lorenzo.volpi
/
QuaPy
forked from moreo/QuaPy
1
0
Fork 0
Code Pull Requests Activity
QuaPy/docs/build/html/quapy.data.html

1208 lines
122 KiB
HTML
Raw Permalink Normal View History

fixing sphinx doc
2024-02-07 18:31:34 +01:00
<!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/" />
doc with sphinx
2021-11-09 15:50:53 +01:00
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>quapy.data package &mdash; 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" />
doc with sphinx
2021-11-09 15:50:53 +01:00
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<!--[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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<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" />
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<link rel="prev" title="quapy.classification package" href="quapy.classification.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 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">
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
<section id="quapy-data-package">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<h1>quapy.data package<a class="headerlink" href="#quapy-data-package" title="Link to this heading"></a></h1>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
<section id="submodules">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<h2>Submodules<a class="headerlink" href="#submodules" title="Link to this heading"></a></h2>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
</section>
<section id="module-quapy.data.base">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py class">
<dt class="sig sig-object py" id="quapy.data.base.Dataset">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>training</strong> – 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</p></li>
<li><p><strong>test</strong> – 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</p></li>
<li><p><strong>vocabulary</strong> – if indicated, is a dictionary of the terms used in this textual dataset</p></li>
<li><p><strong>name</strong> – a string representing the name of the dataset</p></li>
</ul>
</dd>
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.SplitStratified">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>collection</strong> – <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></p></li>
<li><p><strong>train_size</strong> – the proportion of training documents (the rest conforms the test split)</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>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">Dataset</span></code></a></p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.binary">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Returns True if the training collection is labelled according to two classes</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>boolean</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.classes_">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>The classes according to which the training collection is labelled</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>The classes according to which the training collection is labelled</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.kFCV">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>nfolds</strong> – integer (default 5), the number of folds to generate</p></li>
<li><p><strong>nrepeats</strong> – integer (default 1), the number of rounds of k-fold cross validation to run</p></li>
<li><p><strong>random_state</strong> – integer (default 0), guarantees that the folds generated are reproducible</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>yields <cite>nfolds * nrepeats</cite> folds for k-fold cross validation as instances 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">Dataset</span></code></a></p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.load">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>train_path</strong> – string, the path to the file containing the training instances</p></li>
<li><p><strong>test_path</strong> – string, the path to the file containing the test instances</p></li>
<li><p><strong>loader_func</strong> – a custom function that implements the data loader and returns a tuple with instances and
labels</p></li>
<li><p><strong>classes</strong> – array-like, the classes according to which the instances are labelled</p></li>
<li><p><strong>loader_kwargs</strong> – any argument that the <cite>loader_func</cite> function needs in order to read the instances.
See <a class="reference internal" href="#quapy.data.base.LabelledCollection.load" title="quapy.data.base.LabelledCollection.load"><code class="xref py py-meth docutils literal notranslate"><span class="pre">LabelledCollection.load()</span></code></a> for further details.</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">Dataset</span></code></a> object</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.n_classes">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>The number of classes according to which the training collection is labelled</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>integer</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
preparing to merge
2023-02-14 17:00:50 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.reduce">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
preparing to merge
2023-02-14 17:00:50 +01:00
<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>
<dd class="field-odd"><ul class="simple">
<li><p><strong>n_train</strong> – number of training documents to keep (default 100)</p></li>
<li><p><strong>n_test</strong> – number of test documents to keep (default 100)</p></li>
</ul>
</dd>
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>self</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.stats">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">&gt;&gt;&gt; </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">&#39;kindle&#39;</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">&gt;&gt;&gt; </span><span class="n">data</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">Dataset</span><span class="o">=</span><span class="n">kindle</span> <span class="c1">#tr-instances=3821, #te-instances=21591, type=&lt;class &#39;scipy.sparse.csr.csr_matrix&#39;&gt;, #features=4403, #classes=[0 1], tr-prevs=[0.081, 0.919], te-prevs=[0.063, 0.937]</span>
</pre></div>
</div>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p><strong>show</strong> – if set to True (default), prints the stats in standard output</p>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a dictionary containing some stats of this collection for the training and test collections. The keys
are <cite>train</cite> and <cite>test</cite>, and point to dedicated dictionaries of stats, for each collection, with keys
<cite>#instances</cite> (the number of instances), <cite>type</cite> (the type representing the instances),
<cite>#features</cite> (the number of features, if the instances are in array-like format), <cite>#classes</cite> (the classes of
the collection), <cite>prevs</cite> (the prevalence values for each class)</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.train_test">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<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>
<dd class="field-odd"><p>the training and test collections</p>
</dd>
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>the training and test collections</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.Dataset.vocabulary_size">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>If the dataset is textual, and the vocabulary was indicated, returns the size of the vocabulary</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>integer</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
fixing bugs in one-vs-all
2023-02-10 19:02:17 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>instances</strong> – array-like (np.ndarray, list, or csr_matrix are supported)</p></li>
<li><p><strong>labels</strong> – array-like with the same length of instances</p></li>
<li><p><strong>classes</strong> – optional, list of classes from which labels are taken. If not specified, the classes are inferred
from the labels. The classes must be indicated in cases in which some of the labels might have no examples
(i.e., a prevalence of 0)</p></li>
</ul>
</dd>
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.X">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dd><p>An alias to self.instances</p>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
<dd class="field-odd"><p>self.instances</p>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.Xp">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dd><p>Gets the instances and the true prevalence. This is useful when implementing evaluation protocols from
fixing bugs in one-vs-all
2023-02-10 19:02:17 +01:00
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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
<dd class="field-odd"><p>a tuple <cite>(instances, prevalence)</cite> from this collection</p>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.Xy">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<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">&gt;&gt;&gt; </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>
</div>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
<dd class="field-odd"><p>a tuple <cite>(instances, labels)</cite> from this collection</p>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.binary">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Returns True if the number of classes is 2</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>boolean</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.counts">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dd><p>Returns the number of instances for each of the classes in the codeframe.</p>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>a np.ndarray of shape <cite>(n_classes)</cite> with the number of instances of each class, in the same order
as listed by <cite>self.classes_</cite></p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
preparing to merge
2023-02-14 17:00:50 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.join">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
preparing to merge
2023-02-14 17:00:50 +01:00
<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>
<dd class="field-odd"><p><strong>args</strong> – 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></p>
</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">LabelledCollection</span></code></a> representing the union of both collections</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.kFCV">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Generator of stratified folds to be used in k-fold cross validation.</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>nfolds</strong> – integer (default 5), the number of folds to generate</p></li>
<li><p><strong>nrepeats</strong> – integer (default 1), the number of rounds of k-fold cross validation to run</p></li>
<li><p><strong>random_state</strong> – integer (default 0), guarantees that the folds generated are reproducible</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>yields <cite>nfolds * nrepeats</cite> folds for k-fold cross validation</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.load">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>path</strong> – string, the path to the file containing the labelled instances</p></li>
<li><p><strong>loader_func</strong> – a custom function that implements the data loader and returns a tuple with instances and
labels</p></li>
<li><p><strong>classes</strong> – array-like, the classes according to which the instances are labelled</p></li>
<li><p><strong>loader_kwargs</strong> – any argument that the <cite>loader_func</cite> function needs in order to read the instances, i.e.,
these arguments are used to call <cite>loader_func(path, **loader_kwargs)</cite></p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">LabelledCollection</span></code></a> object</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.n_classes">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>The number of classes</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>integer</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.p">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dd><p>An alias to self.prevalence()</p>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
<dd class="field-odd"><p>self.prevalence()</p>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.prevalence">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dd><p>Returns the prevalence, or relative frequency, of the classes in the codeframe.</p>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>a np.ndarray of shape <cite>(n_classes)</cite> with the relative frequencies of each class, in the same order
as listed by <cite>self.classes_</cite></p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>size</strong> – integer, the requested size</p></li>
<li><p><strong>prevs</strong> – the prevalence for each class; the prevalence value for the last class can be lead empty since
it is constrained. E.g., for binary collections, only the prevalence <cite>p</cite> for the first class (as listed in
<cite>self.classes_</cite> can be specified, while the other class takes prevalence value <cite>1-p</cite></p></li>
<li><p><strong>shuffle</strong> – if set to True (default), shuffles the index before returning it</p></li>
fixing bugs in one-vs-all
2023-02-10 19:02:17 +01:00
<li><p><strong>random_state</strong> – seed for reproducing sampling</p></li>
updating the documentation
2021-12-06 18:25:47 +01:00
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>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> with length == <cite>size</cite> and prevalence close to <cite>prevs</cite> (or
prevalence == <cite>prevs</cite> if the exact prevalence values can be met as proportions of instances)</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling_from_index">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p><strong>index</strong> – np.ndarray</p>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>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></p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling_index">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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.
improving code quality in terms of pylint
2023-02-28 10:47:59 +01:00
For each class, the sampling is drawn with replacement if the requested prevalence is larger than
the actual prevalence of the class, or without replacement otherwise.</p>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>size</strong> – integer, the requested size</p></li>
<li><p><strong>prevs</strong> – the prevalence for each class; the prevalence value for the last class can be lead empty since
it is constrained. E.g., for binary collections, only the prevalence <cite>p</cite> for the first class (as listed in
<cite>self.classes_</cite> can be specified, while the other class takes prevalence value <cite>1-p</cite></p></li>
<li><p><strong>shuffle</strong> – if set to True (default), shuffles the index before returning it</p></li>
fixing bugs in one-vs-all
2023-02-10 19:02:17 +01:00
<li><p><strong>random_state</strong> – seed for reproducing sampling</p></li>
updating the documentation
2021-12-06 18:25:47 +01:00
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a np.ndarray of shape <cite>(size)</cite> with the indexes</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.split_random">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<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">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>train_prop</strong> – the proportion of elements to include in the left-most returned collection (typically used
as the training collection). The rest of elements are included in the right-most returned collection
(typically used as a test collection).</p></li>
<li><p><strong>random_state</strong> – if specified, guarantees reproducibility of the split.</p></li>
</ul>
</dd>
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>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>, the first one with <cite>train_prop</cite> elements, and the
second one with <cite>1-train_prop</cite> elements</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.split_stratified">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>train_prop</strong> – the proportion of elements to include in the left-most returned collection (typically used
as the training collection). The rest of elements are included in the right-most returned collection
(typically used as a test collection).</p></li>
<li><p><strong>random_state</strong> – if specified, guarantees reproducibility of the split.</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>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>, the first one with <cite>train_prop</cite> elements, and the
second one with <cite>1-train_prop</cite> elements</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.stats">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">&gt;&gt;&gt; </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">&#39;kindle&#39;</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">&gt;&gt;&gt; </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>
<span class="gp">&gt;&gt;&gt; </span><span class="c1">#instances=3821, type=&lt;class &#39;scipy.sparse.csr.csr_matrix&#39;&gt;, #features=4403, #classes=[0 1], prevs=[0.081, 0.919]</span>
</pre></div>
</div>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p><strong>show</strong> – if set to True (default), prints the stats in standard output</p>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a dictionary containing some stats of this collection. Keys include <cite>#instances</cite> (the number of
instances), <cite>type</cite> (the type representing the instances), <cite>#features</cite> (the number of features, if the
instances are in array-like format), <cite>#classes</cite> (the classes of the collection), <cite>prevs</cite> (the prevalence
values for each class)</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.uniform_sampling">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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
improving code quality in terms of pylint
2023-02-28 10:47:59 +01:00
with replacement if the requested size is greater than the number of instances, or without replacement
updating the documentation
2021-12-06 18:25:47 +01:00
otherwise.</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>size</strong> – integer, the requested size</p></li>
<li><p><strong>random_state</strong> – if specified, guarantees reproducibility of the split.</p></li>
</ul>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>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> with length == <cite>size</cite></p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.uniform_sampling_index">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Returns an index to be used to extract a uniform sample of desired size. The sampling is drawn
improving code quality in terms of pylint
2023-02-28 10:47:59 +01:00
with replacement if the requested size is greater than the number of instances, or without replacement
updating the documentation
2021-12-06 18:25:47 +01:00
otherwise.</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>size</strong> – integer, the size of the uniform sample</p></li>
<li><p><strong>random_state</strong> – if specified, guarantees reproducibility of the split.</p></li>
</ul>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a np.ndarray of shape <cite>(size)</cite> with the indexes</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py property">
<dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.y">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dd><p>An alias to self.labels</p>
updating the documentation
2021-12-06 18:25:47 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
<dd class="field-odd"><p>self.labels</p>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
</dd></dl>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
</section>
<section id="module-quapy.data.datasets">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py function">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_IFCB">
testing IFCB dataset
2024-02-08 14:33:22 +01:00
<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>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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">
testing IFCB dataset
2024-02-08 14:33:22 +01:00
<li><p><strong>single_sample_train</strong> – a boolean. If true, it will return the train dataset as a
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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).
testing IFCB dataset
2024-02-08 14:33:22 +01:00
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>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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
testing IFCB dataset
2024-02-08 14:33:22 +01:00
<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>,
fixing sphinx doc
2024-02-07 18:31:34 +01:00
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">&#x2192;</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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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., &amp; 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.</a>
and
<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego, P., Castano, A., Quevedo, J. R., &amp; del Coz, J. J. (2019).
Dynamic ensemble selection for quantification tasks.
Information Fusion, 45, 1-15.</a>.
fixing sphinx doc
2024-02-07 18:31:34 +01:00
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
updating the documentation
2021-12-06 18:25:47 +01:00
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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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 (from the UCI ML repository) about the datasets</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py function">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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">&#x2192;</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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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., &amp; 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.</a>
and
<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego, P., Castano, A., Quevedo, J. R., &amp; 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, and so Pérez-Gállego et al. adopted a 5FCVx2 evaluation
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">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<span class="gp">&gt;&gt;&gt; </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">&quot;yeast&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </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>
updating the documentation
2021-12-06 18:25:47 +01:00
<span class="gp">&gt;&gt;&gt; </span> <span class="o">...</span>
</pre></div>
</div>
<p>The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI_DATASETS</cite></p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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 (from the UCI ML repository) about the datasets</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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">&#x2192;</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">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
<span class="gp">&gt;&gt;&gt; </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">&quot;dry-bean&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </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">&gt;&gt;&gt; </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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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">&#x2192;</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">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
<span class="gp">&gt;&gt;&gt; </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">&quot;dry-bean&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </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">&gt;&gt;&gt; </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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_lequa2022">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<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.
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.
We refer to the <a class="reference external" href="https://ceur-ws.org/Vol-3180/paper-146.pdf">Esuli, A., Moreo, A., Sebastiani, F., &amp; Sperduti, G. (2022).
A Detailed Overview of LeQua&#64; CLEF 2022: Learning to Quantify.</a> for a detailed description
on the tasks and datasets.</p>
<p>The datasets are downloaded only once, and stored for fast reuse.</p>
<p>See <cite>lequa2022_experiments.py</cite> provided in the example folder, that can serve as a guide on how to use these
datasets.</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>task</strong> – a string representing the task name; valid ones are T1A, T1B, T2A, and T2B</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, 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
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_reviews">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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">&#x2192;</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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>.
The list of valid dataset names can be accessed in <cite>quapy.data.datasets.REVIEWS_SENTIMENT_DATASETS</cite></p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>dataset_name</strong> – the name of the dataset: valid ones are ‘hp’, ‘kindle’, ‘imdb’</p></li>
<li><p><strong>tfidf</strong> – set to True to transform the raw documents into tfidf weighted matrices</p></li>
<li><p><strong>min_df</strong> – minimun number of documents that should contain a term in order for the term to be
kept (ignored if tfidf==False)</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>pickle</strong> – set to True to pickle the Dataset object the first time it is generated, in order to allow for
faster subsequent invokations</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.datasets.fetch_twitter">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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">&#x2192;</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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
Note that the datasets ‘semeval13’, ‘semeval14’, ‘semeval15’ share the same training set.
The list of valid dataset names corresponding to training sets can be accessed in
<cite>quapy.data.datasets.TWITTER_SENTIMENT_DATASETS_TRAIN</cite>, while the test sets can be accessed in
<cite>quapy.data.datasets.TWITTER_SENTIMENT_DATASETS_TEST</cite></p>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>dataset_name</strong> – the name of the dataset: valid ones are ‘gasp’, ‘hcr’, ‘omd’, ‘sanders’, ‘semeval13’,
‘semeval14’, ‘semeval15’, ‘semeval16’, ‘sst’, ‘wa’, ‘wb’</p></li>
<li><p><strong>for_model_selection</strong> – if True, then returns the train split as the training set and the devel split
as the test set; if False, then returns the train+devel split as the training set and the test set as the
test set</p></li>
<li><p><strong>min_df</strong> – minimun number of documents that should contain a term in order for the term to be kept</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>pickle</strong> – set to True to pickle the Dataset object the first time it is generated, in order to allow for
faster subsequent invokations</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd>
</dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.datasets.warn">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd></dd></dl>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
</section>
<section id="module-quapy.data.preprocessing">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py class">
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
updating the documentation
2021-12-06 18:25:47 +01:00
<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
<a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html">CountVectorizer</a></p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><p><strong>kwargs</strong> – <p>keyworded arguments from
<a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html">CountVectorizer</a></p>
updating the documentation
2021-12-06 18:25:47 +01:00
</p>
</dd>
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.add_word">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>word</strong> – string, surface form of the token</p></li>
<li><p><strong>id</strong> – integer, numerical value to assign to the token (leave as None for indicating the next valid id,
default)</p></li>
<li><p><strong>nogaps</strong> – if set to True (default) asserts that the id indicated leads to no numerical gaps with
precedent ids stored so far</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>integer, the numerical id for the new token</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.fit">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Fits the transformer, i.e., decides on the vocabulary, given a list of strings.</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd class="field-odd"><p><strong>X</strong> – a list of strings</p>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd class="field-even"><p>self</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.fit_transform">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Fits the transform on <cite>X</cite> and transforms it.</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>X</strong> – a list of strings</p></li>
<li><p><strong>n_jobs</strong> – the number of parallel workers to carry out this task</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a <cite>np.ndarray</cite> of numerical ids</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.transform">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Transforms the strings in <cite>X</cite> as lists of numerical ids</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>X</strong> – a list of strings</p></li>
<li><p><strong>n_jobs</strong> – the number of parallel workers to carry out this task</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a <cite>np.ndarray</cite> of numerical ids</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py method">
<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.vocabulary_size">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd><p>Gets the length of the vocabulary according to which the document tokens have been indexed</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p>integer</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.preprocessing.index">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>dataset</strong> – 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> object where the instances of training and test documents
are lists of str</p></li>
<li><p><strong>min_df</strong> – minimum number of occurrences below which the term is replaced by a <cite>UNK</cite> index</p></li>
<li><p><strong>inplace</strong> – whether or not to apply the transformation inplace (True), or to a new copy (False, default)</p></li>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<li><p><strong>kwargs</strong> – the rest of parameters of the transformation (as for sklearn’s
<cite>CountVectorizer &lt;https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html&gt;_</cite>)</p></li>
updating the documentation
2021-12-06 18:25:47 +01:00
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>a new <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> (if inplace=False) or a reference to the current
<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> (inplace=True) consisting of lists of integer values representing indices.</p>
</dd>
updating the documentation
2021-12-06 18:25:47 +01:00
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.preprocessing.reduce_columns">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>dataset</strong> – 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> in which instances are represented in sparse format (any
subtype of scipy.sparse.spmatrix)</p></li>
<li><p><strong>min_df</strong> – integer, minimum number of instances below which the columns are removed</p></li>
<li><p><strong>inplace</strong> – whether or not to apply the transformation inplace (True), or to a new copy (False, default)</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a new <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> (if inplace=False) or a reference to the current
<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> (inplace=True) where the dimensions corresponding to infrequent terms
in the training set have been removed</p>
</dd>
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.preprocessing.standardize">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>dataset</strong> – 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> object</p></li>
<li><p><strong>inplace</strong> – set to True if the transformation is to be applied inplace, or to False (default) if a new
<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> is to be returned</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>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>
updating the documentation
2021-12-06 18:25:47 +01:00
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.preprocessing.text2tfidf">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>dataset</strong> – 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> where the instances of training and test collections are
lists of str</p></li>
<li><p><strong>min_df</strong> – minimum number of occurrences for a word to be considered as part of the vocabulary (default 3)</p></li>
<li><p><strong>sublinear_tf</strong> – whether or not to apply the log scalling to the tf counters (default True)</p></li>
<li><p><strong>inplace</strong> – whether or not to apply the transformation inplace (True), or to a new copy (False, default)</p></li>
<li><p><strong>kwargs</strong> – the rest of parameters of the transformation (as for sklearn’s
<a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html">TfidfVectorizer</a>)</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a new <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> in <cite>csr_matrix</cite> format (if inplace=False) or a reference to the
current Dataset (if inplace=True) where the instances are stored in a <cite>csr_matrix</cite> of real-valued tfidf scores</p>
</dd>
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
</section>
<section id="module-quapy.data.reader">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.reader.binarize">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
updating the documentation
2021-12-06 18:25:47 +01:00
<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">&gt;&gt;&gt; </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">&gt;&gt;&gt; </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>
</pre></div>
</div>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>y</strong> – array-like of labels</p></li>
<li><p><strong>pos_class</strong> – integer, the positive class</p></li>
</ul>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a binary np.ndarray, in which values 1 corresponds to positions in whcih <cite>y</cite> had <cite>pos_class</cite> labels, and
0 otherwise</p>
</dd>
</dl>
</dd></dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.reader.from_csv">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Reads a csv file in which columns are separated by ‘,’.
File format &lt;label&gt;,&lt;feat1&gt;,&lt;feat2&gt;,…,&lt;featn&gt;</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>path</strong> – path to the csv file</p></li>
<li><p><strong>encoding</strong> – the text encoding used to open the file</p></li>
</ul>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a np.ndarray for the labels and a ndarray (float) for the covariates</p>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd>
</dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.reader.from_sparse">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Reads a labelled collection of real-valued instances expressed in sparse format
File format &lt;-1 or 0 or 1&gt;[s col(int):val(float)]</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd class="field-odd"><p><strong>path</strong> – path to the labelled collection</p>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a <cite>csr_matrix</cite> containing the instances (rows), and a ndarray containing the labels</p>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd>
</dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.reader.from_text">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Reads a labelled colletion of documents.
File fomart &lt;0 or 1&gt; &lt;document&gt;</p>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><ul class="simple">
<li><p><strong>path</strong> – path to the labelled collection</p></li>
<li><p><strong>encoding</strong> – the text encoding used to open the file</p></li>
<li><p><strong>verbose</strong> – if &gt;0 (default) shows some progress information in standard output</p></li>
</ul>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd class="field-even"><p>a list of sentences, and a list of labels</p>
</dd>
</dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="quapy.data.reader.reindex_labels">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
<dd><p>Re-indexes a list of labels as a list of indexes, and returns the classnames corresponding to the indexes.
updating the documentation
2021-12-06 18:25:47 +01:00
E.g.:</p>
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">reindex_labels</span><span class="p">([</span><span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;A&#39;</span><span class="p">,</span> <span class="s1">&#39;C&#39;</span><span class="p">])</span>
<span class="gp">&gt;&gt;&gt; </span><span class="p">(</span><span class="n">array</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="mi">2</span><span class="p">]),</span> <span class="n">array</span><span class="p">([</span><span class="s1">&#39;A&#39;</span><span class="p">,</span> <span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;C&#39;</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;&lt;U1&#39;</span><span class="p">))</span>
</pre></div>
</div>
<dl class="field-list simple">
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-odd"><p><strong>y</strong> – the list or array of original labels</p>
</dd>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
<dt class="field-even">Returns<span class="colon">:</span></dt>
updating the documentation
2021-12-06 18:25:47 +01:00
<dd class="field-even"><p>a ndarray (int) of class indexes, and a ndarray of classnames corresponding to the indexes.</p>
</dd>
</dl>
doc with sphinx
2021-11-09 15:50:53 +01:00
</dd></dl>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
</section>
<section id="module-quapy.data">
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-quapy.data" title="Link to this heading"></a></h2>
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
2021-11-22 18:10:48 +01:00
</section>
</section>
doc with sphinx
2021-11-09 15:50:53 +01:00
fixing sphinx doc
2024-02-07 18:31:34 +01:00
</div>
doc with sphinx
2021-11-09 15:50:53 +01:00
</div>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<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>
doc with sphinx
2021-11-09 15:50:53 +01:00
fixing sphinx doc
2024-02-07 18:31:34 +01:00
<hr/>
<div role="contentinfo">
<p>&#169; Copyright 2024, Alejandro Moreo.</p>
adding documentation and adding one new example
2023-02-08 19:06:53 +01:00
</div>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
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>
doc with sphinx
2021-11-09 15:50:53 +01:00
</div>
</div>
fixing sphinx doc
2024-02-07 18:31:34 +01:00
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
doc with sphinx
2021-11-09 15:50:53 +01:00
</html>