| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>Tokenizer — PySpark 3.3.3 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="UnivariateFeatureSelector" href="pyspark.ml.feature.UnivariateFeatureSelector.html" /> |
| <link rel="prev" title="StringIndexerModel" href="pyspark.ml.feature.StringIndexerModel.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/index.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/index.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="tokenizer"> |
| <h1>Tokenizer<a class="headerlink" href="#tokenizer" title="Permalink to this headline">¶</a></h1> |
| <dl class="py class"> |
| <dt id="pyspark.ml.feature.Tokenizer"> |
| <em class="property">class </em><code class="sig-prename descclassname">pyspark.ml.feature.</code><code class="sig-name descname">Tokenizer</code><span class="sig-paren">(</span><em class="sig-param"><span class="o">*</span></em>, <em class="sig-param"><span class="n">inputCol</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>str<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">outputCol</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>str<span class="p">]</span></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/feature.html#Tokenizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer" title="Permalink to this definition">¶</a></dt> |
| <dd><p>A tokenizer that converts the input string to lowercase and then |
| splits it by white spaces.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </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="s2">"a b c"</span><span class="p">,)],</span> <span class="p">[</span><span class="s2">"text"</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</span> <span class="o">=</span> <span class="n">Tokenizer</span><span class="p">(</span><span class="n">outputCol</span><span class="o">=</span><span class="s2">"words"</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">setInputCol</span><span class="p">(</span><span class="s2">"text"</span><span class="p">)</span> |
| <span class="go">Tokenizer...</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</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="go">Row(text='a b c', words=['a', 'b', 'c'])</span> |
| <span class="gp">>>> </span><span class="c1"># Change a parameter.</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</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">"tokens"</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">head</span><span class="p">()</span> |
| <span class="go">Row(text='a b c', tokens=['a', 'b', 'c'])</span> |
| <span class="gp">>>> </span><span class="c1"># Temporarily modify a parameter.</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</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="p">{</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">outputCol</span><span class="p">:</span> <span class="s2">"words"</span><span class="p">})</span><span class="o">.</span><span class="n">head</span><span class="p">()</span> |
| <span class="go">Row(text='a b c', words=['a', 'b', 'c'])</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</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="go">Row(text='a b c', tokens=['a', 'b', 'c'])</span> |
| <span class="gp">>>> </span><span class="c1"># Must use keyword arguments to specify params.</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="s2">"text"</span><span class="p">)</span> |
| <span class="gt">Traceback (most recent call last):</span> |
| <span class="w"> </span><span class="o">...</span> |
| <span class="gr">TypeError</span>: <span class="n">Method setParams forces keyword arguments.</span> |
| <span class="gp">>>> </span><span class="n">tokenizerPath</span> <span class="o">=</span> <span class="n">temp_path</span> <span class="o">+</span> <span class="s2">"/tokenizer"</span> |
| <span class="gp">>>> </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">tokenizerPath</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">loadedTokenizer</span> <span class="o">=</span> <span class="n">Tokenizer</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">tokenizerPath</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">loadedTokenizer</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">tokens</span> <span class="o">==</span> <span class="n">tokenizer</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">tokens</span> |
| <span class="go">True</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.Tokenizer.clear" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.copy" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.explainParam" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.explainParams" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.extractParamMap" title="pyspark.ml.feature.Tokenizer.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 < user-supplied values < extra.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.Tokenizer.getInputCol" title="pyspark.ml.feature.Tokenizer.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-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.Tokenizer.getOrDefault" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.getOutputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.getParam" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.hasDefault" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.hasParam" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.isDefined" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.isSet" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.load" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.read" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.save" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.set" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.setInputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.inputCol" title="pyspark.ml.feature.Tokenizer.inputCol"><code class="xref py py-attr docutils literal notranslate"><span class="pre">inputCol</span></code></a>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.Tokenizer.setOutputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.outputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.setParams" title="pyspark.ml.feature.Tokenizer.setParams"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setParams</span></code></a>(self, \*[, inputCol, outputCol])</p></td> |
| <td><p>Sets params for this Tokenizer.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.ml.feature.Tokenizer.transform" title="pyspark.ml.feature.Tokenizer.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.feature.Tokenizer.write" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.inputCol" title="pyspark.ml.feature.Tokenizer.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-even"><td><p><a class="reference internal" href="#pyspark.ml.feature.Tokenizer.outputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.params" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.clear"> |
| <code class="sig-name descname">clear</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n"><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a></span></em><span class="sig-paren">)</span> → None<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.copy"> |
| <code class="sig-name descname">copy</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">extra</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>ParamMap<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → JP<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.explainParam"> |
| <code class="sig-name descname">explainParam</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>str<span class="p">, </span><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a><span class="p">]</span></span></em><span class="sig-paren">)</span> → str<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.explainParams"> |
| <code class="sig-name descname">explainParams</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → str<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.extractParamMap"> |
| <code class="sig-name descname">extractParamMap</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">extra</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>ParamMap<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → ParamMap<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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 < |
| user-supplied values < 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.Tokenizer.getInputCol"> |
| <code class="sig-name descname">getInputCol</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → str<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.getOrDefault"> |
| <code class="sig-name descname">getOrDefault</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>str<span class="p">, </span><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a><span class="p">[</span>T<span class="p">]</span><span class="p">]</span></span></em><span class="sig-paren">)</span> → Union<span class="p">[</span>Any<span class="p">, </span>T<span class="p">]</span><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.getOutputCol"> |
| <code class="sig-name descname">getOutputCol</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → str<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.getParam"> |
| <code class="sig-name descname">getParam</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">paramName</span><span class="p">:</span> <span class="n">str</span></em><span class="sig-paren">)</span> → <a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.hasDefault"> |
| <code class="sig-name descname">hasDefault</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>str<span class="p">, </span><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a><span class="p">[</span>Any<span class="p">]</span><span class="p">]</span></span></em><span class="sig-paren">)</span> → bool<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.hasParam"> |
| <code class="sig-name descname">hasParam</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">paramName</span><span class="p">:</span> <span class="n">str</span></em><span class="sig-paren">)</span> → bool<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.isDefined"> |
| <code class="sig-name descname">isDefined</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>str<span class="p">, </span><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a><span class="p">[</span>Any<span class="p">]</span><span class="p">]</span></span></em><span class="sig-paren">)</span> → bool<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.isSet"> |
| <code class="sig-name descname">isSet</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>str<span class="p">, </span><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a><span class="p">[</span>Any<span class="p">]</span><span class="p">]</span></span></em><span class="sig-paren">)</span> → bool<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.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><span class="p">:</span> <span class="n">str</span></em><span class="sig-paren">)</span> → RL<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.read"> |
| <em class="property">classmethod </em><code class="sig-name descname">read</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → pyspark.ml.util.JavaMLReader<span class="p">[</span>RL<span class="p">]</span><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">path</span><span class="p">:</span> <span class="n">str</span></em><span class="sig-paren">)</span> → None<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.set"> |
| <code class="sig-name descname">set</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">param</span><span class="p">:</span> <span class="n"><a class="reference internal" href="pyspark.ml.param.Param.html#pyspark.ml.param.Param" title="pyspark.ml.param.Param">pyspark.ml.param.Param</a></span></em>, <em class="sig-param"><span class="n">value</span><span class="p">:</span> <span class="n">Any</span></em><span class="sig-paren">)</span> → None<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.setInputCol"> |
| <code class="sig-name descname">setInputCol</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span><span class="p">:</span> <span class="n">str</span></em><span class="sig-paren">)</span> → <a class="reference internal" href="#pyspark.ml.feature.Tokenizer" title="pyspark.ml.feature.Tokenizer">pyspark.ml.feature.Tokenizer</a><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#Tokenizer.setInputCol"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.setInputCol" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.Tokenizer.inputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.setOutputCol"> |
| <code class="sig-name descname">setOutputCol</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">value</span><span class="p">:</span> <span class="n">str</span></em><span class="sig-paren">)</span> → <a class="reference internal" href="#pyspark.ml.feature.Tokenizer" title="pyspark.ml.feature.Tokenizer">pyspark.ml.feature.Tokenizer</a><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#Tokenizer.setOutputCol"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.setOutputCol" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets the value of <a class="reference internal" href="#pyspark.ml.feature.Tokenizer.outputCol" title="pyspark.ml.feature.Tokenizer.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.Tokenizer.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">inputCol=None</em>, <em class="sig-param">outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/ml/feature.html#Tokenizer.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.setParams" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets params for this Tokenizer.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.ml.feature.Tokenizer.transform"> |
| <code class="sig-name descname">transform</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">dataset</span><span class="p">:</span> <span class="n">pyspark.sql.dataframe.DataFrame</span></em>, <em class="sig-param"><span class="n">params</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>ParamMap<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.sql.dataframe.DataFrame<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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/api/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/api/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.feature.Tokenizer.write"> |
| <code class="sig-name descname">write</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → pyspark.ml.util.JavaMLWriter<a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.Tokenizer.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.Tokenizer.inputCol" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py attribute"> |
| <dt id="pyspark.ml.feature.Tokenizer.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.Tokenizer.outputCol" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py attribute"> |
| <dt id="pyspark.ml.feature.Tokenizer.params"> |
| <code class="sig-name descname">params</code><a class="headerlink" href="#pyspark.ml.feature.Tokenizer.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.StringIndexerModel.html" title="previous page">StringIndexerModel</a> |
| <a class='right-next' id="next-link" href="pyspark.ml.feature.UnivariateFeatureSelector.html" title="next page">UnivariateFeatureSelector</a> |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
