blob: 2750fb9d2f465ddc5c8e3b5618d7303da52feb5b [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>LocalLDAModel &#8212; PySpark 3.1.1 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="canonical" href="https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.ml.clustering.LocalLDAModel.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="DistributedLDAModel" href="pyspark.ml.clustering.DistributedLDAModel.html" />
<link rel="prev" title="LDAModel" href="pyspark.ml.clustering.LDAModel.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="en" />
<!-- Matomo -->
<script type="text/javascript">
var _paq = window._paq = window._paq || [];
/* tracker methods like "setCustomDimension" should be called before "trackPageView" */
_paq.push(["disableCookies"]);
_paq.push(['trackPageView']);
_paq.push(['enableLinkTracking']);
(function() {
var u="https://analytics.apache.org/";
_paq.push(['setTrackerUrl', u+'matomo.php']);
_paq.push(['setSiteId', '40']);
var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
})();
</script>
<!-- End Matomo Code -->
</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.ss.html">Structured Streaming</a>
</li>
<li class="active">
<a href="../pyspark.ml.html">MLlib (DataFrame-based)</a>
</li>
<li class="">
<a href="../pyspark.streaming.html">Spark Streaming</a>
</li>
<li class="">
<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="localldamodel">
<h1>LocalLDAModel<a class="headerlink" href="#localldamodel" title="Permalink to this headline"></a></h1>
<dl class="py class">
<dt id="pyspark.ml.clustering.LocalLDAModel">
<em class="property">class </em><code class="sig-prename descclassname">pyspark.ml.clustering.</code><code class="sig-name descname">LocalLDAModel</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">java_model</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/clustering.html#LocalLDAModel"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel" title="Permalink to this definition"></a></dt>
<dd><p>Local (non-distributed) model fitted by <a class="reference internal" href="pyspark.ml.clustering.LDA.html#pyspark.ml.clustering.LDA" title="pyspark.ml.clustering.LDA"><code class="xref py py-class docutils literal notranslate"><span class="pre">LDA</span></code></a>.
This model stores the inferred topics only; it does not store info about the training dataset.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</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.ml.clustering.LocalLDAModel.clear" title="pyspark.ml.clustering.LocalLDAModel.clear"><code class="xref py py-obj docutils literal notranslate"><span class="pre">clear</span></code></a>(param)</p></td>
<td><p>Clears a param from the param map if it has been explicitly set.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.copy" title="pyspark.ml.clustering.LocalLDAModel.copy"><code class="xref py py-obj docutils literal notranslate"><span class="pre">copy</span></code></a>([extra])</p></td>
<td><p>Creates a copy of this instance with the same uid and some extra params.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.describeTopics" title="pyspark.ml.clustering.LocalLDAModel.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 their top-weighted terms.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.estimatedDocConcentration" title="pyspark.ml.clustering.LocalLDAModel.estimatedDocConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">estimatedDocConcentration</span></code></a>()</p></td>
<td><p>Value for <a class="reference internal" href="pyspark.ml.clustering.LDA.html#pyspark.ml.clustering.LDA.docConcentration" title="pyspark.ml.clustering.LDA.docConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">LDA.docConcentration</span></code></a> estimated from data.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.explainParam" title="pyspark.ml.clustering.LocalLDAModel.explainParam"><code class="xref py py-obj docutils literal notranslate"><span class="pre">explainParam</span></code></a>(param)</p></td>
<td><p>Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.explainParams" title="pyspark.ml.clustering.LocalLDAModel.explainParams"><code class="xref py py-obj docutils literal notranslate"><span class="pre">explainParams</span></code></a>()</p></td>
<td><p>Returns the documentation of all params with their optionally default values and user-supplied values.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.extractParamMap" title="pyspark.ml.clustering.LocalLDAModel.extractParamMap"><code class="xref py py-obj docutils literal notranslate"><span class="pre">extractParamMap</span></code></a>([extra])</p></td>
<td><p>Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values &lt; user-supplied values &lt; extra.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getCheckpointInterval" title="pyspark.ml.clustering.LocalLDAModel.getCheckpointInterval"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getCheckpointInterval</span></code></a>()</p></td>
<td><p>Gets the value of checkpointInterval or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getDocConcentration" title="pyspark.ml.clustering.LocalLDAModel.getDocConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getDocConcentration</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.docConcentration" title="pyspark.ml.clustering.LocalLDAModel.docConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">docConcentration</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getFeaturesCol" title="pyspark.ml.clustering.LocalLDAModel.getFeaturesCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getFeaturesCol</span></code></a>()</p></td>
<td><p>Gets the value of featuresCol or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getK" title="pyspark.ml.clustering.LocalLDAModel.getK"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getK</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.k" title="pyspark.ml.clustering.LocalLDAModel.k"><code class="xref py py-attr docutils literal notranslate"><span class="pre">k</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getKeepLastCheckpoint" title="pyspark.ml.clustering.LocalLDAModel.getKeepLastCheckpoint"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getKeepLastCheckpoint</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint" title="pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint"><code class="xref py py-attr docutils literal notranslate"><span class="pre">keepLastCheckpoint</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getLearningDecay" title="pyspark.ml.clustering.LocalLDAModel.getLearningDecay"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getLearningDecay</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.learningDecay" title="pyspark.ml.clustering.LocalLDAModel.learningDecay"><code class="xref py py-attr docutils literal notranslate"><span class="pre">learningDecay</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getLearningOffset" title="pyspark.ml.clustering.LocalLDAModel.getLearningOffset"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getLearningOffset</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.learningOffset" title="pyspark.ml.clustering.LocalLDAModel.learningOffset"><code class="xref py py-attr docutils literal notranslate"><span class="pre">learningOffset</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getMaxIter" title="pyspark.ml.clustering.LocalLDAModel.getMaxIter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getMaxIter</span></code></a>()</p></td>
<td><p>Gets the value of maxIter or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getOptimizeDocConcentration" title="pyspark.ml.clustering.LocalLDAModel.getOptimizeDocConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getOptimizeDocConcentration</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration" title="pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">optimizeDocConcentration</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getOptimizer" title="pyspark.ml.clustering.LocalLDAModel.getOptimizer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getOptimizer</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizer" title="pyspark.ml.clustering.LocalLDAModel.optimizer"><code class="xref py py-attr docutils literal notranslate"><span class="pre">optimizer</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getOrDefault" title="pyspark.ml.clustering.LocalLDAModel.getOrDefault"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getOrDefault</span></code></a>(param)</p></td>
<td><p>Gets the value of a param in the user-supplied param map or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getParam" title="pyspark.ml.clustering.LocalLDAModel.getParam"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getParam</span></code></a>(paramName)</p></td>
<td><p>Gets a param by its name.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getSeed" title="pyspark.ml.clustering.LocalLDAModel.getSeed"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getSeed</span></code></a>()</p></td>
<td><p>Gets the value of seed or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getSubsamplingRate" title="pyspark.ml.clustering.LocalLDAModel.getSubsamplingRate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getSubsamplingRate</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.subsamplingRate" title="pyspark.ml.clustering.LocalLDAModel.subsamplingRate"><code class="xref py py-attr docutils literal notranslate"><span class="pre">subsamplingRate</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getTopicConcentration" title="pyspark.ml.clustering.LocalLDAModel.getTopicConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getTopicConcentration</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicConcentration" title="pyspark.ml.clustering.LocalLDAModel.topicConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">topicConcentration</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.getTopicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.getTopicDistributionCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getTopicDistributionCol</span></code></a>()</p></td>
<td><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.topicDistributionCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">topicDistributionCol</span></code></a> or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.hasDefault" title="pyspark.ml.clustering.LocalLDAModel.hasDefault"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hasDefault</span></code></a>(param)</p></td>
<td><p>Checks whether a param has a default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.hasParam" title="pyspark.ml.clustering.LocalLDAModel.hasParam"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hasParam</span></code></a>(paramName)</p></td>
<td><p>Tests whether this instance contains a param with a given (string) name.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.isDefined" title="pyspark.ml.clustering.LocalLDAModel.isDefined"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isDefined</span></code></a>(param)</p></td>
<td><p>Checks whether a param is explicitly set by user or has a default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.isDistributed" title="pyspark.ml.clustering.LocalLDAModel.isDistributed"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isDistributed</span></code></a>()</p></td>
<td><p>Indicates whether this instance is of type DistributedLDAModel</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.isSet" title="pyspark.ml.clustering.LocalLDAModel.isSet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isSet</span></code></a>(param)</p></td>
<td><p>Checks whether a param is explicitly set by user.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.load" title="pyspark.ml.clustering.LocalLDAModel.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(path)</p></td>
<td><p>Reads an ML instance from the input path, a shortcut of <cite>read().load(path)</cite>.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.logLikelihood" title="pyspark.ml.clustering.LocalLDAModel.logLikelihood"><code class="xref py py-obj docutils literal notranslate"><span class="pre">logLikelihood</span></code></a>(dataset)</p></td>
<td><p>Calculates a lower bound on the log likelihood of the entire corpus.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.logPerplexity" title="pyspark.ml.clustering.LocalLDAModel.logPerplexity"><code class="xref py py-obj docutils literal notranslate"><span class="pre">logPerplexity</span></code></a>(dataset)</p></td>
<td><p>Calculate an upper bound on perplexity.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.read" title="pyspark.ml.clustering.LocalLDAModel.read"><code class="xref py py-obj docutils literal notranslate"><span class="pre">read</span></code></a>()</p></td>
<td><p>Returns an MLReader instance for this class.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.save" title="pyspark.ml.clustering.LocalLDAModel.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(path)</p></td>
<td><p>Save this ML instance to the given path, a shortcut of ‘write().save(path)’.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.set" title="pyspark.ml.clustering.LocalLDAModel.set"><code class="xref py py-obj docutils literal notranslate"><span class="pre">set</span></code></a>(param, value)</p></td>
<td><p>Sets a parameter in the embedded param map.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.setFeaturesCol" title="pyspark.ml.clustering.LocalLDAModel.setFeaturesCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setFeaturesCol</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.featuresCol" title="pyspark.ml.clustering.LocalLDAModel.featuresCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">featuresCol</span></code></a>.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.setSeed" title="pyspark.ml.clustering.LocalLDAModel.setSeed"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setSeed</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.seed" title="pyspark.ml.clustering.LocalLDAModel.seed"><code class="xref py py-attr docutils literal notranslate"><span class="pre">seed</span></code></a>.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.setTopicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.setTopicDistributionCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setTopicDistributionCol</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.topicDistributionCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">topicDistributionCol</span></code></a>.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicsMatrix" title="pyspark.ml.clustering.LocalLDAModel.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-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.transform" title="pyspark.ml.clustering.LocalLDAModel.transform"><code class="xref py py-obj docutils literal notranslate"><span class="pre">transform</span></code></a>(dataset[, params])</p></td>
<td><p>Transforms the input dataset with optional parameters.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.vocabSize" title="pyspark.ml.clustering.LocalLDAModel.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 words in the vocabulary)</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.write" title="pyspark.ml.clustering.LocalLDAModel.write"><code class="xref py py-obj docutils literal notranslate"><span class="pre">write</span></code></a>()</p></td>
<td><p>Returns an MLWriter instance for this ML instance.</p></td>
</tr>
</tbody>
</table>
<p class="rubric">Attributes</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.ml.clustering.LocalLDAModel.checkpointInterval" title="pyspark.ml.clustering.LocalLDAModel.checkpointInterval"><code class="xref py py-obj docutils literal notranslate"><span class="pre">checkpointInterval</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.docConcentration" title="pyspark.ml.clustering.LocalLDAModel.docConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">docConcentration</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.featuresCol" title="pyspark.ml.clustering.LocalLDAModel.featuresCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">featuresCol</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.k" title="pyspark.ml.clustering.LocalLDAModel.k"><code class="xref py py-obj docutils literal notranslate"><span class="pre">k</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint" title="pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint"><code class="xref py py-obj docutils literal notranslate"><span class="pre">keepLastCheckpoint</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.learningDecay" title="pyspark.ml.clustering.LocalLDAModel.learningDecay"><code class="xref py py-obj docutils literal notranslate"><span class="pre">learningDecay</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.learningOffset" title="pyspark.ml.clustering.LocalLDAModel.learningOffset"><code class="xref py py-obj docutils literal notranslate"><span class="pre">learningOffset</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.maxIter" title="pyspark.ml.clustering.LocalLDAModel.maxIter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">maxIter</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration" title="pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimizeDocConcentration</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizer" title="pyspark.ml.clustering.LocalLDAModel.optimizer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimizer</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.params" title="pyspark.ml.clustering.LocalLDAModel.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td>
<td><p>Returns all params ordered by name.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.seed" title="pyspark.ml.clustering.LocalLDAModel.seed"><code class="xref py py-obj docutils literal notranslate"><span class="pre">seed</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.subsamplingRate" title="pyspark.ml.clustering.LocalLDAModel.subsamplingRate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">subsamplingRate</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicConcentration" title="pyspark.ml.clustering.LocalLDAModel.topicConcentration"><code class="xref py py-obj docutils literal notranslate"><span class="pre">topicConcentration</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.topicDistributionCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">topicDistributionCol</span></code></a></p></td>
<td><p></p></td>
</tr>
</tbody>
</table>
<p class="rubric">Methods Documentation</p>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.clear">
<code class="sig-name descname">clear</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.clear" title="Permalink to this definition"></a></dt>
<dd><p>Clears a param from the param map if it has been explicitly set.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.copy">
<code class="sig-name descname">copy</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">extra</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.copy" title="Permalink to this definition"></a></dt>
<dd><p>Creates a copy of this instance with the same uid and some
extra params. This implementation first calls Params.copy and
then make a copy of the companion Java pipeline component with
extra params. So both the Python wrapper and the Java pipeline
component get copied.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><dl class="simple">
<dt><strong>extra</strong><span class="classifier">dict, optional</span></dt><dd><p>Extra parameters to copy to the new instance</p>
</dd>
</dl>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><dl class="simple">
<dt><code class="xref py py-class docutils literal notranslate"><span class="pre">JavaParams</span></code></dt><dd><p>Copy of this instance</p>
</dd>
</dl>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.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">10</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.describeTopics" title="Permalink to this definition"></a></dt>
<dd><p>Return the topics described by their top-weighted terms.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.estimatedDocConcentration">
<code class="sig-name descname">estimatedDocConcentration</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.estimatedDocConcentration" title="Permalink to this definition"></a></dt>
<dd><p>Value for <a class="reference internal" href="pyspark.ml.clustering.LDA.html#pyspark.ml.clustering.LDA.docConcentration" title="pyspark.ml.clustering.LDA.docConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">LDA.docConcentration</span></code></a> estimated from data.
If Online LDA was used and <a class="reference internal" href="pyspark.ml.clustering.LDA.html#pyspark.ml.clustering.LDA.optimizeDocConcentration" title="pyspark.ml.clustering.LDA.optimizeDocConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">LDA.optimizeDocConcentration</span></code></a> was set to false,
then this returns the fixed (given) value for the <a class="reference internal" href="pyspark.ml.clustering.LDA.html#pyspark.ml.clustering.LDA.docConcentration" title="pyspark.ml.clustering.LDA.docConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">LDA.docConcentration</span></code></a> parameter.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.explainParam">
<code class="sig-name descname">explainParam</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.explainParam" title="Permalink to this definition"></a></dt>
<dd><p>Explains a single param and returns its name, doc, and optional
default value and user-supplied value in a string.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.explainParams">
<code class="sig-name descname">explainParams</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.explainParams" title="Permalink to this definition"></a></dt>
<dd><p>Returns the documentation of all params with their optionally
default values and user-supplied values.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.extractParamMap">
<code class="sig-name descname">extractParamMap</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">extra</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.extractParamMap" title="Permalink to this definition"></a></dt>
<dd><p>Extracts the embedded default param values and user-supplied
values, and then merges them with extra values from input into
a flat param map, where the latter value is used if there exist
conflicts, i.e., with ordering: default param values &lt;
user-supplied values &lt; extra.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><dl class="simple">
<dt><strong>extra</strong><span class="classifier">dict, optional</span></dt><dd><p>extra param values</p>
</dd>
</dl>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><dl class="simple">
<dt>dict</dt><dd><p>merged param map</p>
</dd>
</dl>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getCheckpointInterval">
<code class="sig-name descname">getCheckpointInterval</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getCheckpointInterval" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of checkpointInterval or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getDocConcentration">
<code class="sig-name descname">getDocConcentration</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getDocConcentration" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.docConcentration" title="pyspark.ml.clustering.LocalLDAModel.docConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">docConcentration</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getFeaturesCol">
<code class="sig-name descname">getFeaturesCol</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getFeaturesCol" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of featuresCol or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getK">
<code class="sig-name descname">getK</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getK" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.k" title="pyspark.ml.clustering.LocalLDAModel.k"><code class="xref py py-attr docutils literal notranslate"><span class="pre">k</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getKeepLastCheckpoint">
<code class="sig-name descname">getKeepLastCheckpoint</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getKeepLastCheckpoint" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint" title="pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint"><code class="xref py py-attr docutils literal notranslate"><span class="pre">keepLastCheckpoint</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getLearningDecay">
<code class="sig-name descname">getLearningDecay</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getLearningDecay" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.learningDecay" title="pyspark.ml.clustering.LocalLDAModel.learningDecay"><code class="xref py py-attr docutils literal notranslate"><span class="pre">learningDecay</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getLearningOffset">
<code class="sig-name descname">getLearningOffset</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getLearningOffset" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.learningOffset" title="pyspark.ml.clustering.LocalLDAModel.learningOffset"><code class="xref py py-attr docutils literal notranslate"><span class="pre">learningOffset</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getMaxIter">
<code class="sig-name descname">getMaxIter</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getMaxIter" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of maxIter or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getOptimizeDocConcentration">
<code class="sig-name descname">getOptimizeDocConcentration</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getOptimizeDocConcentration" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration" title="pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">optimizeDocConcentration</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getOptimizer">
<code class="sig-name descname">getOptimizer</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getOptimizer" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizer" title="pyspark.ml.clustering.LocalLDAModel.optimizer"><code class="xref py py-attr docutils literal notranslate"><span class="pre">optimizer</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getOrDefault">
<code class="sig-name descname">getOrDefault</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getOrDefault" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of a param in the user-supplied param map or its
default value. Raises an error if neither is set.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getParam">
<code class="sig-name descname">getParam</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">paramName</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getParam" title="Permalink to this definition"></a></dt>
<dd><p>Gets a param by its name.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getSeed">
<code class="sig-name descname">getSeed</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getSeed" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of seed or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getSubsamplingRate">
<code class="sig-name descname">getSubsamplingRate</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getSubsamplingRate" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.subsamplingRate" title="pyspark.ml.clustering.LocalLDAModel.subsamplingRate"><code class="xref py py-attr docutils literal notranslate"><span class="pre">subsamplingRate</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getTopicConcentration">
<code class="sig-name descname">getTopicConcentration</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getTopicConcentration" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicConcentration" title="pyspark.ml.clustering.LocalLDAModel.topicConcentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">topicConcentration</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.getTopicDistributionCol">
<code class="sig-name descname">getTopicDistributionCol</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.getTopicDistributionCol" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.topicDistributionCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">topicDistributionCol</span></code></a> or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.hasDefault">
<code class="sig-name descname">hasDefault</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.hasDefault" title="Permalink to this definition"></a></dt>
<dd><p>Checks whether a param has a default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.hasParam">
<code class="sig-name descname">hasParam</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">paramName</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.hasParam" title="Permalink to this definition"></a></dt>
<dd><p>Tests whether this instance contains a param with a given
(string) name.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.isDefined">
<code class="sig-name descname">isDefined</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.isDefined" title="Permalink to this definition"></a></dt>
<dd><p>Checks whether a param is explicitly set by user or has
a default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.isDistributed">
<code class="sig-name descname">isDistributed</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.isDistributed" title="Permalink to this definition"></a></dt>
<dd><p>Indicates whether this instance is of type DistributedLDAModel</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.isSet">
<code class="sig-name descname">isSet</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.isSet" title="Permalink to this definition"></a></dt>
<dd><p>Checks whether a param is explicitly set by user.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.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">path</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.load" title="Permalink to this definition"></a></dt>
<dd><p>Reads an ML instance from the input path, a shortcut of <cite>read().load(path)</cite>.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.logLikelihood">
<code class="sig-name descname">logLikelihood</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">dataset</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.logLikelihood" title="Permalink to this definition"></a></dt>
<dd><p>Calculates a lower bound on the log likelihood of the entire corpus.
See Equation (16) in the Online LDA paper (Hoffman et al., 2010).</p>
<div class="admonition warning">
<p class="admonition-title">Warning</p>
<p>If this model is an instance of <a class="reference internal" href="pyspark.ml.clustering.DistributedLDAModel.html#pyspark.ml.clustering.DistributedLDAModel" title="pyspark.ml.clustering.DistributedLDAModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">DistributedLDAModel</span></code></a> (produced when
<a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizer" title="pyspark.ml.clustering.LocalLDAModel.optimizer"><code class="xref py py-attr docutils literal notranslate"><span class="pre">optimizer</span></code></a> is set to “em”), this involves collecting a large
<a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicsMatrix" title="pyspark.ml.clustering.LocalLDAModel.topicsMatrix"><code class="xref py py-func docutils literal notranslate"><span class="pre">topicsMatrix()</span></code></a> to the driver. This implementation may be changed in the future.</p>
</div>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.logPerplexity">
<code class="sig-name descname">logPerplexity</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">dataset</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.logPerplexity" title="Permalink to this definition"></a></dt>
<dd><p>Calculate an upper bound on perplexity. (Lower is better.)
See Equation (16) in the Online LDA paper (Hoffman et al., 2010).</p>
<div class="admonition warning">
<p class="admonition-title">Warning</p>
<p>If this model is an instance of <a class="reference internal" href="pyspark.ml.clustering.DistributedLDAModel.html#pyspark.ml.clustering.DistributedLDAModel" title="pyspark.ml.clustering.DistributedLDAModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">DistributedLDAModel</span></code></a> (produced when
<a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.optimizer" title="pyspark.ml.clustering.LocalLDAModel.optimizer"><code class="xref py py-attr docutils literal notranslate"><span class="pre">optimizer</span></code></a> is set to “em”), this involves collecting a large
<a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicsMatrix" title="pyspark.ml.clustering.LocalLDAModel.topicsMatrix"><code class="xref py py-func docutils literal notranslate"><span class="pre">topicsMatrix()</span></code></a> to the driver. This implementation may be changed in the future.</p>
</div>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.read">
<em class="property">classmethod </em><code class="sig-name descname">read</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.read" title="Permalink to this definition"></a></dt>
<dd><p>Returns an MLReader instance for this class.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.save">
<code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">path</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.save" title="Permalink to this definition"></a></dt>
<dd><p>Save this ML instance to the given path, a shortcut of ‘write().save(path)’.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.set">
<code class="sig-name descname">set</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span></em>, <em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.set" title="Permalink to this definition"></a></dt>
<dd><p>Sets a parameter in the embedded param map.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.setFeaturesCol">
<code class="sig-name descname">setFeaturesCol</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.setFeaturesCol" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.featuresCol" title="pyspark.ml.clustering.LocalLDAModel.featuresCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">featuresCol</span></code></a>.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 3.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.setSeed">
<code class="sig-name descname">setSeed</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.setSeed" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.seed" title="pyspark.ml.clustering.LocalLDAModel.seed"><code class="xref py py-attr docutils literal notranslate"><span class="pre">seed</span></code></a>.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 3.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.setTopicDistributionCol">
<code class="sig-name descname">setTopicDistributionCol</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.setTopicDistributionCol" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.clustering.LocalLDAModel.topicDistributionCol" title="pyspark.ml.clustering.LocalLDAModel.topicDistributionCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">topicDistributionCol</span></code></a>.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 3.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.topicsMatrix">
<code class="sig-name descname">topicsMatrix</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.topicsMatrix" title="Permalink to this definition"></a></dt>
<dd><p>Inferred topics, where each topic is represented by a distribution over terms.
This is a matrix of size vocabSize x k, where each column is a topic.
No guarantees are given about the ordering of the topics.</p>
<div class="admonition warning">
<p class="admonition-title">Warning</p>
<p>If this model is actually a <a class="reference internal" href="pyspark.ml.clustering.DistributedLDAModel.html#pyspark.ml.clustering.DistributedLDAModel" title="pyspark.ml.clustering.DistributedLDAModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">DistributedLDAModel</span></code></a>
instance produced by the Expectation-Maximization (“em”) <cite>optimizer</cite>,
then this method could involve collecting a large amount of data
to the driver (on the order of vocabSize x k).</p>
</div>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.transform">
<code class="sig-name descname">transform</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">dataset</span></em>, <em class="sig-param"><span class="n">params</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.transform" title="Permalink to this definition"></a></dt>
<dd><p>Transforms the input dataset with optional parameters.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.3.0.</span></p>
</div>
<dl class="field-list">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><dl>
<dt><strong>dataset</strong><span class="classifier"><a class="reference internal" href="pyspark.sql.DataFrame.html#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.DataFrame</span></code></a></span></dt><dd><p>input dataset</p>
</dd>
<dt><strong>params</strong><span class="classifier">dict, optional</span></dt><dd><p>an optional param map that overrides embedded params.</p>
</dd>
</dl>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><dl class="simple">
<dt><a class="reference internal" href="pyspark.sql.DataFrame.html#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.DataFrame</span></code></a></dt><dd><p>transformed dataset</p>
</dd>
</dl>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.vocabSize">
<code class="sig-name descname">vocabSize</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.vocabSize" title="Permalink to this definition"></a></dt>
<dd><p>Vocabulary size (number of terms or words in the vocabulary)</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.clustering.LocalLDAModel.write">
<code class="sig-name descname">write</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.write" title="Permalink to this definition"></a></dt>
<dd><p>Returns an MLWriter instance for this ML instance.</p>
</dd></dl>
<p class="rubric">Attributes Documentation</p>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.checkpointInterval">
<code class="sig-name descname">checkpointInterval</code><em class="property"> = Param(parent='undefined', name='checkpointInterval', doc='set checkpoint interval (&gt;= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.checkpointInterval" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.docConcentration">
<code class="sig-name descname">docConcentration</code><em class="property"> = Param(parent='undefined', name='docConcentration', doc='Concentration parameter (commonly named &quot;alpha&quot;) for the prior placed on documents\' distributions over topics (&quot;theta&quot;).')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.docConcentration" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.featuresCol">
<code class="sig-name descname">featuresCol</code><em class="property"> = Param(parent='undefined', name='featuresCol', doc='features column name.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.featuresCol" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.k">
<code class="sig-name descname">k</code><em class="property"> = Param(parent='undefined', name='k', doc='The number of topics (clusters) to infer. Must be &gt; 1.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.k" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint">
<code class="sig-name descname">keepLastCheckpoint</code><em class="property"> = Param(parent='undefined', name='keepLastCheckpoint', doc='(For EM optimizer) If using checkpointing, this indicates whether to keep the last checkpoint. If false, then the checkpoint will be deleted. Deleting the checkpoint can cause failures if a data partition is lost, so set this bit with care.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.keepLastCheckpoint" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.learningDecay">
<code class="sig-name descname">learningDecay</code><em class="property"> = Param(parent='undefined', name='learningDecay', doc='Learning rate, set as anexponential decay rate. This should be between (0.5, 1.0] to guarantee asymptotic convergence.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.learningDecay" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.learningOffset">
<code class="sig-name descname">learningOffset</code><em class="property"> = Param(parent='undefined', name='learningOffset', doc='A (positive) learning parameter that downweights early iterations. Larger values make early iterations count less')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.learningOffset" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.maxIter">
<code class="sig-name descname">maxIter</code><em class="property"> = Param(parent='undefined', name='maxIter', doc='max number of iterations (&gt;= 0).')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.maxIter" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration">
<code class="sig-name descname">optimizeDocConcentration</code><em class="property"> = Param(parent='undefined', name='optimizeDocConcentration', doc='Indicates whether the docConcentration (Dirichlet parameter for document-topic distribution) will be optimized during training.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.optimizeDocConcentration" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.optimizer">
<code class="sig-name descname">optimizer</code><em class="property"> = Param(parent='undefined', name='optimizer', doc='Optimizer or inference algorithm used to estimate the LDA model. Supported: online, em')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.optimizer" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.params">
<code class="sig-name descname">params</code><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.params" title="Permalink to this definition"></a></dt>
<dd><p>Returns all params ordered by name. The default implementation
uses <code class="xref py py-func docutils literal notranslate"><span class="pre">dir()</span></code> to get all attributes of type
<code class="xref py py-class docutils literal notranslate"><span class="pre">Param</span></code>.</p>
</dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.seed">
<code class="sig-name descname">seed</code><em class="property"> = Param(parent='undefined', name='seed', doc='random seed.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.seed" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.subsamplingRate">
<code class="sig-name descname">subsamplingRate</code><em class="property"> = Param(parent='undefined', name='subsamplingRate', doc='Fraction of the corpus to be sampled and used in each iteration of mini-batch gradient descent, in range (0, 1].')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.subsamplingRate" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.topicConcentration">
<code class="sig-name descname">topicConcentration</code><em class="property"> = Param(parent='undefined', name='topicConcentration', doc='Concentration parameter (commonly named &quot;beta&quot; or &quot;eta&quot;) for the prior placed on topic\' distributions over terms.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.topicConcentration" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.clustering.LocalLDAModel.topicDistributionCol">
<code class="sig-name descname">topicDistributionCol</code><em class="property"> = Param(parent='undefined', name='topicDistributionCol', doc='Output column with estimates of the topic mixture distribution for each document (often called &quot;theta&quot; in the literature). Returns a vector of zeros for an empty document.')</em><a class="headerlink" href="#pyspark.ml.clustering.LocalLDAModel.topicDistributionCol" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</div>
</div>
<div class='prev-next-bottom'>
<a class='left-prev' id="prev-link" href="pyspark.ml.clustering.LDAModel.html" title="previous page">LDAModel</a>
<a class='right-next' id="next-link" href="pyspark.ml.clustering.DistributedLDAModel.html" title="next page">DistributedLDAModel</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>
&copy; Copyright .<br/>
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/>
</p>
</div>
</footer>
</body>
</html>