Google Git
Sign in
apache / spark-website / e70e5c0adf47fbb67f89c252db397607e9f77225 / . / site / docs / 3.1.1 / api / python / reference / api / pyspark.ml.feature.VectorIndexer.html
blob: 4d6be552b0c91f28771e8655804a105a50662d40 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>VectorIndexer &#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.feature.VectorIndexer.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="VectorIndexerModel" href="pyspark.ml.feature.VectorIndexerModel.html" />
<link rel="prev" title="VectorAssembler" href="pyspark.ml.feature.VectorAssembler.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="vectorindexer">
<h1>VectorIndexer<a class="headerlink" href="#vectorindexer" title="Permalink to this headline"></a></h1>
<dl class="py class">
<dt id="pyspark.ml.feature.VectorIndexer">
<em class="property">class </em><code class="sig-prename descclassname">pyspark.ml.feature.</code><code class="sig-name descname">VectorIndexer</code><span class="sig-paren">(</span><em class="sig-param"><span class="o">*</span></em>, <em class="sig-param"><span class="n">maxCategories</span><span class="o">=</span><span class="default_value">20</span></em>, <em class="sig-param"><span class="n">inputCol</span><span class="o">=</span><span class="default_value">None</span></em>, <em class="sig-param"><span class="n">outputCol</span><span class="o">=</span><span class="default_value">None</span></em>, <em class="sig-param"><span class="n">handleInvalid</span><span class="o">=</span><span class="default_value">'error'</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#VectorIndexer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer" title="Permalink to this definition"></a></dt>
<dd><p>Class for indexing categorical feature columns in a dataset of <cite>Vector</cite>.</p>
<dl>
<dt>This has 2 usage modes:</dt><dd><blockquote>
<div><ul class="simple">
<li><dl class="simple">
<dt>Automatically identify categorical features (default behavior)</dt><dd><ul>
<li><p>This helps process a dataset of unknown vectors into a dataset with some continuous
features and some categorical features. The choice between continuous and categorical
is based upon a maxCategories parameter.</p></li>
<li><p>Set maxCategories to the maximum number of categorical any categorical feature should
have.</p></li>
<li><p>E.g.: Feature 0 has unique values {-1.0, 0.0}, and feature 1 values {1.0, 3.0, 5.0}.
If maxCategories = 2, then feature 0 will be declared categorical and use indices {0, 1},
and feature 1 will be declared continuous.</p></li>
</ul>
</dd>
</dl>
</li>
<li><dl class="simple">
<dt>Index all features, if all features are categorical</dt><dd><ul>
<li><p>If maxCategories is set to be very large, then this will build an index of unique
values for all features.</p></li>
<li><p>Warning: This can cause problems if features are continuous since this will collect ALL
unique values to the driver.</p></li>
<li><p>E.g.: Feature 0 has unique values {-1.0, 0.0}, and feature 1 values {1.0, 3.0, 5.0}.
If maxCategories &gt;= 3, then both features will be declared categorical.</p></li>
</ul>
</dd>
</dl>
</li>
</ul>
</div></blockquote>
<p>This returns a model which can transform categorical features to use 0-based indices.</p>
</dd>
<dt>Index stability:</dt><dd><ul class="simple">
<li><p>This is not guaranteed to choose the same category index across multiple runs.</p></li>
<li><p>If a categorical feature includes value 0, then this is guaranteed to map value 0 to
index 0. This maintains vector sparsity.</p></li>
<li><p>More stability may be added in the future.</p></li>
</ul>
</dd>
<dt>TODO: Future extensions: The following functionality is planned for the future:</dt><dd><ul class="simple">
<li><p>Preserve metadata in transform; if a feature’s metadata is already present,
do not recompute.</p></li>
<li><p>Specify certain features to not index, either via a parameter or via existing metadata.</p></li>
<li><p>Add warning if a categorical feature has only 1 category.</p></li>
</ul>
</dd>
</dl>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.4.0.</span></p>
</div>
<p class="rubric">Examples</p>
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</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="o">-</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">]),),</span>
<span class="gp">... </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="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">2.0</span><span class="p">]),)],</span> <span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">])</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">indexer</span> <span class="o">=</span> <span class="n">VectorIndexer</span><span class="p">(</span><span class="n">maxCategories</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">inputCol</span><span class="o">=</span><span class="s2">&quot;a&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">indexer</span><span class="o">.</span><span class="n">setOutputCol</span><span class="p">(</span><span class="s2">&quot;indexed&quot;</span><span class="p">)</span>
<span class="go">VectorIndexer...</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span> <span class="o">=</span> <span class="n">indexer</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">indexer</span><span class="o">.</span><span class="n">getHandleInvalid</span><span class="p">()</span>
<span class="go">&#39;error&#39;</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">setOutputCol</span><span class="p">(</span><span class="s2">&quot;output&quot;</span><span class="p">)</span>
<span class="go">VectorIndexerModel...</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span><span class="o">.</span><span class="n">output</span>
<span class="go">DenseVector([1.0, 0.0])</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">numFeatures</span>
<span class="go">2</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">categoryMaps</span>
<span class="go">{0: {0.0: 0, -1.0: 1}}</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">indexer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;test&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">test</span>
<span class="go">DenseVector([0.0, 1.0])</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">params</span> <span class="o">=</span> <span class="p">{</span><span class="n">indexer</span><span class="o">.</span><span class="n">maxCategories</span><span class="p">:</span> <span class="mi">3</span><span class="p">,</span> <span class="n">indexer</span><span class="o">.</span><span class="n">outputCol</span><span class="p">:</span> <span class="s2">&quot;vector&quot;</span><span class="p">}</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model2</span> <span class="o">=</span> <span class="n">indexer</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">params</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model2</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span><span class="o">.</span><span class="n">vector</span>
<span class="go">DenseVector([1.0, 0.0])</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">vectorIndexerPath</span> <span class="o">=</span> <span class="n">temp_path</span> <span class="o">+</span> <span class="s2">&quot;/vector-indexer&quot;</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">indexer</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">vectorIndexerPath</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">loadedIndexer</span> <span class="o">=</span> <span class="n">VectorIndexer</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">vectorIndexerPath</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">loadedIndexer</span><span class="o">.</span><span class="n">getMaxCategories</span><span class="p">()</span> <span class="o">==</span> <span class="n">indexer</span><span class="o">.</span><span class="n">getMaxCategories</span><span class="p">()</span>
<span class="go">True</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">modelPath</span> <span class="o">=</span> <span class="n">temp_path</span> <span class="o">+</span> <span class="s2">&quot;/vector-indexer-model&quot;</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">modelPath</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">loadedModel</span> <span class="o">=</span> <span class="n">VectorIndexerModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">modelPath</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">loadedModel</span><span class="o">.</span><span class="n">numFeatures</span> <span class="o">==</span> <span class="n">model</span><span class="o">.</span><span class="n">numFeatures</span>
<span class="go">True</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">loadedModel</span><span class="o">.</span><span class="n">categoryMaps</span> <span class="o">==</span> <span class="n">model</span><span class="o">.</span><span class="n">categoryMaps</span>
<span class="go">True</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">loadedModel</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="o">==</span> <span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="go">True</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">dfWithInvalid</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</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">3.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">]),)],</span> <span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">])</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">indexer</span><span class="o">.</span><span class="n">getHandleInvalid</span><span class="p">()</span>
<span class="go">&#39;error&#39;</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model3</span> <span class="o">=</span> <span class="n">indexer</span><span class="o">.</span><span class="n">setHandleInvalid</span><span class="p">(</span><span class="s2">&quot;skip&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model3</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dfWithInvalid</span><span class="p">)</span><span class="o">.</span><span class="n">count</span><span class="p">()</span>
<span class="go">0</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model4</span> <span class="o">=</span> <span class="n">indexer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="n">handleInvalid</span><span class="o">=</span><span class="s2">&quot;keep&quot;</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;indexed&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model4</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dfWithInvalid</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span><span class="o">.</span><span class="n">indexed</span>
<span class="go">DenseVector([2.0, 1.0])</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.ml.feature.VectorIndexer.clear" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.copy" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.explainParam" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.explainParams" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.extractParamMap" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.fit" title="pyspark.ml.feature.VectorIndexer.fit"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fit</span></code></a>(dataset[, params])</p></td>
<td><p>Fits a model to the input dataset with optional parameters.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.fitMultiple" title="pyspark.ml.feature.VectorIndexer.fitMultiple"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fitMultiple</span></code></a>(dataset, paramMaps)</p></td>
<td><p>Fits a model to the input dataset for each param map in <cite>paramMaps</cite>.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.getHandleInvalid" title="pyspark.ml.feature.VectorIndexer.getHandleInvalid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getHandleInvalid</span></code></a>()</p></td>
<td><p>Gets the value of handleInvalid or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.getInputCol" title="pyspark.ml.feature.VectorIndexer.getInputCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getInputCol</span></code></a>()</p></td>
<td><p>Gets the value of inputCol or its default value.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.getMaxCategories" title="pyspark.ml.feature.VectorIndexer.getMaxCategories"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getMaxCategories</span></code></a>()</p></td>
<td><p>Gets the value of maxCategories or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.getOrDefault" title="pyspark.ml.feature.VectorIndexer.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-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.getOutputCol" title="pyspark.ml.feature.VectorIndexer.getOutputCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">getOutputCol</span></code></a>()</p></td>
<td><p>Gets the value of outputCol or its default value.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.getParam" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.hasDefault" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.hasParam" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.isDefined" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.isSet" title="pyspark.ml.feature.VectorIndexer.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-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.load" title="pyspark.ml.feature.VectorIndexer.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-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.read" title="pyspark.ml.feature.VectorIndexer.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-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.save" title="pyspark.ml.feature.VectorIndexer.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-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.set" title="pyspark.ml.feature.VectorIndexer.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-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.setHandleInvalid" title="pyspark.ml.feature.VectorIndexer.setHandleInvalid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setHandleInvalid</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.handleInvalid" title="pyspark.ml.feature.VectorIndexer.handleInvalid"><code class="xref py py-attr docutils literal notranslate"><span class="pre">handleInvalid</span></code></a>.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.setInputCol" title="pyspark.ml.feature.VectorIndexer.setInputCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setInputCol</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.inputCol" title="pyspark.ml.feature.VectorIndexer.inputCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">inputCol</span></code></a>.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.setMaxCategories" title="pyspark.ml.feature.VectorIndexer.setMaxCategories"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setMaxCategories</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.maxCategories" title="pyspark.ml.feature.VectorIndexer.maxCategories"><code class="xref py py-attr docutils literal notranslate"><span class="pre">maxCategories</span></code></a>.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.setOutputCol" title="pyspark.ml.feature.VectorIndexer.setOutputCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setOutputCol</span></code></a>(value)</p></td>
<td><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.outputCol" title="pyspark.ml.feature.VectorIndexer.outputCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">outputCol</span></code></a>.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.setParams" title="pyspark.ml.feature.VectorIndexer.setParams"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setParams</span></code></a>(self, \*[, maxCategories, …])</p></td>
<td><p>Sets params for this VectorIndexer.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.write" title="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.handleInvalid" title="pyspark.ml.feature.VectorIndexer.handleInvalid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">handleInvalid</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.inputCol" title="pyspark.ml.feature.VectorIndexer.inputCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">inputCol</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.maxCategories" title="pyspark.ml.feature.VectorIndexer.maxCategories"><code class="xref py py-obj docutils literal notranslate"><span class="pre">maxCategories</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.outputCol" title="pyspark.ml.feature.VectorIndexer.outputCol"><code class="xref py py-obj docutils literal notranslate"><span class="pre">outputCol</span></code></a></p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.params" title="pyspark.ml.feature.VectorIndexer.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>
</tbody>
</table>
<p class="rubric">Methods Documentation</p>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.explainParams">
<code class="sig-name descname">explainParams</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.fit">
<code class="sig-name descname">fit</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.feature.VectorIndexer.fit" title="Permalink to this definition"></a></dt>
<dd><p>Fits a model to 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 or list or tuple, optional</span></dt><dd><p>an optional param map that overrides embedded params. If a list/tuple of
param maps is given, this calls fit on each param map and returns a list of
models.</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">Transformer</span></code> or a list of <code class="xref py py-class docutils literal notranslate"><span class="pre">Transformer</span></code></dt><dd><p>fitted model(s)</p>
</dd>
</dl>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.fitMultiple">
<code class="sig-name descname">fitMultiple</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">dataset</span></em>, <em class="sig-param"><span class="n">paramMaps</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.fitMultiple" title="Permalink to this definition"></a></dt>
<dd><p>Fits a model to the input dataset for each param map in <cite>paramMaps</cite>.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.3.0.</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>paramMaps</strong><span class="classifier"><code class="xref py py-class docutils literal notranslate"><span class="pre">collections.abc.Sequence</span></code></span></dt><dd><p>A Sequence of param maps.</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">_FitMultipleIterator</span></code></dt><dd><p>A thread safe iterable which contains one model for each param map. Each
call to <cite>next(modelIterator)</cite> will return <cite>(index, model)</cite> where model was fit
using <cite>paramMaps[index]</cite>. <cite>index</cite> values may not be sequential.</p>
</dd>
</dl>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.getHandleInvalid">
<code class="sig-name descname">getHandleInvalid</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.getHandleInvalid" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of handleInvalid or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.getInputCol">
<code class="sig-name descname">getInputCol</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.getInputCol" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of inputCol or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.getMaxCategories">
<code class="sig-name descname">getMaxCategories</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.getMaxCategories" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of maxCategories or its default value.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.4.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.getOutputCol">
<code class="sig-name descname">getOutputCol</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.getOutputCol" title="Permalink to this definition"></a></dt>
<dd><p>Gets the value of outputCol or its default value.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.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.feature.VectorIndexer.setHandleInvalid">
<code class="sig-name descname">setHandleInvalid</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#VectorIndexer.setHandleInvalid"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.setHandleInvalid" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.handleInvalid" title="pyspark.ml.feature.VectorIndexer.handleInvalid"><code class="xref py py-attr docutils literal notranslate"><span class="pre">handleInvalid</span></code></a>.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.setInputCol">
<code class="sig-name descname">setInputCol</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#VectorIndexer.setInputCol"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.setInputCol" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.inputCol" title="pyspark.ml.feature.VectorIndexer.inputCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">inputCol</span></code></a>.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.setMaxCategories">
<code class="sig-name descname">setMaxCategories</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#VectorIndexer.setMaxCategories"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.setMaxCategories" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.maxCategories" title="pyspark.ml.feature.VectorIndexer.maxCategories"><code class="xref py py-attr docutils literal notranslate"><span class="pre">maxCategories</span></code></a>.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.4.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.setOutputCol">
<code class="sig-name descname">setOutputCol</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#VectorIndexer.setOutputCol"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.setOutputCol" title="Permalink to this definition"></a></dt>
<dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.VectorIndexer.outputCol" title="pyspark.ml.feature.VectorIndexer.outputCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">outputCol</span></code></a>.</p>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.setParams">
<code class="sig-name descname">setParams</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">\*</em>, <em class="sig-param">maxCategories=20</em>, <em class="sig-param">inputCol=None</em>, <em class="sig-param">outputCol=None</em>, <em class="sig-param">handleInvalid=&quot;error&quot;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#VectorIndexer.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.setParams" title="Permalink to this definition"></a></dt>
<dd><p>Sets params for this VectorIndexer.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.4.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.ml.feature.VectorIndexer.write">
<code class="sig-name descname">write</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.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.feature.VectorIndexer.handleInvalid">
<code class="sig-name descname">handleInvalid</code><em class="property"> = Param(parent='undefined', name='handleInvalid', doc=&quot;How to handle invalid data (unseen labels or NULL values). Options are 'skip' (filter out rows with invalid data), 'error' (throw an error), or 'keep' (put invalid data in a special additional bucket, at index of the number of categories of the feature).&quot;)</em><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.handleInvalid" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.feature.VectorIndexer.inputCol">
<code class="sig-name descname">inputCol</code><em class="property"> = Param(parent='undefined', name='inputCol', doc='input column name.')</em><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.inputCol" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.feature.VectorIndexer.maxCategories">
<code class="sig-name descname">maxCategories</code><em class="property"> = Param(parent='undefined', name='maxCategories', doc='Threshold for the number of values a categorical feature can take (&gt;= 2). If a feature is found to have &gt; maxCategories values, then it is declared continuous.')</em><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.maxCategories" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.feature.VectorIndexer.outputCol">
<code class="sig-name descname">outputCol</code><em class="property"> = Param(parent='undefined', name='outputCol', doc='output column name.')</em><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.outputCol" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt id="pyspark.ml.feature.VectorIndexer.params">
<code class="sig-name descname">params</code><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer.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>
</dd></dl>
</div>
</div>
<div class='prev-next-bottom'>
<a class='left-prev' id="prev-link" href="pyspark.ml.feature.VectorAssembler.html" title="previous page">VectorAssembler</a>
<a class='right-next' id="next-link" href="pyspark.ml.feature.VectorIndexerModel.html" title="next page">VectorIndexerModel</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>