| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>LDAModel — PySpark 3.2.2 documentation</title> |
| |
| <link rel="stylesheet" href="../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script> |
| <script src="../../_static/jquery.js"></script> |
| <script src="../../_static/underscore.js"></script> |
| <script src="../../_static/doctools.js"></script> |
| <script src="../../_static/language_data.js"></script> |
| <script src="../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <link rel="next" title="BinaryClassificationMetrics" href="pyspark.mllib.evaluation.BinaryClassificationMetrics.html" /> |
| <link rel="prev" title="LDA" href="pyspark.mllib.clustering.LDA.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../index.html"> |
| |
| <img src="../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../user_guide/index.html">User Guide</a> |
| </li> |
| |
| <li class="nav-item active"> |
| <a class="nav-link" href="../index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../migration_guide/index.html">Migration Guide</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.sql.html">Spark SQL</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.pandas/index.html">Pandas API on Spark</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.ss.html">Structured Streaming</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.ml.html">MLlib (DataFrame-based)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.streaming.html">Spark Streaming</a> |
| </li> |
| |
| |
| |
| <li class="active"> |
| <a href="../pyspark.mllib.html">MLlib (RDD-based)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.html">Spark Core</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.resource.html">Resource Management</a> |
| </li> |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <div class="section" id="ldamodel"> |
| <h1>LDAModel<a class="headerlink" href="#ldamodel" title="Permalink to this headline">¶</a></h1> |
| <dl class="py class"> |
| <dt id="pyspark.mllib.clustering.LDAModel"> |
| <em class="property">class </em><code class="sig-prename descclassname">pyspark.mllib.clustering.</code><code class="sig-name descname">LDAModel</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">java_model</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/clustering.html#LDAModel"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel" title="Permalink to this definition">¶</a></dt> |
| <dd><p>A clustering model derived from the LDA method.</p> |
| <p>Latent Dirichlet Allocation (LDA), a topic model designed for text documents. |
| Terminology</p> |
| <ul class="simple"> |
| <li><p>“word” = “term”: an element of the vocabulary</p></li> |
| <li><p>“token”: instance of a term appearing in a document</p></li> |
| <li><p>“topic”: multinomial distribution over words representing some concept</p></li> |
| </ul> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.5.0.</span></p> |
| </div> |
| <p class="rubric">Notes</p> |
| <p>See the original LDA paper (journal version) <a class="reference internal" href="#r870f3a018ef8-1" id="id1">[1]</a></p> |
| <dl class="citation"> |
| <dt class="label" id="r870f3a018ef8-1"><span class="brackets"><a class="fn-backref" href="#id1">1</a></span></dt> |
| <dd><p>Blei, D. et al. “Latent Dirichlet Allocation.” |
| J. Mach. Learn. Res. 3 (2003): 993-1022. |
| <a class="reference external" href="https://www.jmlr.org/papers/v3/blei03a">https://www.jmlr.org/papers/v3/blei03a</a></p> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">numpy.testing</span> <span class="kn">import</span> <span class="n">assert_almost_equal</span><span class="p">,</span> <span class="n">assert_equal</span> |
| <span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="gp">... </span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">])],</span> |
| <span class="gp">... </span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="p">{</span><span class="mi">0</span><span class="p">:</span> <span class="mf">1.0</span><span class="p">})],</span> |
| <span class="gp">... </span><span class="p">]</span> |
| <span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">model</span> <span class="o">=</span> <span class="n">LDA</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">model</span><span class="o">.</span><span class="n">vocabSize</span><span class="p">()</span> |
| <span class="go">2</span> |
| <span class="gp">>>> </span><span class="n">model</span><span class="o">.</span><span class="n">describeTopics</span><span class="p">()</span> |
| <span class="go">[([1, 0], [0.5..., 0.49...]), ([0, 1], [0.5..., 0.49...])]</span> |
| <span class="gp">>>> </span><span class="n">model</span><span class="o">.</span><span class="n">describeTopics</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> |
| <span class="go">[([1], [0.5...]), ([0], [0.5...])]</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">topics</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">topicsMatrix</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">topics_expect</span> <span class="o">=</span> <span class="n">array</span><span class="p">([[</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">]])</span> |
| <span class="gp">>>> </span><span class="n">assert_almost_equal</span><span class="p">(</span><span class="n">topics</span><span class="p">,</span> <span class="n">topics_expect</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span> <span class="nn">os</span><span class="o">,</span> <span class="nn">tempfile</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span> |
| <span class="gp">>>> </span><span class="n">path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">sameModel</span> <span class="o">=</span> <span class="n">LDAModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">assert_equal</span><span class="p">(</span><span class="n">sameModel</span><span class="o">.</span><span class="n">topicsMatrix</span><span class="p">(),</span> <span class="n">model</span><span class="o">.</span><span class="n">topicsMatrix</span><span class="p">())</span> |
| <span class="gp">>>> </span><span class="n">sameModel</span><span class="o">.</span><span class="n">vocabSize</span><span class="p">()</span> <span class="o">==</span> <span class="n">model</span><span class="o">.</span><span class="n">vocabSize</span><span class="p">()</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="k">try</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">rmtree</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">pass</span> |
| </pre></div> |
| </div> |
| <p class="rubric">Methods</p> |
| <table class="longtable table autosummary"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.clustering.LDAModel.call" title="pyspark.mllib.clustering.LDAModel.call"><code class="xref py py-obj docutils literal notranslate"><span class="pre">call</span></code></a>(name, *a)</p></td> |
| <td><p>Call method of java_model</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.clustering.LDAModel.describeTopics" title="pyspark.mllib.clustering.LDAModel.describeTopics"><code class="xref py py-obj docutils literal notranslate"><span class="pre">describeTopics</span></code></a>([maxTermsPerTopic])</p></td> |
| <td><p>Return the topics described by weighted terms.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.clustering.LDAModel.load" title="pyspark.mllib.clustering.LDAModel.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(sc, path)</p></td> |
| <td><p>Load the LDAModel from disk.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.clustering.LDAModel.save" title="pyspark.mllib.clustering.LDAModel.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(sc, path)</p></td> |
| <td><p>Save this model to the given path.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.clustering.LDAModel.topicsMatrix" title="pyspark.mllib.clustering.LDAModel.topicsMatrix"><code class="xref py py-obj docutils literal notranslate"><span class="pre">topicsMatrix</span></code></a>()</p></td> |
| <td><p>Inferred topics, where each topic is represented by a distribution over terms.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.clustering.LDAModel.vocabSize" title="pyspark.mllib.clustering.LDAModel.vocabSize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vocabSize</span></code></a>()</p></td> |
| <td><p>Vocabulary size (number of terms or terms in the vocabulary)</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p class="rubric">Methods Documentation</p> |
| <dl class="py method"> |
| <dt id="pyspark.mllib.clustering.LDAModel.call"> |
| <code class="sig-name descname">call</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">name</span></em>, <em class="sig-param"><span class="o">*</span><span class="n">a</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel.call" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Call method of java_model</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.clustering.LDAModel.describeTopics"> |
| <code class="sig-name descname">describeTopics</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">maxTermsPerTopic</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/clustering.html#LDAModel.describeTopics"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel.describeTopics" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Return the topics described by weighted terms.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.6.0.</span></p> |
| </div> |
| <div class="admonition warning"> |
| <p class="admonition-title">Warning</p> |
| <p>If vocabSize and k are large, this can return a large object!</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl class="simple"> |
| <dt><strong>maxTermsPerTopic</strong><span class="classifier">int, optional</span></dt><dd><p>Maximum number of terms to collect for each topic. |
| (default: vocabulary size)</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt>list</dt><dd><p>Array over topics. Each topic is represented as a pair of |
| matching arrays: (term indices, term weights in topic). |
| Each topic’s terms are sorted in order of decreasing weight.</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.clustering.LDAModel.load"> |
| <em class="property">classmethod </em><code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span></em>, <em class="sig-param"><span class="n">path</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/clustering.html#LDAModel.load"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load the LDAModel from disk.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.5.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd></dd> |
| <dt><strong>path</strong><span class="classifier">str</span></dt><dd><p>Path to where the model is stored.</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.clustering.LDAModel.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span></em>, <em class="sig-param"><span class="n">path</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save this model to the given path.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.clustering.LDAModel.topicsMatrix"> |
| <code class="sig-name descname">topicsMatrix</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/clustering.html#LDAModel.topicsMatrix"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel.topicsMatrix" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Inferred topics, where each topic is represented by a distribution over terms.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.5.0.</span></p> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.clustering.LDAModel.vocabSize"> |
| <code class="sig-name descname">vocabSize</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/clustering.html#LDAModel.vocabSize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.clustering.LDAModel.vocabSize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Vocabulary size (number of terms or terms in the vocabulary)</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.5.0.</span></p> |
| </div> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| <a class='left-prev' id="prev-link" href="pyspark.mllib.clustering.LDA.html" title="previous page">LDA</a> |
| <a class='right-next' id="next-link" href="pyspark.mllib.evaluation.BinaryClassificationMetrics.html" title="next page">BinaryClassificationMetrics</a> |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
