692 lines
70 KiB
HTML
692 lines
70 KiB
HTML
<!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>quapy.protocol — 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" />
|
|
|
|
|
|
<!--[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" />
|
|
</head>
|
|
|
|
<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"><a href="../index.html">Module code</a></li>
|
|
<li class="breadcrumb-item active">quapy.protocol</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>Source code for quapy.protocol</h1><div class="highlight"><pre>
|
|
<span></span><span class="kn">from</span> <span class="nn">copy</span> <span class="kn">import</span> <span class="n">deepcopy</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">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
|
<span class="kn">import</span> <span class="nn">itertools</span>
|
|
<span class="kn">from</span> <span class="nn">contextlib</span> <span class="kn">import</span> <span class="n">ExitStack</span>
|
|
<span class="kn">from</span> <span class="nn">abc</span> <span class="kn">import</span> <span class="n">ABCMeta</span><span class="p">,</span> <span class="n">abstractmethod</span>
|
|
<span class="kn">from</span> <span class="nn">quapy.data</span> <span class="kn">import</span> <span class="n">LabelledCollection</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">os.path</span> <span class="kn">import</span> <span class="n">exists</span>
|
|
<span class="kn">from</span> <span class="nn">glob</span> <span class="kn">import</span> <span class="n">glob</span>
|
|
|
|
|
|
<div class="viewcode-block" id="AbstractProtocol">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.AbstractProtocol">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">AbstractProtocol</span><span class="p">(</span><span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Abstract parent class for sample generation protocols.</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="nd">@abstractmethod</span>
|
|
<span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Implements the protocol. Yields one sample at a time along with its prevalence</span>
|
|
|
|
<span class="sd"> :return: yields a tuple `(sample, prev) at a time, where `sample` is a set of instances</span>
|
|
<span class="sd"> and in which `prev` is an `nd.array` with the class prevalence values</span>
|
|
<span class="sd"> """</span>
|
|
<span class="o">...</span>
|
|
|
|
<div class="viewcode-block" id="AbstractProtocol.total">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.AbstractProtocol.total">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">total</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Indicates the total number of samples that the protocol generates.</span>
|
|
|
|
<span class="sd"> :return: The number of samples to generate if known, or `None` otherwise.</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="kc">None</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="IterateProtocol">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.IterateProtocol">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">IterateProtocol</span><span class="p">(</span><span class="n">AbstractProtocol</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> A very simple protocol which simply iterates over a list of previously generated samples</span>
|
|
|
|
<span class="sd"> :param samples: a list of :class:`quapy.data.base.LabelledCollection`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">samples</span><span class="p">:</span> <span class="p">[</span><span class="n">LabelledCollection</span><span class="p">]):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">samples</span> <span class="o">=</span> <span class="n">samples</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Yields one sample from the initial list at a time</span>
|
|
|
|
<span class="sd"> :return: yields a tuple `(sample, prev) at a time, where `sample` is a set of instances</span>
|
|
<span class="sd"> and in which `prev` is an `nd.array` with the class prevalence values</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">for</span> <span class="n">sample</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">samples</span><span class="p">:</span>
|
|
<span class="k">yield</span> <span class="n">sample</span><span class="o">.</span><span class="n">Xp</span>
|
|
|
|
<div class="viewcode-block" id="IterateProtocol.total">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.IterateProtocol.total">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">total</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns the number of samples in this protocol</span>
|
|
|
|
<span class="sd"> :return: int</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">samples</span><span class="p">)</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="AbstractStochasticSeededProtocol">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.AbstractStochasticSeededProtocol">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">AbstractStochasticSeededProtocol</span><span class="p">(</span><span class="n">AbstractProtocol</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> An `AbstractStochasticSeededProtocol` is a protocol that generates, via any random procedure (e.g.,</span>
|
|
<span class="sd"> via random sampling), sequences of :class:`quapy.data.base.LabelledCollection` samples.</span>
|
|
<span class="sd"> The protocol abstraction enforces</span>
|
|
<span class="sd"> the object to be instantiated using a seed, so that the sequence can be fully replicated.</span>
|
|
<span class="sd"> In order to make this functionality possible, the classes extending this abstraction need to</span>
|
|
<span class="sd"> implement only two functions, :meth:`samples_parameters` which generates all the parameters</span>
|
|
<span class="sd"> needed for extracting the samples, and :meth:`sample` that, given some parameters as input,</span>
|
|
<span class="sd"> deterministically generates a sample.</span>
|
|
|
|
<span class="sd"> :param random_state: the seed for allowing to replicate any sequence of samples. Default is 0, meaning that</span>
|
|
<span class="sd"> the sequence will be consistent every time the protocol is called.</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="n">_random_state</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> <span class="c1"># means "not set"</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</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="bp">self</span><span class="o">.</span><span class="n">random_state</span> <span class="o">=</span> <span class="n">random_state</span>
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">random_state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_random_state</span>
|
|
|
|
<span class="nd">@random_state</span><span class="o">.</span><span class="n">setter</span>
|
|
<span class="k">def</span> <span class="nf">random_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">random_state</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_random_state</span> <span class="o">=</span> <span class="n">random_state</span>
|
|
|
|
<div class="viewcode-block" id="AbstractStochasticSeededProtocol.samples_parameters">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.samples_parameters">[docs]</a>
|
|
<span class="nd">@abstractmethod</span>
|
|
<span class="k">def</span> <span class="nf">samples_parameters</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> This function has to return all the necessary parameters to replicate the samples</span>
|
|
|
|
<span class="sd"> :return: a list of parameters, each of which serves to deterministically generate a sample</span>
|
|
<span class="sd"> """</span>
|
|
<span class="o">...</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="AbstractStochasticSeededProtocol.sample">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.sample">[docs]</a>
|
|
<span class="nd">@abstractmethod</span>
|
|
<span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Extract one sample determined by the given parameters</span>
|
|
|
|
<span class="sd"> :param params: all the necessary parameters to generate a sample</span>
|
|
<span class="sd"> :return: one sample (the same sample has to be generated for the same parameters)</span>
|
|
<span class="sd"> """</span>
|
|
<span class="o">...</span></div>
|
|
|
|
|
|
<span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Yields one sample at a time. The type of object returned depends on the `collator` function. The</span>
|
|
<span class="sd"> default behaviour returns tuples of the form `(sample, prevalence)`.</span>
|
|
|
|
<span class="sd"> :return: a tuple `(sample, prevalence)` if return_type='sample_prev', or an instance of</span>
|
|
<span class="sd"> :class:`qp.data.LabelledCollection` if return_type='labelled_collection'</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">with</span> <span class="n">ExitStack</span><span class="p">()</span> <span class="k">as</span> <span class="n">stack</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">random_state</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'The random seed has never been initialized. '</span>
|
|
<span class="s1">'Set it to None not to impose replicability.'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">random_state</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">stack</span><span class="o">.</span><span class="n">enter_context</span><span class="p">(</span><span class="n">qp</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="n">temp_seed</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">random_state</span><span class="p">))</span>
|
|
<span class="k">for</span> <span class="n">params</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">samples_parameters</span><span class="p">():</span>
|
|
<span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">collator</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sample</span><span class="p">(</span><span class="n">params</span><span class="p">))</span>
|
|
|
|
<div class="viewcode-block" id="AbstractStochasticSeededProtocol.collator">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.AbstractStochasticSeededProtocol.collator">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">collator</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sample</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> The collator prepares the sample to accommodate the desired output format before returning the output.</span>
|
|
<span class="sd"> This collator simply returns the sample as it is. Classes inheriting from this abstract class can</span>
|
|
<span class="sd"> implement their custom collators.</span>
|
|
|
|
<span class="sd"> :param sample: the sample to be returned</span>
|
|
<span class="sd"> :param args: additional arguments</span>
|
|
<span class="sd"> :return: the sample adhering to a desired output format (in this case, the sample is returned as it is)</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="n">sample</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="OnLabelledCollectionProtocol">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.OnLabelledCollectionProtocol">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">OnLabelledCollectionProtocol</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Protocols that generate samples from a :class:`qp.data.LabelledCollection` object.</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="n">RETURN_TYPES</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'sample_prev'</span><span class="p">,</span> <span class="s1">'labelled_collection'</span><span class="p">,</span> <span class="s1">'index'</span><span class="p">]</span>
|
|
|
|
<div class="viewcode-block" id="OnLabelledCollectionProtocol.get_labelled_collection">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_labelled_collection">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">get_labelled_collection</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns the labelled collection on which this protocol acts.</span>
|
|
|
|
<span class="sd"> :return: an object of type :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">data</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="OnLabelledCollectionProtocol.on_preclassified_instances">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.OnLabelledCollectionProtocol.on_preclassified_instances">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">on_preclassified_instances</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pre_classifications</span><span class="p">,</span> <span class="n">in_place</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns a copy of this protocol that acts on a modified version of the original</span>
|
|
<span class="sd"> :class:`qp.data.LabelledCollection` in which the original instances have been replaced</span>
|
|
<span class="sd"> with the outputs of a classifier for each instance. (This is convenient for speeding-up</span>
|
|
<span class="sd"> the evaluation procedures for many samples, by pre-classifying the instances in advance.)</span>
|
|
|
|
<span class="sd"> :param pre_classifications: the predictions issued by a classifier, typically an array-like</span>
|
|
<span class="sd"> with shape `(n_instances,)` when the classifier is a hard one, or with shape</span>
|
|
<span class="sd"> `(n_instances, n_classes)` when the classifier is a probabilistic one.</span>
|
|
<span class="sd"> :param in_place: whether or not to apply the modification in-place or in a new copy (default).</span>
|
|
<span class="sd"> :return: a copy of this protocol</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pre_classifications</span><span class="p">)</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">),</span> \
|
|
<span class="sa">f</span><span class="s1">'error: the pre-classified data has different shape '</span> \
|
|
<span class="sa">f</span><span class="s1">'(expected </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">)</span><span class="si">}</span><span class="s1">, found </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">pre_classifications</span><span class="p">)</span><span class="si">}</span><span class="s1">)'</span>
|
|
<span class="k">if</span> <span class="n">in_place</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">instances</span> <span class="o">=</span> <span class="n">pre_classifications</span>
|
|
<span class="k">return</span> <span class="bp">self</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">new</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">new</span><span class="o">.</span><span class="n">on_preclassified_instances</span><span class="p">(</span><span class="n">pre_classifications</span><span class="p">,</span> <span class="n">in_place</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="OnLabelledCollectionProtocol.get_collator">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.OnLabelledCollectionProtocol.get_collator">[docs]</a>
|
|
<span class="nd">@classmethod</span>
|
|
<span class="k">def</span> <span class="nf">get_collator</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">return_type</span><span class="o">=</span><span class="s1">'sample_prev'</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns a collator function, i.e., a function that prepares the yielded data</span>
|
|
|
|
<span class="sd"> :param return_type: either 'sample_prev' (default) if the collator is requested to yield tuples of</span>
|
|
<span class="sd"> `(sample, prevalence)`, or 'labelled_collection' when it is requested to yield instances of</span>
|
|
<span class="sd"> :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> :return: the collator function (a callable function that takes as input an instance of</span>
|
|
<span class="sd"> :class:`qp.data.LabelledCollection`)</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">assert</span> <span class="n">return_type</span> <span class="ow">in</span> <span class="bp">cls</span><span class="o">.</span><span class="n">RETURN_TYPES</span><span class="p">,</span> \
|
|
<span class="sa">f</span><span class="s1">'unknown return type passed as argument; valid ones are </span><span class="si">{</span><span class="bp">cls</span><span class="o">.</span><span class="n">RETURN_TYPES</span><span class="si">}</span><span class="s1">'</span>
|
|
<span class="k">if</span> <span class="n">return_type</span><span class="o">==</span><span class="s1">'sample_prev'</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="k">lambda</span> <span class="n">lc</span><span class="p">:</span><span class="n">lc</span><span class="o">.</span><span class="n">Xp</span>
|
|
<span class="k">elif</span> <span class="n">return_type</span><span class="o">==</span><span class="s1">'labelled_collection'</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="k">lambda</span> <span class="n">lc</span><span class="p">:</span><span class="n">lc</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="APP">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.APP">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">APP</span><span class="p">(</span><span class="n">AbstractStochasticSeededProtocol</span><span class="p">,</span> <span class="n">OnLabelledCollectionProtocol</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Implementation of the artificial prevalence protocol (APP).</span>
|
|
<span class="sd"> The APP consists of exploring a grid of prevalence values containing `n_prevalences` points (e.g.,</span>
|
|
<span class="sd"> [0, 0.05, 0.1, 0.15, ..., 1], if `n_prevalences=21`), and generating all valid combinations of</span>
|
|
<span class="sd"> prevalence values for all classes (e.g., for 3 classes, samples with [0, 0, 1], [0, 0.05, 0.95], ...,</span>
|
|
<span class="sd"> [1, 0, 0] prevalence values of size `sample_size` will be yielded). The number of samples for each valid</span>
|
|
<span class="sd"> combination of prevalence values is indicated by `repeats`.</span>
|
|
|
|
<span class="sd"> :param data: a `LabelledCollection` from which the samples will be drawn</span>
|
|
<span class="sd"> :param sample_size: integer, number of instances in each sample; if None (default) then it is taken from</span>
|
|
<span class="sd"> qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised.</span>
|
|
<span class="sd"> :param n_prevalences: the number of equidistant prevalence points to extract from the [0,1] interval for the</span>
|
|
<span class="sd"> grid (default is 21)</span>
|
|
<span class="sd"> :param repeats: number of copies for each valid prevalence vector (default is 10)</span>
|
|
<span class="sd"> :param smooth_limits_epsilon: the quantity to add and subtract to the limits 0 and 1</span>
|
|
<span class="sd"> :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples</span>
|
|
<span class="sd"> will be the same every time the protocol is called)</span>
|
|
<span class="sd"> :param sanity_check: int, raises an exception warning the user that the number of examples to be generated exceed</span>
|
|
<span class="sd"> this number; set to None for skipping this check</span>
|
|
<span class="sd"> :param return_type: set to "sample_prev" (default) to get the pairs of (sample, prevalence) at each iteration, or</span>
|
|
<span class="sd"> to "labelled_collection" to get instead instances of LabelledCollection</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__init__</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">sample_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">n_prevalences</span><span class="o">=</span><span class="mi">21</span><span class="p">,</span> <span class="n">repeats</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
|
|
<span class="n">smooth_limits_epsilon</span><span class="o">=</span><span class="mi">0</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">sanity_check</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">return_type</span><span class="o">=</span><span class="s1">'sample_prev'</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">(</span><span class="n">APP</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">random_state</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">data</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">_get_sample_size</span><span class="p">(</span><span class="n">sample_size</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">n_prevalences</span> <span class="o">=</span> <span class="n">n_prevalences</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">repeats</span> <span class="o">=</span> <span class="n">repeats</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">smooth_limits_epsilon</span> <span class="o">=</span> <span class="n">smooth_limits_epsilon</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="p">((</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">sanity_check</span><span class="p">,</span> <span class="nb">int</span><span class="p">)</span> <span class="ow">and</span> <span class="n">sanity_check</span><span class="o">></span><span class="mi">0</span><span class="p">)</span> <span class="ow">or</span> <span class="n">sanity_check</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">):</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'param "sanity_check" must either be None or a positive integer'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">sanity_check</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
|
|
<span class="n">n</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">num_prevalence_combinations</span><span class="p">(</span><span class="n">n_prevpoints</span><span class="o">=</span><span class="n">n_prevalences</span><span class="p">,</span> <span class="n">n_classes</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">n_classes</span><span class="p">,</span> <span class="n">n_repeats</span><span class="o">=</span><span class="n">repeats</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">n</span> <span class="o">></span> <span class="n">sanity_check</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Abort: the number of samples that will be generated by </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2"> (</span><span class="si">{</span><span class="n">n</span><span class="si">}</span><span class="s2">) "</span>
|
|
<span class="sa">f</span><span class="s2">"exceeds the maximum number of allowed samples (</span><span class="si">{</span><span class="n">sanity_check</span><span class="w"> </span><span class="si">= }</span><span class="s2">). Set 'sanity_check' to "</span>
|
|
<span class="sa">f</span><span class="s2">"None, or to a higher number, for bypassing this check."</span><span class="p">)</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">collator</span> <span class="o">=</span> <span class="n">OnLabelledCollectionProtocol</span><span class="o">.</span><span class="n">get_collator</span><span class="p">(</span><span class="n">return_type</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="APP.prevalence_grid">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.APP.prevalence_grid">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">prevalence_grid</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Generates vectors of prevalence values from an exhaustive grid of prevalence values. The</span>
|
|
<span class="sd"> number of prevalence values explored for each dimension depends on `n_prevalences`, so that, if, for example,</span>
|
|
<span class="sd"> `n_prevalences=11` then the prevalence values of the grid are taken from [0, 0.1, 0.2, ..., 0.9, 1]. Only</span>
|
|
<span class="sd"> valid prevalence distributions are returned, i.e., vectors of prevalence values that sum up to 1. For each</span>
|
|
<span class="sd"> valid vector of prevalence values, `repeat` copies are returned. The vector of prevalence values can be</span>
|
|
<span class="sd"> implicit (by setting `return_constrained_dim=False`), meaning that the last dimension (which is constrained</span>
|
|
<span class="sd"> to 1 - sum of the rest) is not returned (note that, quite obviously, in this case the vector does not sum up to</span>
|
|
<span class="sd"> 1). Note that this method is deterministic, i.e., there is no random sampling anywhere.</span>
|
|
|
|
<span class="sd"> :return: a `np.ndarray` of shape `(n, dimensions)` if `return_constrained_dim=True` or of shape</span>
|
|
<span class="sd"> `(n, dimensions-1)` if `return_constrained_dim=False`, where `n` is the number of valid combinations found</span>
|
|
<span class="sd"> in the grid multiplied by `repeat`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">dimensions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">n_classes</span>
|
|
<span class="n">s</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">prevalence_linspace</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_prevalences</span><span class="p">,</span> <span class="n">repeats</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">smooth_limits_epsilon</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">smooth_limits_epsilon</span><span class="p">)</span>
|
|
<span class="n">eps</span> <span class="o">=</span> <span class="p">(</span><span class="n">s</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">-</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span><span class="o">/</span><span class="mi">2</span> <span class="c1"># handling floating rounding</span>
|
|
<span class="n">s</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="p">]</span> <span class="o">*</span> <span class="p">(</span><span class="n">dimensions</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">prevs</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">itertools</span><span class="o">.</span><span class="n">product</span><span class="p">(</span><span class="o">*</span><span class="n">s</span><span class="p">,</span> <span class="n">repeat</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="k">if</span> <span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o"><</span> <span class="p">(</span><span class="mf">1.</span><span class="o">+</span><span class="n">eps</span><span class="p">))]</span>
|
|
<span class="n">prevs</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="n">prevs</span><span class="p">)</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">prevs</span><span class="p">),</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">repeats</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="n">prevs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="n">prevs</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">repeats</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">prevs</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="APP.samples_parameters">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.APP.samples_parameters">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">samples_parameters</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Return all the necessary parameters to replicate the samples as according to the APP protocol.</span>
|
|
|
|
<span class="sd"> :return: a list of indexes that realize the APP sampling</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">indexes</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">prevs</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">prevalence_grid</span><span class="p">():</span>
|
|
<span class="n">index</span> <span class="o">=</span> <span class="bp">self</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="bp">self</span><span class="o">.</span><span class="n">sample_size</span><span class="p">,</span> <span class="o">*</span><span class="n">prevs</span><span class="p">)</span>
|
|
<span class="n">indexes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">indexes</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="APP.sample">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.APP.sample">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">index</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Realizes the sample given the index of the instances.</span>
|
|
|
|
<span class="sd"> :param index: indexes of the instances to select</span>
|
|
<span class="sd"> :return: an instance of :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</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></div>
|
|
|
|
|
|
<div class="viewcode-block" id="APP.total">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.APP.total">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">total</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns the number of samples that will be generated</span>
|
|
|
|
<span class="sd"> :return: int</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">num_prevalence_combinations</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_prevalences</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">n_classes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">repeats</span><span class="p">)</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="NPP">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.NPP">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">NPP</span><span class="p">(</span><span class="n">AbstractStochasticSeededProtocol</span><span class="p">,</span> <span class="n">OnLabelledCollectionProtocol</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> A generator of samples that implements the natural prevalence protocol (NPP). The NPP consists of drawing</span>
|
|
<span class="sd"> samples uniformly at random, therefore approximately preserving the natural prevalence of the collection.</span>
|
|
|
|
<span class="sd"> :param data: a `LabelledCollection` from which the samples will be drawn</span>
|
|
<span class="sd"> :param sample_size: integer, the number of instances in each sample; if None (default) then it is taken from</span>
|
|
<span class="sd"> qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised.</span>
|
|
<span class="sd"> :param repeats: the number of samples to generate. Default is 100.</span>
|
|
<span class="sd"> :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples</span>
|
|
<span class="sd"> will be the same every time the protocol is called)</span>
|
|
<span class="sd"> :param return_type: set to "sample_prev" (default) to get the pairs of (sample, prevalence) at each iteration, or</span>
|
|
<span class="sd"> to "labelled_collection" to get instead instances of LabelledCollection</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__init__</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">sample_size</span><span class="o">=</span><span class="kc">None</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">return_type</span><span class="o">=</span><span class="s1">'sample_prev'</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">(</span><span class="n">NPP</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">random_state</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">data</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">_get_sample_size</span><span class="p">(</span><span class="n">sample_size</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">repeats</span> <span class="o">=</span> <span class="n">repeats</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">random_state</span> <span class="o">=</span> <span class="n">random_state</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">collator</span> <span class="o">=</span> <span class="n">OnLabelledCollectionProtocol</span><span class="o">.</span><span class="n">get_collator</span><span class="p">(</span><span class="n">return_type</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="NPP.samples_parameters">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.NPP.samples_parameters">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">samples_parameters</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Return all the necessary parameters to replicate the samples as according to the NPP protocol.</span>
|
|
|
|
<span class="sd"> :return: a list of indexes that realize the NPP sampling</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">indexes</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">repeats</span><span class="p">):</span>
|
|
<span class="n">index</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">uniform_sampling_index</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span><span class="p">)</span>
|
|
<span class="n">indexes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">indexes</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="NPP.sample">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.NPP.sample">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">index</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Realizes the sample given the index of the instances.</span>
|
|
|
|
<span class="sd"> :param index: indexes of the instances to select</span>
|
|
<span class="sd"> :return: an instance of :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</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></div>
|
|
|
|
|
|
<div class="viewcode-block" id="NPP.total">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.NPP.total">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">total</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns the number of samples that will be generated (equals to "repeats")</span>
|
|
|
|
<span class="sd"> :return: int</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">repeats</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="UPP">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.UPP">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">UPP</span><span class="p">(</span><span class="n">AbstractStochasticSeededProtocol</span><span class="p">,</span> <span class="n">OnLabelledCollectionProtocol</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> A variant of :class:`APP` that, instead of using a grid of equidistant prevalence values,</span>
|
|
<span class="sd"> relies on the Kraemer algorithm for sampling unit (k-1)-simplex uniformly at random, with</span>
|
|
<span class="sd"> k the number of classes. This protocol covers the entire range of prevalence values in a</span>
|
|
<span class="sd"> statistical sense, i.e., unlike APP there is no guarantee that it is covered precisely</span>
|
|
<span class="sd"> equally for all classes, but it is preferred in cases in which the number of possible</span>
|
|
<span class="sd"> combinations of the grid values of APP makes this endeavour intractable.</span>
|
|
|
|
<span class="sd"> :param data: a `LabelledCollection` from which the samples will be drawn</span>
|
|
<span class="sd"> :param sample_size: integer, the number of instances in each sample; if None (default) then it is taken from</span>
|
|
<span class="sd"> qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised.</span>
|
|
<span class="sd"> :param repeats: the number of samples to generate. Default is 100.</span>
|
|
<span class="sd"> :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples</span>
|
|
<span class="sd"> will be the same every time the protocol is called)</span>
|
|
<span class="sd"> :param return_type: set to "sample_prev" (default) to get the pairs of (sample, prevalence) at each iteration, or</span>
|
|
<span class="sd"> to "labelled_collection" to get instead instances of LabelledCollection</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__init__</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">sample_size</span><span class="o">=</span><span class="kc">None</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">return_type</span><span class="o">=</span><span class="s1">'sample_prev'</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">(</span><span class="n">UPP</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">random_state</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">data</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">_get_sample_size</span><span class="p">(</span><span class="n">sample_size</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">repeats</span> <span class="o">=</span> <span class="n">repeats</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">random_state</span> <span class="o">=</span> <span class="n">random_state</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">collator</span> <span class="o">=</span> <span class="n">OnLabelledCollectionProtocol</span><span class="o">.</span><span class="n">get_collator</span><span class="p">(</span><span class="n">return_type</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="UPP.samples_parameters">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.UPP.samples_parameters">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">samples_parameters</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Return all the necessary parameters to replicate the samples as according to the UPP protocol.</span>
|
|
|
|
<span class="sd"> :return: a list of indexes that realize the UPP sampling</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">indexes</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">prevs</span> <span class="ow">in</span> <span class="n">F</span><span class="o">.</span><span class="n">uniform_simplex_sampling</span><span class="p">(</span><span class="n">n_classes</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">n_classes</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">repeats</span><span class="p">):</span>
|
|
<span class="n">index</span> <span class="o">=</span> <span class="bp">self</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="bp">self</span><span class="o">.</span><span class="n">sample_size</span><span class="p">,</span> <span class="o">*</span><span class="n">prevs</span><span class="p">)</span>
|
|
<span class="n">indexes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">indexes</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="UPP.sample">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.UPP.sample">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">index</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Realizes the sample given the index of the instances.</span>
|
|
|
|
<span class="sd"> :param index: indexes of the instances to select</span>
|
|
<span class="sd"> :return: an instance of :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</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></div>
|
|
|
|
|
|
<div class="viewcode-block" id="UPP.total">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.UPP.total">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">total</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns the number of samples that will be generated (equals to "repeats")</span>
|
|
|
|
<span class="sd"> :return: int</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">repeats</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="DomainMixer">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.DomainMixer">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">DomainMixer</span><span class="p">(</span><span class="n">AbstractStochasticSeededProtocol</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Generates mixtures of two domains (A and B) at controlled rates, but preserving the original class prevalence.</span>
|
|
|
|
<span class="sd"> :param domainA: one domain, an object of :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> :param domainB: another domain, an object of :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> :param sample_size: integer, the number of instances in each sample; if None (default) then it is taken from</span>
|
|
<span class="sd"> qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised.</span>
|
|
<span class="sd"> :param repeats: int, number of samples to draw for every mixture rate</span>
|
|
<span class="sd"> :param prevalence: the prevalence to preserv along the mixtures. If specified, should be an array containing</span>
|
|
<span class="sd"> one prevalence value (positive float) for each class and summing up to one. If not specified, the prevalence</span>
|
|
<span class="sd"> will be taken from the domain A (default).</span>
|
|
<span class="sd"> :param mixture_points: an integer indicating the number of points to take from a linear scale (e.g., 21 will</span>
|
|
<span class="sd"> generate the mixture points [1, 0.95, 0.9, ..., 0]), or the array of mixture values itself.</span>
|
|
<span class="sd"> the specific points</span>
|
|
<span class="sd"> :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples</span>
|
|
<span class="sd"> will be the same every time the protocol is called)</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
|
|
<span class="bp">self</span><span class="p">,</span>
|
|
<span class="n">domainA</span><span class="p">:</span> <span class="n">LabelledCollection</span><span class="p">,</span>
|
|
<span class="n">domainB</span><span class="p">:</span> <span class="n">LabelledCollection</span><span class="p">,</span>
|
|
<span class="n">sample_size</span><span class="p">,</span>
|
|
<span class="n">repeats</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
|
|
<span class="n">prevalence</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
|
<span class="n">mixture_points</span><span class="o">=</span><span class="mi">11</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">return_type</span><span class="o">=</span><span class="s1">'sample_prev'</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">(</span><span class="n">DomainMixer</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">random_state</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">A</span> <span class="o">=</span> <span class="n">domainA</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">B</span> <span class="o">=</span> <span class="n">domainB</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">_get_sample_size</span><span class="p">(</span><span class="n">sample_size</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">repeats</span> <span class="o">=</span> <span class="n">repeats</span>
|
|
<span class="k">if</span> <span class="n">prevalence</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prevalence</span> <span class="o">=</span> <span class="n">domainA</span><span class="o">.</span><span class="n">prevalence</span><span class="p">()</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prevalence</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="n">prevalence</span><span class="p">)</span>
|
|
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">prevalence</span><span class="p">)</span> <span class="o">==</span> <span class="n">domainA</span><span class="o">.</span><span class="n">n_classes</span><span class="p">,</span> \
|
|
<span class="sa">f</span><span class="s1">'wrong shape for the vector prevalence (expected </span><span class="si">{</span><span class="n">domainA</span><span class="o">.</span><span class="n">n_classes</span><span class="si">}</span><span class="s1">)'</span>
|
|
<span class="k">assert</span> <span class="n">F</span><span class="o">.</span><span class="n">check_prevalence_vector</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">prevalence</span><span class="p">),</span> \
|
|
<span class="sa">f</span><span class="s1">'the prevalence vector is not valid (either it contains values outside [0,1] or does not sum up to 1)'</span>
|
|
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">mixture_points</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">mixture_points</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linspace</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="n">mixture_points</span><span class="p">)[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">mixture_points</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="n">mixture_points</span><span class="p">)</span>
|
|
<span class="k">assert</span> <span class="nb">all</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_and</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mixture_points</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mixture_points</span><span class="o"><=</span><span class="mi">1</span><span class="p">)),</span> \
|
|
<span class="s1">'mixture_model datatype not understood (expected int or a sequence of real values in [0,1])'</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">random_state</span> <span class="o">=</span> <span class="n">random_state</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">collator</span> <span class="o">=</span> <span class="n">OnLabelledCollectionProtocol</span><span class="o">.</span><span class="n">get_collator</span><span class="p">(</span><span class="n">return_type</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="DomainMixer.samples_parameters">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.DomainMixer.samples_parameters">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">samples_parameters</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Return all the necessary parameters to replicate the samples as according to the this protocol.</span>
|
|
|
|
<span class="sd"> :return: a list of zipped indexes (from A and B) that realize the sampling</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">indexesA</span><span class="p">,</span> <span class="n">indexesB</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">propA</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">mixture_points</span><span class="p">:</span>
|
|
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">repeats</span><span class="p">):</span>
|
|
<span class="n">nA</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span> <span class="o">*</span> <span class="n">propA</span><span class="p">))</span>
|
|
<span class="n">nB</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sample_size</span><span class="o">-</span><span class="n">nA</span>
|
|
<span class="n">sampleAidx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">A</span><span class="o">.</span><span class="n">sampling_index</span><span class="p">(</span><span class="n">nA</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">prevalence</span><span class="p">)</span>
|
|
<span class="n">sampleBidx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">B</span><span class="o">.</span><span class="n">sampling_index</span><span class="p">(</span><span class="n">nB</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">prevalence</span><span class="p">)</span>
|
|
<span class="n">indexesA</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">sampleAidx</span><span class="p">)</span>
|
|
<span class="n">indexesB</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">sampleBidx</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">indexesA</span><span class="p">,</span> <span class="n">indexesB</span><span class="p">))</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="DomainMixer.sample">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.DomainMixer.sample">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">indexes</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Realizes the sample given a pair of indexes of the instances from A and B.</span>
|
|
|
|
<span class="sd"> :param indexes: indexes of the instances to select from A and B</span>
|
|
<span class="sd"> :return: an instance of :class:`qp.data.LabelledCollection`</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">indexesA</span><span class="p">,</span> <span class="n">indexesB</span> <span class="o">=</span> <span class="n">indexes</span>
|
|
<span class="n">sampleA</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">A</span><span class="o">.</span><span class="n">sampling_from_index</span><span class="p">(</span><span class="n">indexesA</span><span class="p">)</span>
|
|
<span class="n">sampleB</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">B</span><span class="o">.</span><span class="n">sampling_from_index</span><span class="p">(</span><span class="n">indexesB</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">sampleA</span><span class="o">+</span><span class="n">sampleB</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="DomainMixer.total">
|
|
<a class="viewcode-back" href="../../quapy.html#quapy.protocol.DomainMixer.total">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">total</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> Returns the number of samples that will be generated (equals to "repeats * mixture_points")</span>
|
|
|
|
<span class="sd"> :return: int</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">repeats</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mixture_points</span><span class="p">)</span></div>
|
|
</div>
|
|
|
|
|
|
|
|
<span class="c1"># aliases</span>
|
|
|
|
<span class="n">ArtificialPrevalenceProtocol</span> <span class="o">=</span> <span class="n">APP</span>
|
|
<span class="n">NaturalPrevalenceProtocol</span> <span class="o">=</span> <span class="n">NPP</span>
|
|
<span class="n">UniformPrevalenceProtocol</span> <span class="o">=</span> <span class="n">UPP</span>
|
|
</pre></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>
|
|
</section>
|
|
</div>
|
|
<script>
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
</body>
|
|
</html> |