.param(qp.datasets.fetch_UCIBinaryDataset('ionosphere').reduce(), id='tiny_ionosphere')]
|
||||
|
||||
learners = [LogisticRegression, LinearSVC]
|
||||
|
||||
|
||||
@pytest.mark.parametrize('dataset', datasets)
|
||||
@pytest.mark.parametrize('dataset', tinydatasets)
|
||||
@pytest.mark.parametrize('aggregative_method', AGGREGATIVE_METHODS)
|
||||
@pytest.mark.parametrize('learner', learners)
|
||||
def test_aggregative_methods(dataset: Dataset, aggregative_method, learner):
|
||||
|
|
@ -36,10 +40,10 @@ def test_aggregative_methods(dataset: Dataset, aggregative_method, learner):
|
|||
true_prevalences = dataset.test.prevalence()
|
||||
error = qp.error.mae(true_prevalences, estim_prevalences)
|
||||
|
||||
assert type(error) == numpy.float64
|
||||
assert type(error) == np.float64
|
||||
|
||||
|
||||
@pytest.mark.parametrize('dataset', datasets)
|
||||
@pytest.mark.parametrize('dataset', tinydatasets)
|
||||
@pytest.mark.parametrize('non_aggregative_method', NON_AGGREGATIVE_METHODS)
|
||||
def test_non_aggregative_methods(dataset: Dataset, non_aggregative_method):
|
||||
model = non_aggregative_method()
|
||||
|
|
@ -55,23 +59,24 @@ def test_non_aggregative_methods(dataset: Dataset, non_aggregative_method):
|
|||
true_prevalences = dataset.test.prevalence()
|
||||
error = qp.error.mae(true_prevalences, estim_prevalences)
|
||||
|
||||
assert type(error) == numpy.float64
|
||||
assert type(error) == np.float64
|
||||
|
||||
|
||||
@pytest.mark.parametrize('base_method', AGGREGATIVE_METHODS)
|
||||
@pytest.mark.parametrize('base_method', [method.aggregative.ACC, method.aggregative.PACC])
|
||||
@pytest.mark.parametrize('learner', [LogisticRegression])
|
||||
@pytest.mark.parametrize('dataset', tinydatasets)
|
||||
@pytest.mark.parametrize('policy', Ensemble.VALID_POLICIES)
|
||||
def test_ensemble_method(base_method, learner, dataset: Dataset, policy):
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 20
|
||||
|
||||
base_quantifier=base_method(learner())
|
||||
if isinstance(base_quantifier, BinaryQuantifier) and not dataset.binary:
|
||||
print(f'skipping the test of binary model {base_quantifier} on non-binary dataset {dataset}')
|
||||
return
|
||||
|
||||
if not dataset.binary and policy=='ds':
|
||||
print(f'skipping the test of binary policy ds on non-binary dataset {dataset}')
|
||||
return
|
||||
model = Ensemble(quantifier=base_quantifier, size=5, policy=policy, n_jobs=-1)
|
||||
|
||||
model = Ensemble(quantifier=base_quantifier, size=3, policy=policy, n_jobs=-1)
|
||||
|
||||
model.fit(dataset.training)
|
||||
|
||||
|
|
@ -80,7 +85,7 @@ def test_ensemble_method(base_method, learner, dataset: Dataset, policy):
|
|||
true_prevalences = dataset.test.prevalence()
|
||||
error = qp.error.mae(true_prevalences, estim_prevalences)
|
||||
|
||||
assert type(error) == numpy.float64
|
||||
assert type(error) == np.float64
|
||||
|
||||
|
||||
def test_quanet_method():
|
||||
|
|
@ -90,13 +95,10 @@ def test_quanet_method():
|
|||
print('skipping QuaNet test due to missing torch package')
|
||||
return
|
||||
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 100
|
||||
|
||||
# load the kindle dataset as text, and convert words to numerical indexes
|
||||
dataset = qp.datasets.fetch_reviews('kindle', pickle=True)
|
||||
dataset = Dataset(dataset.training.sampling(200, *dataset.training.prevalence()),
|
||||
dataset.test.sampling(200, *dataset.test.prevalence()))
|
||||
dataset = qp.datasets.fetch_reviews('kindle', pickle=True).reduce(200, 200)
|
||||
qp.data.preprocessing.index(dataset, min_df=5, inplace=True)
|
||||
|
||||
from quapy.classification.neural import CNNnet
|
||||
|
|
@ -119,7 +121,7 @@ def test_quanet_method():
|
|||
true_prevalences = dataset.test.prevalence()
|
||||
error = qp.error.mae(true_prevalences, estim_prevalences)
|
||||
|
||||
assert type(error) == numpy.float64
|
||||
assert type(error) == np.float64
|
||||
|
||||
|
||||
def test_str_label_names():
|
||||
|
|
@ -130,32 +132,103 @@ def test_str_label_names():
|
|||
dataset.test.sampling(1000, 0.25, 0.75))
|
||||
qp.data.preprocessing.text2tfidf(dataset, min_df=5, inplace=True)
|
||||
|
||||
numpy.random.seed(0)
|
||||
np.random.seed(0)
|
||||
model.fit(dataset.training)
|
||||
|
||||
int_estim_prevalences = model.quantify(dataset.test.instances)
|
||||
true_prevalences = dataset.test.prevalence()
|
||||
|
||||
error = qp.error.mae(true_prevalences, int_estim_prevalences)
|
||||
assert type(error) == numpy.float64
|
||||
assert type(error) == np.float64
|
||||
|
||||
dataset_str = Dataset(LabelledCollection(dataset.training.instances,
|
||||
['one' if label == 1 else 'zero' for label in dataset.training.labels]),
|
||||
LabelledCollection(dataset.test.instances,
|
||||
['one' if label == 1 else 'zero' for label in dataset.test.labels]))
|
||||
assert all(dataset_str.training.classes_ == dataset_str.test.classes_), 'wrong indexation'
|
||||
numpy.random.seed(0)
|
||||
np.random.seed(0)
|
||||
model.fit(dataset_str.training)
|
||||
|
||||
str_estim_prevalences = model.quantify(dataset_str.test.instances)
|
||||
true_prevalences = dataset_str.test.prevalence()
|
||||
|
||||
error = qp.error.mae(true_prevalences, str_estim_prevalences)
|
||||
assert type(error) == numpy.float64
|
||||
assert type(error) == np.float64
|
||||
|
||||
print(true_prevalences)
|
||||
print(int_estim_prevalences)
|
||||
print(str_estim_prevalences)
|
||||
|
||||
numpy.testing.assert_almost_equal(int_estim_prevalences[1],
|
||||
np.testing.assert_almost_equal(int_estim_prevalences[1],
|
||||
str_estim_prevalences[list(model.classes_).index('one')])
|
||||
|
||||
# helper
|
||||
def __fit_test(quantifier, train, test):
|
||||
quantifier.fit(train)
|
||||
test_samples = APP(test)
|
||||
true_prevs, estim_prevs = qp.evaluation.prediction(quantifier, test_samples)
|
||||
return qp.error.mae(true_prevs, estim_prevs), estim_prevs
|
||||
|
||||
|
||||
def test_median_meta():
|
||||
"""
|
||||
This test compares the performance of the MedianQuantifier with respect to computing the median of the predictions
|
||||
of a differently parameterized quantifier. We use the DistributionMatching base quantifier and the median is
|
||||
computed across different values of nbins
|
||||
"""
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 100
|
||||
|
||||
# grid of values
|
||||
nbins_grid = list(range(2, 11))
|
||||
|
||||
dataset = 'kindle'
|
||||
train, test = qp.datasets.fetch_reviews(dataset, tfidf=True, min_df=10).train_test
|
||||
prevs = []
|
||||
errors = []
|
||||
for nbins in nbins_grid:
|
||||
with qp.util.temp_seed(0):
|
||||
q = DMy(LogisticRegression(), nbins=nbins)
|
||||
mae, estim_prevs = __fit_test(q, train, test)
|
||||
prevs.append(estim_prevs)
|
||||
errors.append(mae)
|
||||
print(f'{dataset} DistributionMatching(nbins={nbins}) got MAE {mae:.4f}')
|
||||
prevs = np.asarray(prevs)
|
||||
mae = np.mean(errors)
|
||||
print(f'\tMAE={mae:.4f}')
|
||||
|
||||
q = DMy(LogisticRegression())
|
||||
q = MedianEstimator(q, param_grid={'nbins': nbins_grid}, random_state=0, n_jobs=-1)
|
||||
median_mae, prev = __fit_test(q, train, test)
|
||||
print(f'\tMAE={median_mae:.4f}')
|
||||
|
||||
np.testing.assert_almost_equal(np.median(prevs, axis=0), prev)
|
||||
assert median_mae < mae, 'the median-based quantifier provided a higher error...'
|
||||
|
||||
|
||||
def test_median_meta_modsel():
|
||||
"""
|
||||
This test checks the median-meta quantifier with model selection
|
||||
"""
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 100
|
||||
|
||||
dataset = 'kindle'
|
||||
train, test = qp.datasets.fetch_reviews(dataset, tfidf=True, min_df=10).train_test
|
||||
train, val = train.split_stratified(random_state=0)
|
||||
|
||||
nbins_grid = [2, 4, 5, 10, 15]
|
||||
|
||||
q = DMy(LogisticRegression())
|
||||
q = MedianEstimator(q, param_grid={'nbins': nbins_grid}, random_state=0, n_jobs=-1)
|
||||
median_mae, _ = __fit_test(q, train, test)
|
||||
print(f'\tMAE={median_mae:.4f}')
|
||||
|
||||
q = DMy(LogisticRegression())
|
||||
lr_params = {'classifier__C': np.logspace(-1, 1, 3)}
|
||||
q = MedianEstimator(q, param_grid={'nbins': nbins_grid}, random_state=0, n_jobs=-1)
|
||||
q = GridSearchQ(q, param_grid=lr_params, protocol=APP(val), n_jobs=-1)
|
||||
optimized_median_ave, _ = __fit_test(q, train, test)
|
||||
print(f'\tMAE={optimized_median_ave:.4f}')
|
||||
|
||||
assert optimized_median_ave < median_mae, "the optimized method yielded worse performance..."
|
||||
|
|
@ -97,11 +97,22 @@ class ModselTestCase(unittest.TestCase):
|
|||
|
||||
param_grid = {'classifier__C': np.logspace(-3,3,7)}
|
||||
app = APP(validation, sample_size=100, random_state=1)
|
||||
q = GridSearchQ(
|
||||
q, param_grid, protocol=app, error='mae', refit=True, timeout=3, n_jobs=-1, verbose=True
|
||||
|
||||
print('Expecting TimeoutError to be raised')
|
||||
modsel = GridSearchQ(
|
||||
q, param_grid, protocol=app, timeout=3, n_jobs=-1, verbose=True, raise_errors=True
|
||||
)
|
||||
with self.assertRaises(TimeoutError):
|
||||
q.fit(training)
|
||||
modsel.fit(training)
|
||||
|
||||
print('Expecting ValueError to be raised')
|
||||
modsel = GridSearchQ(
|
||||
q, param_grid, protocol=app, timeout=3, n_jobs=-1, verbose=True, raise_errors=False
|
||||
)
|
||||
with self.assertRaises(ValueError):
|
||||
# this exception is not raised because of the timeout, but because no combination of hyperparams
|
||||
# succedded (in this case, a ValueError is raised, regardless of "raise_errors"
|
||||
modsel.fit(training)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
|
|
|||
|
|
@ -3,14 +3,16 @@ import quapy as qp
|
|||
from quapy.data import LabelledCollection
|
||||
from quapy.functional import strprev
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
import numpy as np
|
||||
from quapy.method.aggregative import PACC
|
||||
import quapy.functional as F
|
||||
|
||||
|
||||
class MyTestCase(unittest.TestCase):
|
||||
|
||||
def test_prediction_replicability(self):
|
||||
|
||||
dataset = qp.datasets.fetch_UCIDataset('yeast')
|
||||
dataset = qp.datasets.fetch_UCIBinaryDataset('yeast')
|
||||
|
||||
with qp.util.temp_seed(0):
|
||||
lr = LogisticRegression(random_state=0, max_iter=10000)
|
||||
|
|
@ -26,8 +28,8 @@ class MyTestCase(unittest.TestCase):
|
|||
|
||||
self.assertEqual(str_prev1, str_prev2) # add assertion here
|
||||
|
||||
|
||||
def test_samping_replicability(self):
|
||||
import numpy as np
|
||||
|
||||
def equal_collections(c1, c2, value=True):
|
||||
self.assertEqual(np.all(c1.X == c2.X), value)
|
||||
|
|
@ -74,5 +76,36 @@ class MyTestCase(unittest.TestCase):
|
|||
equal_collections(sample1_te, sample2_te, True)
|
||||
|
||||
|
||||
def test_parallel_replicability(self):
|
||||
|
||||
train, test = qp.datasets.fetch_UCIMulticlassDataset('dry-bean').train_test
|
||||
|
||||
test = test.sampling(500, *[0.1, 0.0, 0.1, 0.1, 0.2, 0.5, 0.0])
|
||||
|
||||
with qp.util.temp_seed(10):
|
||||
pacc = PACC(LogisticRegression(), val_split=2, n_jobs=2)
|
||||
pacc.fit(train, val_split=0.5)
|
||||
prev1 = F.strprev(pacc.quantify(test.instances))
|
||||
|
||||
with qp.util.temp_seed(0):
|
||||
pacc = PACC(LogisticRegression(), val_split=2, n_jobs=2)
|
||||
pacc.fit(train, val_split=0.5)
|
||||
prev2 = F.strprev(pacc.quantify(test.instances))
|
||||
|
||||
with qp.util.temp_seed(0):
|
||||
pacc = PACC(LogisticRegression(), val_split=2, n_jobs=2)
|
||||
pacc.fit(train, val_split=0.5)
|
||||
prev3 = F.strprev(pacc.quantify(test.instances))
|
||||
|
||||
print(prev1)
|
||||
print(prev2)
|
||||
print(prev3)
|
||||
|
||||
self.assertNotEqual(prev1, prev2)
|
||||
self.assertEqual(prev2, prev3)
|
||||
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
|
|
|||
|
|
@ -10,6 +10,8 @@ import quapy as qp
|
|||
|
||||
import numpy as np
|
||||
from joblib import Parallel, delayed
|
||||
from time import time
|
||||
import signal
|
||||
|
||||
|
||||
def _get_parallel_slices(n_tasks, n_jobs):
|
||||
|
|
@ -22,7 +24,7 @@ def _get_parallel_slices(n_tasks, n_jobs):
|
|||
|
||||
def map_parallel(func, args, n_jobs):
|
||||
"""
|
||||
Applies func to n_jobs slices of args. E.g., if args is an array of 99 items and `n_jobs`=2, then
|
||||
Applies func to n_jobs slices of args. E.g., if args is an array of 99 items and n_jobs=2, then
|
||||
func is applied in two parallel processes to args[0:50] and to args[50:99]. func is a function
|
||||
that already works with a list of arguments.
|
||||
|
||||
|
|
@ -38,7 +40,7 @@ def map_parallel(func, args, n_jobs):
|
|||
return list(itertools.chain.from_iterable(results))
|
||||
|
||||
|
||||
def parallel(func, args, n_jobs, seed=None):
|
||||
def parallel(func, args, n_jobs, seed=None, asarray=True, backend='loky'):
|
||||
"""
|
||||
A wrapper of multiprocessing:
|
||||
|
||||
|
|
@ -47,7 +49,13 @@ def parallel(func, args, n_jobs, seed=None):
|
|||
>>> )
|
||||
|
||||
that takes the `quapy.environ` variable as input silently.
|
||||
Seeds the child processes to ensure reproducibility when n_jobs>1
|
||||
Seeds the child processes to ensure reproducibility when n_jobs>1.
|
||||
|
||||
:param func: callable
|
||||
:param args: args of func
|
||||
:param seed: the numeric seed
|
||||
:param asarray: set to True to return a np.ndarray instead of a list
|
||||
:param backend: indicates the backend used for handling parallel works
|
||||
"""
|
||||
def func_dec(environ, seed, *args):
|
||||
qp.environ = environ.copy()
|
||||
|
|
@ -58,9 +66,12 @@ def parallel(func, args, n_jobs, seed=None):
|
|||
stack.enter_context(qp.util.temp_seed(seed))
|
||||
return func(*args)
|
||||
|
||||
return Parallel(n_jobs=n_jobs)(
|
||||
out = Parallel(n_jobs=n_jobs, backend=backend)(
|
||||
delayed(func_dec)(qp.environ, None if seed is None else seed+i, args_i) for i, args_i in enumerate(args)
|
||||
)
|
||||
if asarray:
|
||||
out = np.asarray(out)
|
||||
return out
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
|
|
@ -254,3 +265,35 @@ class EarlyStop:
|
|||
if self.patience <= 0:
|
||||
self.STOP = True
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def timeout(seconds):
|
||||
"""
|
||||
Opens a context that will launch an exception if not closed after a given number of seconds
|
||||
|
||||
>>> def func(start_msg, end_msg):
|
||||
>>> print(start_msg)
|
||||
>>> sleep(2)
|
||||
>>> print(end_msg)
|
||||
>>>
|
||||
>>> with timeout(1):
|
||||
>>> func('begin function', 'end function')
|
||||
>>> Out[]
|
||||
>>> begin function
|
||||
>>> TimeoutError
|
||||
|
||||
|
||||
:param seconds: number of seconds, set to <=0 to ignore the timer
|
||||
"""
|
||||
if seconds > 0:
|
||||
def handler(signum, frame):
|
||||
raise TimeoutError()
|
||||
|
||||
signal.signal(signal.SIGALRM, handler)
|
||||
signal.alarm(seconds)
|
||||
|
||||
yield
|
||||
|
||||
if seconds > 0:
|
||||
signal.alarm(0)
|
||||
|
||||
|
|
|
|||
2
setup.py
2
setup.py
|
|
@ -113,7 +113,7 @@ setup(
|
|||
|
||||
python_requires='>=3.8, <4',
|
||||
|
||||
install_requires=['scikit-learn', 'pandas', 'tqdm', 'matplotlib', 'joblib', 'xlrd', 'abstention'],
|
||||
install_requires=['scikit-learn', 'pandas', 'tqdm', 'matplotlib', 'joblib', 'xlrd', 'abstention', 'ucimlrepo'],
|
||||
|
||||
# List additional groups of dependencies here (e.g. development
|
||||
# dependencies). Users will be able to install these using the "extras"
|
||||
|
|
|
|||
Loading…
Reference in New Issue