Google Git
Sign in
apache / spark-website / 28656f2c00baf1bc2d26570a16b4f96f9a890723 / . / site / docs / 3.2.2 / api / python / reference / api / pyspark.mllib.feature.Word2Vec.html
blob: 910649ebe076dca4768e1a5e8ce2906a185d1675 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>Word2Vec &#8212; PySpark 3.2.2 documentation</title>
<link rel="stylesheet" href="../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css">
<link rel="stylesheet"
href="../../_static/vendor/fontawesome/5.13.0/css/all.min.css">
<link rel="preload" as="font" type="font/woff2" crossorigin
href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2">
<link rel="preload" as="font" type="font/woff2" crossorigin
href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2">
<link rel="stylesheet"
href="../../_static/vendor/open-sans_all/1.44.1/index.css">
<link rel="stylesheet"
href="../../_static/vendor/lato_latin-ext/1.44.1/index.css">
<link rel="stylesheet" href="../../_static/basic.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" type="text/css" href="../../_static/css/pyspark.css" />
<link rel="preload" as="script" href="../../_static/js/index.3da636dd464baa7582d2.js">
<script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
<script src="../../_static/jquery.js"></script>
<script src="../../_static/underscore.js"></script>
<script src="../../_static/doctools.js"></script>
<script src="../../_static/language_data.js"></script>
<script src="../../_static/copybutton.js"></script>
<script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
<script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script>
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Word2VecModel" href="pyspark.mllib.feature.Word2VecModel.html" />
<link rel="prev" title="IDF" href="pyspark.mllib.feature.IDF.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="en" />
</head>
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
<nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main">
<div class="container-xl">
<a class="navbar-brand" href="../../index.html">
<img src="../../_static/spark-logo-reverse.png" class="logo" alt="logo" />
</a>
<button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div id="navbar-menu" class="col-lg-9 collapse navbar-collapse">
<ul id="navbar-main-elements" class="navbar-nav mr-auto">
<li class="nav-item ">
<a class="nav-link" href="../../getting_started/index.html">Getting Started</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../user_guide/index.html">User Guide</a>
</li>
<li class="nav-item active">
<a class="nav-link" href="../index.html">API Reference</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../development/index.html">Development</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../migration_guide/index.html">Migration Guide</a>
</li>
</ul>
<ul class="navbar-nav">
</ul>
</div>
</div>
</nav>
<div class="container-xl">
<div class="row">
<div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../search.html" method="get">
<i class="icon fas fa-search"></i>
<input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" >
</form>
<nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation">
<div class="bd-toc-item active">
<ul class="nav bd-sidenav">
<li class="">
<a href="../pyspark.sql.html">Spark SQL</a>
</li>
<li class="">
<a href="../pyspark.pandas/index.html">Pandas API on Spark</a>
</li>
<li class="">
<a href="../pyspark.ss.html">Structured Streaming</a>
</li>
<li class="">
<a href="../pyspark.ml.html">MLlib (DataFrame-based)</a>
</li>
<li class="">
<a href="../pyspark.streaming.html">Spark Streaming</a>
</li>
<li class="active">
<a href="../pyspark.mllib.html">MLlib (RDD-based)</a>
</li>
<li class="">
<a href="../pyspark.html">Spark Core</a>
</li>
<li class="">
<a href="../pyspark.resource.html">Resource Management</a>
</li>
</ul>
</nav>
</div>
<div class="d-none d-xl-block col-xl-2 bd-toc">
<nav id="bd-toc-nav">
<ul class="nav section-nav flex-column">
</ul>
</nav>
</div>
<main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main">
<div>
<div class="section" id="word2vec">
<h1>Word2Vec<a class="headerlink" href="#word2vec" title="Permalink to this headline"></a></h1>
<dl class="py class">
<dt id="pyspark.mllib.feature.Word2Vec">
<em class="property">class </em><code class="sig-prename descclassname">pyspark.mllib.feature.</code><code class="sig-name descname">Word2Vec</code><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec" title="Permalink to this definition"></a></dt>
<dd><p>Word2Vec creates vector representation of words in a text corpus.
The algorithm first constructs a vocabulary from the corpus
and then learns vector representation of words in the vocabulary.
The vector representation can be used as features in
natural language processing and machine learning algorithms.</p>
<p>We used skip-gram model in our implementation and hierarchical
softmax method to train the model. The variable names in the
implementation matches the original C implementation.</p>
<p>For original C implementation,
see <a class="reference external" href="https://code.google.com/p/word2vec/">https://code.google.com/p/word2vec/</a>
For research papers, see
Efficient Estimation of Word Representations in Vector Space
and Distributed Representations of Words and Phrases and their
Compositionality.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</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="n">sentence</span> <span class="o">=</span> <span class="s2">&quot;a b &quot;</span> <span class="o">*</span> <span class="mi">100</span> <span class="o">+</span> <span class="s2">&quot;a c &quot;</span> <span class="o">*</span> <span class="mi">10</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">localDoc</span> <span class="o">=</span> <span class="p">[</span><span class="n">sentence</span><span class="p">,</span> <span class="n">sentence</span><span class="p">]</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">doc</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">localDoc</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">line</span><span class="p">:</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot; &quot;</span><span class="p">))</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span> <span class="o">=</span> <span class="n">Word2Vec</span><span class="p">()</span><span class="o">.</span><span class="n">setVectorSize</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span><span class="o">.</span><span class="n">setSeed</span><span class="p">(</span><span class="mi">42</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">doc</span><span class="p">)</span>
</pre></div>
</div>
<p>Querying for synonyms of a word will not return that word:</p>
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">syms</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">syms</span><span class="p">]</span>
<span class="go">[&#39;b&#39;, &#39;c&#39;]</span>
</pre></div>
</div>
<p>But querying for synonyms of a vector may return the word whose
representation is that vector:</p>
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">vec</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="s2">&quot;a&quot;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">syms</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="n">vec</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">syms</span><span class="p">]</span>
<span class="go">[&#39;a&#39;, &#39;b&#39;]</span>
</pre></div>
</div>
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">os</span><span class="o">,</span> <span class="nn">tempfile</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span>
<span class="gp">&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">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">sameModel</span> <span class="o">=</span> <span class="n">Word2VecModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">)</span> <span class="o">==</span> <span class="n">sameModel</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">)</span>
<span class="go">True</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">syms</span> <span class="o">=</span> <span class="n">sameModel</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">syms</span><span class="p">]</span>
<span class="go">[&#39;b&#39;, &#39;c&#39;]</span>
<span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span>
<span class="gp">&gt;&gt;&gt; </span><span class="k">try</span><span class="p">:</span>
<span class="gp">... </span> <span class="n">rmtree</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="gp">... </span><span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span>
<span class="gp">... </span> <span class="k">pass</span>
</pre></div>
</div>
<p class="rubric">Methods</p>
<table class="longtable table autosummary">
<colgroup>
<col style="width: 10%" />
<col style="width: 90%" />
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.fit" title="pyspark.mllib.feature.Word2Vec.fit"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fit</span></code></a>(data)</p></td>
<td><p>Computes the vector representation of each word in vocabulary.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setLearningRate" title="pyspark.mllib.feature.Word2Vec.setLearningRate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setLearningRate</span></code></a>(learningRate)</p></td>
<td><p>Sets initial learning rate (default: 0.025).</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setMinCount" title="pyspark.mllib.feature.Word2Vec.setMinCount"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setMinCount</span></code></a>(minCount)</p></td>
<td><p>Sets minCount, the minimum number of times a token must appear to be included in the word2vec model’s vocabulary (default: 5).</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setNumIterations" title="pyspark.mllib.feature.Word2Vec.setNumIterations"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setNumIterations</span></code></a>(numIterations)</p></td>
<td><p>Sets number of iterations (default: 1), which should be smaller than or equal to number of partitions.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setNumPartitions" title="pyspark.mllib.feature.Word2Vec.setNumPartitions"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setNumPartitions</span></code></a>(numPartitions)</p></td>
<td><p>Sets number of partitions (default: 1).</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setSeed" title="pyspark.mllib.feature.Word2Vec.setSeed"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setSeed</span></code></a>(seed)</p></td>
<td><p>Sets random seed.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setVectorSize" title="pyspark.mllib.feature.Word2Vec.setVectorSize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setVectorSize</span></code></a>(vectorSize)</p></td>
<td><p>Sets vector size (default: 100).</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.feature.Word2Vec.setWindowSize" title="pyspark.mllib.feature.Word2Vec.setWindowSize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setWindowSize</span></code></a>(windowSize)</p></td>
<td><p>Sets window size (default: 5).</p></td>
</tr>
</tbody>
</table>
<p class="rubric">Methods Documentation</p>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.fit">
<code class="sig-name descname">fit</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">data</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.fit"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.fit" title="Permalink to this definition"></a></dt>
<dd><p>Computes the vector representation of each word in vocabulary.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</span></p>
</div>
<dl class="field-list">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><dl>
<dt><strong>data</strong><span class="classifier"><a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.RDD</span></code></a></span></dt><dd><p>training data. RDD of list of string</p>
</dd>
</dl>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><dl class="simple">
<dt><a class="reference internal" href="pyspark.mllib.feature.Word2VecModel.html#pyspark.mllib.feature.Word2VecModel" title="pyspark.mllib.feature.Word2VecModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">Word2VecModel</span></code></a></dt><dd></dd>
</dl>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.setLearningRate">
<code class="sig-name descname">setLearningRate</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">learningRate</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setLearningRate"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setLearningRate" title="Permalink to this definition"></a></dt>
<dd><p>Sets initial learning rate (default: 0.025).</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.setMinCount">
<code class="sig-name descname">setMinCount</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">minCount</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setMinCount"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setMinCount" title="Permalink to this definition"></a></dt>
<dd><p>Sets minCount, the minimum number of times a token must appear
to be included in the word2vec model’s vocabulary (default: 5).</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.mllib.feature.Word2Vec.setNumIterations">
<code class="sig-name descname">setNumIterations</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">numIterations</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setNumIterations"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setNumIterations" title="Permalink to this definition"></a></dt>
<dd><p>Sets number of iterations (default: 1), which should be smaller
than or equal to number of partitions.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.setNumPartitions">
<code class="sig-name descname">setNumPartitions</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">numPartitions</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setNumPartitions"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setNumPartitions" title="Permalink to this definition"></a></dt>
<dd><p>Sets number of partitions (default: 1). Use a small number for
accuracy.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.setSeed">
<code class="sig-name descname">setSeed</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">seed</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setSeed"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setSeed" title="Permalink to this definition"></a></dt>
<dd><p>Sets random seed.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.setVectorSize">
<code class="sig-name descname">setVectorSize</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">vectorSize</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setVectorSize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setVectorSize" title="Permalink to this definition"></a></dt>
<dd><p>Sets vector size (default: 100).</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 1.2.0.</span></p>
</div>
</dd></dl>
<dl class="py method">
<dt id="pyspark.mllib.feature.Word2Vec.setWindowSize">
<code class="sig-name descname">setWindowSize</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">windowSize</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/mllib/feature.html#Word2Vec.setWindowSize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.feature.Word2Vec.setWindowSize" title="Permalink to this definition"></a></dt>
<dd><p>Sets window size (default: 5).</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 2.0.0.</span></p>
</div>
</dd></dl>
</dd></dl>
</div>
</div>
<div class='prev-next-bottom'>
<a class='left-prev' id="prev-link" href="pyspark.mllib.feature.IDF.html" title="previous page">IDF</a>
<a class='right-next' id="next-link" href="pyspark.mllib.feature.Word2VecModel.html" title="next page">Word2VecModel</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>