moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity
QuaPy/docs/build/html/_modules/quapy/data/reader.html

590 lines
34 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>quapy.data.reader &#8212; QuaPy: A Python-based open-source framework for quantification 0.2.1 documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=90905a2f556bf617f1a9" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=90905a2f556bf617f1a9" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../../_static/sphinx-design.min.css?v=95c83b7e" />
<link rel="stylesheet" type="text/css" href="../../../_static/custom.css?v=9f2a2228" />
<!-- So that users can add custom icons -->
<script defer src="../../../_static/scripts/fontawesome.js?digest=90905a2f556bf617f1a9"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=90905a2f556bf617f1a9" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=90905a2f556bf617f1a9" />
<script src="../../../_static/documentation_options.js?v=37f418d5"></script>
<script src="../../../_static/doctools.js?v=fd6eb6e6"></script>
<script src="../../../_static/sphinx_highlight.js?v=6ffebe34"></script>
<script src="../../../_static/design-tabs.js?v=f930bc37"></script>
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/quapy/data/reader';</script>
<script>DOCUMENTATION_OPTIONS.search_as_you_type = false;</script>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="" />
<script src="../../../_static/searchtools.js"></script>
<script src="../../../_static/language_data.js"></script>
<script src="../../../searchindex.js"></script>
</head>
<body data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header id="pst-header" class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../../index.html">
<img src="../../../_static/quapy_logo.png" class="logo__image only-light" alt="QuaPy: A Python-based open-source framework for quantification 0.2.1 documentation - Home"/>
<img src="../../../_static/quapy_logo_dark.png" class="logo__image only-dark pst-js-only" alt="QuaPy: A Python-based open-source framework for quantification 0.2.1 documentation - Home"/>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<nav>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item ">
<a class="nav-link nav-internal" href="../../../index.html">
Home
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../../../manuals.html">
Manuals
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../../../quapy.html">
API
</a>
</li>
</ul>
</nav></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<div class="theme-switch-container dropdown pst-js-only" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Color mode">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button dropdown-toggle" aria-label="Color mode" data-bs-toggle="dropdown">
<i class="theme-switch fa-solid fa-sun fa-lg fa-fw" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg fa-fw" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg fa-fw" data-mode="auto" title="System Settings"></i>
</button>
<ul class="dropdown-menu dropdown-menu-end">
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="auto"><i class="fa-solid fa-circle-half-stroke fa-lg fa-fw me-1"></i>System Settings</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="light"><i class="fa-solid fa-sun fa-lg fa-fw me-1"></i>Light</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="dark"><i class="fa-solid fa-moon fa-lg fa-fw me-1"></i>Dark</button></li>
</ul>
</div></div>
<div class="navbar-item"><ul class="navbar-icon-links"
aria-label="Icon Links">
<li class="nav-item">
<a href="https://github.com/HLT-ISTI/QuaPy" title="GitHub" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-github fa-lg" aria-hidden="true"></i><span class="visually-hidden">GitHub</span></a>
</li>
</ul></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar hide-on-wide">
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<nav>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item ">
<a class="nav-link nav-internal" href="../../../index.html">
Home
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../../../manuals.html">
Manuals
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../../../quapy.html">
API
</a>
</li>
</ul>
</nav></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<div class="theme-switch-container dropdown pst-js-only" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Color mode">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button dropdown-toggle" aria-label="Color mode" data-bs-toggle="dropdown">
<i class="theme-switch fa-solid fa-sun fa-lg fa-fw" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg fa-fw" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg fa-fw" data-mode="auto" title="System Settings"></i>
</button>
<ul class="dropdown-menu dropdown-menu-end">
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="auto"><i class="fa-solid fa-circle-half-stroke fa-lg fa-fw me-1"></i>System Settings</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="light"><i class="fa-solid fa-sun fa-lg fa-fw me-1"></i>Light</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="dark"><i class="fa-solid fa-moon fa-lg fa-fw me-1"></i>Dark</button></li>
</ul>
</div></div>
<div class="navbar-item"><ul class="navbar-icon-links"
aria-label="Icon Links">
<li class="nav-item">
<a href="https://github.com/HLT-ISTI/QuaPy" title="GitHub" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-github fa-lg" aria-hidden="true"></i><span class="visually-hidden">GitHub</span></a>
</li>
</ul></div>
</div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
<div class="sidebar-primary-item">
<div id="ethical-ad-placement"
class="flat"
data-ea-publisher="readthedocs"
data-ea-type="readthedocs-sidebar"
data-ea-manual="true">
</div></div>
</div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumb" class="d-print-none">
<ul class="bd-breadcrumbs">
<li class="breadcrumb-item breadcrumb-home">
<a href="../../../index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">quapy.data.reader</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for quapy.data.reader</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">scipy.sparse</span><span class="w"> </span><span class="kn">import</span> <span class="n">dok_matrix</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tqdm</span><span class="w"> </span><span class="kn">import</span> <span class="n">tqdm</span>
<div class="viewcode-block" id="from_text">
<a class="viewcode-back" href="../../../quapy.data.html#quapy.data.reader.from_text">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">from_text</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;utf-8&#39;</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">class2int</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Reads a labelled colletion of documents.</span>
<span class="sd"> File fomart &lt;0 or 1&gt;\t&lt;document&gt;\n</span>
<span class="sd"> :param path: path to the labelled collection</span>
<span class="sd"> :param encoding: the text encoding used to open the file</span>
<span class="sd"> :param verbose: if &gt;0 (default) shows some progress information in standard output</span>
<span class="sd"> :return: a list of sentences, and a list of labels</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">all_sentences</span><span class="p">,</span> <span class="n">all_labels</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span>
<span class="k">if</span> <span class="n">verbose</span><span class="o">&gt;</span><span class="mi">0</span><span class="p">:</span>
<span class="n">file</span> <span class="o">=</span> <span class="n">tqdm</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">&#39;rt&#39;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">)</span><span class="o">.</span><span class="n">readlines</span><span class="p">(),</span> <span class="sa">f</span><span class="s1">&#39;loading </span><span class="si">{</span><span class="n">path</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">file</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">&#39;rt&#39;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">)</span><span class="o">.</span><span class="n">readlines</span><span class="p">()</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">file</span><span class="p">:</span>
<span class="n">line</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
<span class="k">if</span> <span class="n">line</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">label</span><span class="p">,</span> <span class="n">sentence</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\t</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="n">sentence</span> <span class="o">=</span> <span class="n">sentence</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
<span class="k">if</span> <span class="n">class2int</span><span class="p">:</span>
<span class="n">label</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">label</span><span class="p">)</span>
<span class="k">if</span> <span class="n">sentence</span><span class="p">:</span>
<span class="n">all_sentences</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">sentence</span><span class="p">)</span>
<span class="n">all_labels</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">label</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;format error in </span><span class="si">{</span><span class="n">line</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">all_sentences</span><span class="p">,</span> <span class="n">all_labels</span></div>
<div class="viewcode-block" id="from_sparse">
<a class="viewcode-back" href="../../../quapy.data.html#quapy.data.reader.from_sparse">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">from_sparse</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Reads a labelled collection of real-valued instances expressed in sparse format</span>
<span class="sd"> File format &lt;-1 or 0 or 1&gt;[\s col(int):val(float)]\n</span>
<span class="sd"> :param path: path to the labelled collection</span>
<span class="sd"> :return: a `csr_matrix` containing the instances (rows), and a ndarray containing the labels</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span><span class="w"> </span><span class="nf">split_col_val</span><span class="p">(</span><span class="n">col_val</span><span class="p">):</span>
<span class="n">col</span><span class="p">,</span> <span class="n">val</span> <span class="o">=</span> <span class="n">col_val</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;:&#39;</span><span class="p">)</span>
<span class="n">col</span><span class="p">,</span> <span class="n">val</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">col</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">val</span><span class="p">)</span>
<span class="k">return</span> <span class="n">col</span><span class="p">,</span> <span class="n">val</span>
<span class="n">all_documents</span><span class="p">,</span> <span class="n">all_labels</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span>
<span class="n">max_col</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">&#39;rt&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">readlines</span><span class="p">(),</span> <span class="sa">f</span><span class="s1">&#39;loading </span><span class="si">{</span><span class="n">path</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">):</span>
<span class="n">parts</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
<span class="k">if</span> <span class="n">parts</span><span class="p">:</span>
<span class="n">all_labels</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">parts</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span>
<span class="n">cols</span><span class="p">,</span> <span class="n">vals</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="p">[</span><span class="n">split_col_val</span><span class="p">(</span><span class="n">col_val</span><span class="p">)</span> <span class="k">for</span> <span class="n">col_val</span> <span class="ow">in</span> <span class="n">parts</span><span class="p">[</span><span class="mi">1</span><span class="p">:]])</span>
<span class="n">cols</span><span class="p">,</span> <span class="n">vals</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">cols</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">vals</span><span class="p">)</span>
<span class="n">max_col</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">max_col</span><span class="p">,</span> <span class="n">cols</span><span class="o">.</span><span class="n">max</span><span class="p">())</span>
<span class="n">all_documents</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">cols</span><span class="p">,</span> <span class="n">vals</span><span class="p">))</span>
<span class="n">n_docs</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">all_labels</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">dok_matrix</span><span class="p">((</span><span class="n">n_docs</span><span class="p">,</span> <span class="n">max_col</span> <span class="o">+</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="p">(</span><span class="n">cols</span><span class="p">,</span> <span class="n">vals</span><span class="p">)</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="nb">enumerate</span><span class="p">(</span><span class="n">all_documents</span><span class="p">),</span> <span class="n">total</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="n">all_documents</span><span class="p">),</span>
<span class="n">desc</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;\-- filling matrix of shape </span><span class="si">{</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">):</span>
<span class="n">X</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">cols</span><span class="p">]</span> <span class="o">=</span> <span class="n">vals</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">tocsr</span><span class="p">()</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">all_labels</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">X</span><span class="p">,</span> <span class="n">y</span></div>
<div class="viewcode-block" id="from_csv">
<a class="viewcode-back" href="../../../quapy.data.html#quapy.data.reader.from_csv">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">from_csv</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;utf-8&#39;</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Reads a csv file in which columns are separated by &#39;,&#39;.</span>
<span class="sd"> File format &lt;label&gt;,&lt;feat1&gt;,&lt;feat2&gt;,...,&lt;featn&gt;\n</span>
<span class="sd"> :param path: path to the csv file</span>
<span class="sd"> :param encoding: the text encoding used to open the file</span>
<span class="sd"> :return: a np.ndarray for the labels and a ndarray (float) for the covariates</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">X</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">instance</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">&#39;rt&#39;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">)</span><span class="o">.</span><span class="n">readlines</span><span class="p">(),</span> <span class="n">desc</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;reading </span><span class="si">{</span><span class="n">path</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">):</span>
<span class="n">yi</span><span class="p">,</span> <span class="o">*</span><span class="n">xi</span> <span class="o">=</span> <span class="n">instance</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;,&#39;</span><span class="p">)</span>
<span class="n">X</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="nb">float</span><span class="p">,</span><span class="n">xi</span><span class="p">)))</span>
<span class="n">y</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">yi</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">y</span><span class="p">)</span>
<span class="k">return</span> <span class="n">X</span><span class="p">,</span> <span class="n">y</span></div>
<div class="viewcode-block" id="reindex_labels">
<a class="viewcode-back" href="../../../quapy.data.html#quapy.data.reader.reindex_labels">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">reindex_labels</span><span class="p">(</span><span class="n">y</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Re-indexes a list of labels as a list of indexes, and returns the classnames corresponding to the indexes.</span>
<span class="sd"> E.g.:</span>
<span class="sd"> &gt;&gt;&gt; reindex_labels([&#39;B&#39;, &#39;B&#39;, &#39;A&#39;, &#39;C&#39;])</span>
<span class="sd"> &gt;&gt;&gt; (array([1, 1, 0, 2]), array([&#39;A&#39;, &#39;B&#39;, &#39;C&#39;], dtype=&#39;&lt;U1&#39;))</span>
<span class="sd"> :param y: the list or array of original labels</span>
<span class="sd"> :return: a ndarray (int) of class indexes, and a ndarray of classnames corresponding to the indexes.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">y</span><span class="p">)</span>
<span class="n">classnames</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="nb">sorted</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">unique</span><span class="p">(</span><span class="n">y</span><span class="p">)))</span>
<span class="n">label2index</span> <span class="o">=</span> <span class="p">{</span><span class="n">label</span><span class="p">:</span> <span class="n">index</span> <span class="k">for</span> <span class="n">index</span><span class="p">,</span> <span class="n">label</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">classnames</span><span class="p">)}</span>
<span class="n">indexed</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="n">y</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">int</span><span class="p">)</span>
<span class="k">for</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">classnames</span><span class="p">:</span>
<span class="n">indexed</span><span class="p">[</span><span class="n">y</span><span class="o">==</span><span class="n">label</span><span class="p">]</span> <span class="o">=</span> <span class="n">label2index</span><span class="p">[</span><span class="n">label</span><span class="p">]</span>
<span class="k">return</span> <span class="n">indexed</span><span class="p">,</span> <span class="n">classnames</span></div>
<div class="viewcode-block" id="binarize">
<a class="viewcode-back" href="../../../quapy.data.html#quapy.data.reader.binarize">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">binarize</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">pos_class</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Binarizes a categorical array-like collection of labels towards the positive class `pos_class`. E.g.,:</span>
<span class="sd"> &gt;&gt;&gt; binarize([1, 2, 3, 1, 1, 0], pos_class=2)</span>
<span class="sd"> &gt;&gt;&gt; array([0, 1, 0, 0, 0, 0])</span>
<span class="sd"> :param y: array-like of labels</span>
<span class="sd"> :param pos_class: integer, the positive class</span>
<span class="sd"> :return: a binary np.ndarray, in which values 1 corresponds to positions in whcih `y` had `pos_class` labels, and</span>
<span class="sd"> 0 otherwise</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">y</span><span class="p">)</span>
<span class="n">ybin</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">y</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">int</span><span class="p">)</span>
<span class="n">ybin</span><span class="p">[</span><span class="n">y</span> <span class="o">==</span> <span class="n">pos_class</span><span class="p">]</span> <span class="o">=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">ybin</span></div>
</pre></div>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
</div>
</footer>
</div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../../../_static/scripts/bootstrap.js?digest=90905a2f556bf617f1a9"></script>
<script defer src="../../../_static/scripts/pydata-sphinx-theme.js?digest=90905a2f556bf617f1a9"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Alejandro Moreo.
<br/>
</p>
</div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 9.0.4.
<br/>
</p>
</div>
</div>
<div class="footer-items__end">
<div class="footer-item">
<p class="theme-version">
<!-- # L10n: Setting the PST URL as an argument as this does not need to be localized -->
Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.20.0.
</p></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink