225 lines
13 KiB
HTML
225 lines
13 KiB
HTML
|
||
|
||
<!doctype html>
|
||
|
||
<html>
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
|
||
|
||
<title>Welcome to QuaPy’s documentation! — QuaPy 0.1.6 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/doctools.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="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 0.1.6 documentation</a> »</li>
|
||
<li class="nav-item nav-item-this"><a href="">Welcome to QuaPy’s documentation!</a></li>
|
||
</ul>
|
||
</div>
|
||
|
||
<div class="document">
|
||
<div class="documentwrapper">
|
||
<div class="bodywrapper">
|
||
<div class="body" role="main">
|
||
|
||
<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 headline">¶</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 headline">¶</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 headline">¶</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>
|
||
</section>
|
||
<section id="features">
|
||
<h3>Features<a class="headerlink" href="#features" title="Permalink to this headline">¶</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>
|
||
</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>
|
||
<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>
|
||
</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#adding-custom-datasets">Adding Custom Datasets</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>
|
||
</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>
|
||
</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>
|
||
</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 headline">¶</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>
|
||
<li><p><a class="reference internal" href="search.html"><span class="std std-ref">Search Page</span></a></p></li>
|
||
</ul>
|
||
</section>
|
||
|
||
|
||
<div class="clearer"></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||
<div class="sphinxsidebarwrapper">
|
||
<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>
|
||
|
||
<h4>Next topic</h4>
|
||
<p class="topless"><a href="Installation.html"
|
||
title="next chapter">Installation</a></p>
|
||
<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>$('#searchbox').show(0);</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="Installation.html" title="Installation"
|
||
>next</a> |</li>
|
||
<li class="nav-item nav-item-0"><a href="#">QuaPy 0.1.6 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> 4.2.0.
|
||
</div>
|
||
</body>
|
||
</html> |