| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.feature — 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" /> |
| <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 "> |
| <a class="nav-link" href="../../../reference/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"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </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> |
| |
| <h1>Source code for pyspark.mllib.feature</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">Python package for feature in MLlib.</span> |
| <span class="sd">"""</span> |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">import</span> <span class="nn">warnings</span> |
| <span class="kn">from</span> <span class="nn">py4j.protocol</span> <span class="kn">import</span> <span class="n">Py4JJavaError</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.rdd</span> <span class="kn">import</span> <span class="n">RDD</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">callMLlibFunc</span><span class="p">,</span> <span class="n">JavaModelWrapper</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span><span class="p">,</span> <span class="n">_convert_to_vector</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">JavaLoader</span><span class="p">,</span> <span class="n">JavaSaveable</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'Normalizer'</span><span class="p">,</span> <span class="s1">'StandardScalerModel'</span><span class="p">,</span> <span class="s1">'StandardScaler'</span><span class="p">,</span> |
| <span class="s1">'HashingTF'</span><span class="p">,</span> <span class="s1">'IDFModel'</span><span class="p">,</span> <span class="s1">'IDF'</span><span class="p">,</span> <span class="s1">'Word2Vec'</span><span class="p">,</span> <span class="s1">'Word2VecModel'</span><span class="p">,</span> |
| <span class="s1">'ChiSqSelector'</span><span class="p">,</span> <span class="s1">'ChiSqSelectorModel'</span><span class="p">,</span> <span class="s1">'ElementwiseProduct'</span><span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">VectorTransformer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Base class for transformation of a vector or RDD of vector</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Applies transformation on a vector.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> vector : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> vector or convertible or RDD to be transformed.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span> |
| |
| |
| <div class="viewcode-block" id="Normalizer"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Normalizer.html#pyspark.mllib.feature.Normalizer">[docs]</a><span class="k">class</span> <span class="nc">Normalizer</span><span class="p">(</span><span class="n">VectorTransformer</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""</span> |
| <span class="sd"> Normalizes samples individually to unit L\ :sup:`p`\ norm</span> |
| |
| <span class="sd"> For any 1 <= `p` < float('inf'), normalizes samples using</span> |
| <span class="sd"> sum(abs(vector) :sup:`p`) :sup:`(1/p)` as norm.</span> |
| |
| <span class="sd"> For `p` = float('inf'), max(abs(vector)) will be used as norm for</span> |
| <span class="sd"> normalization.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> p : float, optional</span> |
| <span class="sd"> Normalization in L^p^ space, p = 2 by default.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span> |
| <span class="sd"> >>> v = Vectors.dense(range(3))</span> |
| <span class="sd"> >>> nor = Normalizer(1)</span> |
| <span class="sd"> >>> nor.transform(v)</span> |
| <span class="sd"> DenseVector([0.0, 0.3333, 0.6667])</span> |
| |
| <span class="sd"> >>> rdd = sc.parallelize([v])</span> |
| <span class="sd"> >>> nor.transform(rdd).collect()</span> |
| <span class="sd"> [DenseVector([0.0, 0.3333, 0.6667])]</span> |
| |
| <span class="sd"> >>> nor2 = Normalizer(float("inf"))</span> |
| <span class="sd"> >>> nor2.transform(v)</span> |
| <span class="sd"> DenseVector([0.0, 0.5, 1.0])</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">p</span><span class="o">=</span><span class="mf">2.0</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">p</span> <span class="o">>=</span> <span class="mf">1.0</span><span class="p">,</span> <span class="s2">"p should be greater than 1.0"</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">p</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="Normalizer.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Normalizer.html#pyspark.mllib.feature.Normalizer.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Applies unit length normalization on a vector.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> vector : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> vector or RDD of vector to be normalized.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> normalized vector(s). If the norm of the input is zero, it</span> |
| <span class="sd"> will return the input vector.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="n">vector</span> <span class="o">=</span> <span class="n">vector</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">vector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"normalizeVector"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">p</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span></div></div> |
| |
| |
| <span class="k">class</span> <span class="nc">JavaVectorTransformer</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">VectorTransformer</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Wrapper for the model in JVM</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Applies transformation on a vector or an RDD[Vector].</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> vector : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> Input vector(s) to be transformed.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> In Python, transform cannot currently be used within</span> |
| <span class="sd"> an RDD transformation or action.</span> |
| <span class="sd"> Call transform directly on the RDD instead.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="n">vector</span> <span class="o">=</span> <span class="n">vector</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">vector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"transform"</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="StandardScalerModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.StandardScalerModel.html#pyspark.mllib.feature.StandardScalerModel">[docs]</a><span class="k">class</span> <span class="nc">StandardScalerModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Represents a StandardScaler model that can transform vectors.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="StandardScalerModel.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.StandardScalerModel.html#pyspark.mllib.feature.StandardScalerModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Applies standardization transformation on a vector.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> vector : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> Input vector(s) to be standardized.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> Standardized vector(s). If the variance of a column is</span> |
| <span class="sd"> zero, it will return default `0.0` for the column with</span> |
| <span class="sd"> zero variance.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> In Python, transform cannot currently be used within</span> |
| <span class="sd"> an RDD transformation or action.</span> |
| <span class="sd"> Call transform directly on the RDD instead.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">JavaVectorTransformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="StandardScalerModel.setWithMean"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.StandardScalerModel.html#pyspark.mllib.feature.StandardScalerModel.setWithMean">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.4.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWithMean</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">withMean</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Setter of the boolean which decides</span> |
| <span class="sd"> whether it uses mean or not</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"setWithMean"</span><span class="p">,</span> <span class="n">withMean</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="StandardScalerModel.setWithStd"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.StandardScalerModel.html#pyspark.mllib.feature.StandardScalerModel.setWithStd">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.4.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWithStd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">withStd</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Setter of the boolean which decides</span> |
| <span class="sd"> whether it uses std or not</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"setWithStd"</span><span class="p">,</span> <span class="n">withStd</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">withStd</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns if the model scales the data to unit standard deviation.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"withStd"</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">withMean</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns if the model centers the data before scaling.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"withMean"</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">std</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Return the column standard deviation values.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"std"</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">mean</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Return the column mean values.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"mean"</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="StandardScaler"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.StandardScaler.html#pyspark.mllib.feature.StandardScaler">[docs]</a><span class="k">class</span> <span class="nc">StandardScaler</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Standardizes features by removing the mean and scaling to unit</span> |
| <span class="sd"> variance using column summary statistics on the samples in the</span> |
| <span class="sd"> training set.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> withMean : bool, optional</span> |
| <span class="sd"> False by default. Centers the data with mean</span> |
| <span class="sd"> before scaling. It will build a dense output, so take</span> |
| <span class="sd"> care when applying to sparse input.</span> |
| <span class="sd"> withStd : bool, optional</span> |
| <span class="sd"> True by default. Scales the data to unit</span> |
| <span class="sd"> standard deviation.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> vs = [Vectors.dense([-2.0, 2.3, 0]), Vectors.dense([3.8, 0.0, 1.9])]</span> |
| <span class="sd"> >>> dataset = sc.parallelize(vs)</span> |
| <span class="sd"> >>> standardizer = StandardScaler(True, True)</span> |
| <span class="sd"> >>> model = standardizer.fit(dataset)</span> |
| <span class="sd"> >>> result = model.transform(dataset)</span> |
| <span class="sd"> >>> for r in result.collect(): r</span> |
| <span class="sd"> DenseVector([-0.7071, 0.7071, -0.7071])</span> |
| <span class="sd"> DenseVector([0.7071, -0.7071, 0.7071])</span> |
| <span class="sd"> >>> int(model.std[0])</span> |
| <span class="sd"> 4</span> |
| <span class="sd"> >>> int(model.mean[0]*10)</span> |
| <span class="sd"> 9</span> |
| <span class="sd"> >>> model.withStd</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> model.withMean</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">withMean</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">withStd</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">withMean</span> <span class="ow">or</span> <span class="n">withStd</span><span class="p">):</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s2">"Both withMean and withStd are false. The model does nothing."</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">withMean</span> <span class="o">=</span> <span class="n">withMean</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">withStd</span> <span class="o">=</span> <span class="n">withStd</span> |
| |
| <div class="viewcode-block" id="StandardScaler.fit"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.StandardScaler.html#pyspark.mllib.feature.StandardScaler.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Computes the mean and variance and stores as a model to be used</span> |
| <span class="sd"> for later scaling.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The data used to compute the mean and variance</span> |
| <span class="sd"> to build the transformation model.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`StandardScalerModel`</span> |
| <span class="sd"> """</span> |
| <span class="n">dataset</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">)</span> |
| <span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"fitStandardScaler"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">withMean</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">withStd</span><span class="p">,</span> <span class="n">dataset</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">StandardScalerModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ChiSqSelectorModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelectorModel.html#pyspark.mllib.feature.ChiSqSelectorModel">[docs]</a><span class="k">class</span> <span class="nc">ChiSqSelectorModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Represents a Chi Squared selector model.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="ChiSqSelectorModel.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelectorModel.html#pyspark.mllib.feature.ChiSqSelectorModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Applies transformation on a vector.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> vector : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> Input vector(s) to be transformed.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> transformed vector(s).</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">JavaVectorTransformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ChiSqSelector"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector">[docs]</a><span class="k">class</span> <span class="nc">ChiSqSelector</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Creates a ChiSquared feature selector.</span> |
| <span class="sd"> The selector supports different selection methods: `numTopFeatures`, `percentile`, `fpr`,</span> |
| <span class="sd"> `fdr`, `fwe`.</span> |
| |
| <span class="sd"> * `numTopFeatures` chooses a fixed number of top features according to a chi-squared test.</span> |
| |
| <span class="sd"> * `percentile` is similar but chooses a fraction of all features</span> |
| <span class="sd"> instead of a fixed number.</span> |
| |
| <span class="sd"> * `fpr` chooses all features whose p-values are below a threshold,</span> |
| <span class="sd"> thus controlling the false positive rate of selection.</span> |
| |
| <span class="sd"> * `fdr` uses the `Benjamini-Hochberg procedure <https://en.wikipedia.org/wiki/</span> |
| <span class="sd"> False_discovery_rate#Benjamini.E2.80.93Hochberg_procedure>`_</span> |
| <span class="sd"> to choose all features whose false discovery rate is below a threshold.</span> |
| |
| <span class="sd"> * `fwe` chooses all features whose p-values are below a threshold. The threshold is scaled by</span> |
| <span class="sd"> 1/numFeatures, thus controlling the family-wise error rate of selection.</span> |
| |
| <span class="sd"> By default, the selection method is `numTopFeatures`, with the default number of top features</span> |
| <span class="sd"> set to 50.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector, DenseVector</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> data = sc.parallelize([</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(3, {0: 8.0, 1: 7.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(3, {1: 9.0, 2: 6.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [0.0, 9.0, 8.0]),</span> |
| <span class="sd"> ... LabeledPoint(2.0, [7.0, 9.0, 5.0]),</span> |
| <span class="sd"> ... LabeledPoint(2.0, [8.0, 7.0, 3.0])</span> |
| <span class="sd"> ... ])</span> |
| <span class="sd"> >>> model = ChiSqSelector(numTopFeatures=1).fit(data)</span> |
| <span class="sd"> >>> model.transform(SparseVector(3, {1: 9.0, 2: 6.0}))</span> |
| <span class="sd"> SparseVector(1, {})</span> |
| <span class="sd"> >>> model.transform(DenseVector([7.0, 9.0, 5.0]))</span> |
| <span class="sd"> DenseVector([7.0])</span> |
| <span class="sd"> >>> model = ChiSqSelector(selectorType="fpr", fpr=0.2).fit(data)</span> |
| <span class="sd"> >>> model.transform(SparseVector(3, {1: 9.0, 2: 6.0}))</span> |
| <span class="sd"> SparseVector(1, {})</span> |
| <span class="sd"> >>> model.transform(DenseVector([7.0, 9.0, 5.0]))</span> |
| <span class="sd"> DenseVector([7.0])</span> |
| <span class="sd"> >>> model = ChiSqSelector(selectorType="percentile", percentile=0.34).fit(data)</span> |
| <span class="sd"> >>> model.transform(DenseVector([7.0, 9.0, 5.0]))</span> |
| <span class="sd"> DenseVector([7.0])</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numTopFeatures</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">selectorType</span><span class="o">=</span><span class="s2">"numTopFeatures"</span><span class="p">,</span> <span class="n">percentile</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">fpr</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> |
| <span class="n">fdr</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">fwe</span><span class="o">=</span><span class="mf">0.05</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numTopFeatures</span> <span class="o">=</span> <span class="n">numTopFeatures</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">selectorType</span> <span class="o">=</span> <span class="n">selectorType</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">percentile</span> <span class="o">=</span> <span class="n">percentile</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fpr</span> <span class="o">=</span> <span class="n">fpr</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fdr</span> <span class="o">=</span> <span class="n">fdr</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fwe</span> <span class="o">=</span> <span class="n">fwe</span> |
| |
| <div class="viewcode-block" id="ChiSqSelector.setNumTopFeatures"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.setNumTopFeatures">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.1.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setNumTopFeatures</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numTopFeatures</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> set numTopFeature for feature selection by number of top features.</span> |
| <span class="sd"> Only applicable when selectorType = "numTopFeatures".</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numTopFeatures</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">numTopFeatures</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="ChiSqSelector.setPercentile"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.setPercentile">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.1.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPercentile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">percentile</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> set percentile [0.0, 1.0] for feature selection by percentile.</span> |
| <span class="sd"> Only applicable when selectorType = "percentile".</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">percentile</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">percentile</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="ChiSqSelector.setFpr"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.setFpr">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.1.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setFpr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fpr</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> set FPR [0.0, 1.0] for feature selection by FPR.</span> |
| <span class="sd"> Only applicable when selectorType = "fpr".</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fpr</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">fpr</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="ChiSqSelector.setFdr"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.setFdr">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setFdr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fdr</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> set FDR [0.0, 1.0] for feature selection by FDR.</span> |
| <span class="sd"> Only applicable when selectorType = "fdr".</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fdr</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">fdr</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="ChiSqSelector.setFwe"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.setFwe">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setFwe</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fwe</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> set FWE [0.0, 1.0] for feature selection by FWE.</span> |
| <span class="sd"> Only applicable when selectorType = "fwe".</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fwe</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">fwe</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="ChiSqSelector.setSelectorType"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.setSelectorType">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.1.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setSelectorType</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">selectorType</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> set the selector type of the ChisqSelector.</span> |
| <span class="sd"> Supported options: "numTopFeatures" (default), "percentile", "fpr", "fdr", "fwe".</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">selectorType</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">selectorType</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="ChiSqSelector.fit"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ChiSqSelector.html#pyspark.mllib.feature.ChiSqSelector.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns a ChiSquared feature selector.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD` of :py:class:`pyspark.mllib.regression.LabeledPoint`</span> |
| <span class="sd"> containing the labeled dataset with categorical features.</span> |
| <span class="sd"> Real-valued features will be treated as categorical for each</span> |
| <span class="sd"> distinct value. Apply feature discretizer before using this function.</span> |
| <span class="sd"> """</span> |
| <span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"fitChiSqSelector"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">selectorType</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numTopFeatures</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">percentile</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fpr</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fdr</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fwe</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">ChiSqSelectorModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span></div></div> |
| |
| |
| <span class="k">class</span> <span class="nc">PCAModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| <span class="sd"> """</span> |
| |
| |
| <span class="k">class</span> <span class="nc">PCA</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> A feature transformer that projects vectors to a low-dimensional space using PCA.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> data = [Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),</span> |
| <span class="sd"> ... Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]),</span> |
| <span class="sd"> ... Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0])]</span> |
| <span class="sd"> >>> model = PCA(2).fit(sc.parallelize(data))</span> |
| <span class="sd"> >>> pcArray = model.transform(Vectors.sparse(5, [(1, 1.0), (3, 7.0)])).toArray()</span> |
| <span class="sd"> >>> pcArray[0]</span> |
| <span class="sd"> 1.648...</span> |
| <span class="sd"> >>> pcArray[1]</span> |
| <span class="sd"> -4.013...</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> k : int</span> |
| <span class="sd"> number of principal components.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">k</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Computes a [[PCAModel]] that contains the principal components of the input vectors.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> source vectors</span> |
| <span class="sd"> """</span> |
| <span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"fitPCA"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">k</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">PCAModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="HashingTF"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.HashingTF.html#pyspark.mllib.feature.HashingTF">[docs]</a><span class="k">class</span> <span class="nc">HashingTF</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Maps a sequence of terms to their term frequencies using the hashing</span> |
| <span class="sd"> trick.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> numFeatures : int, optional</span> |
| <span class="sd"> number of features (default: 2^20)</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> The terms must be hashable (can not be dict/set/list...).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> htf = HashingTF(100)</span> |
| <span class="sd"> >>> doc = "a a b b c d".split(" ")</span> |
| <span class="sd"> >>> htf.transform(doc)</span> |
| <span class="sd"> SparseVector(100, {...})</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numFeatures</span><span class="o">=</span><span class="mi">1</span> <span class="o"><<</span> <span class="mi">20</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numFeatures</span> <span class="o">=</span> <span class="n">numFeatures</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">binary</span> <span class="o">=</span> <span class="kc">False</span> |
| |
| <div class="viewcode-block" id="HashingTF.setBinary"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.HashingTF.html#pyspark.mllib.feature.HashingTF.setBinary">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setBinary</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> If True, term frequency vector will be binary such that non-zero</span> |
| <span class="sd"> term counts will be set to 1</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">binary</span> <span class="o">=</span> <span class="n">value</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="HashingTF.indexOf"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.HashingTF.html#pyspark.mllib.feature.HashingTF.indexOf">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">indexOf</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">term</span><span class="p">):</span> |
| <span class="sd">""" Returns the index of the input term. """</span> |
| <span class="k">return</span> <span class="nb">hash</span><span class="p">(</span><span class="n">term</span><span class="p">)</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">numFeatures</span></div> |
| |
| <div class="viewcode-block" id="HashingTF.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.HashingTF.html#pyspark.mllib.feature.HashingTF.transform">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">document</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Transforms the input document (list of terms) to term frequency</span> |
| <span class="sd"> vectors, or transform the RDD of document to RDD of term</span> |
| <span class="sd"> frequency vectors.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">document</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">document</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transform</span><span class="p">)</span> |
| |
| <span class="n">freq</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">term</span> <span class="ow">in</span> <span class="n">document</span><span class="p">:</span> |
| <span class="n">i</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">indexOf</span><span class="p">(</span><span class="n">term</span><span class="p">)</span> |
| <span class="n">freq</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">binary</span> <span class="k">else</span> <span class="n">freq</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="o">+</span> <span class="mf">1.0</span> |
| <span class="k">return</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">sparse</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numFeatures</span><span class="p">,</span> <span class="n">freq</span><span class="o">.</span><span class="n">items</span><span class="p">())</span></div></div> |
| |
| |
| <div class="viewcode-block" id="IDFModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDFModel.html#pyspark.mllib.feature.IDFModel">[docs]</a><span class="k">class</span> <span class="nc">IDFModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Represents an IDF model that can transform term frequency vectors.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="IDFModel.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDFModel.html#pyspark.mllib.feature.IDFModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Transforms term frequency (TF) vectors to TF-IDF vectors.</span> |
| |
| <span class="sd"> If `minDocFreq` was set for the IDF calculation,</span> |
| <span class="sd"> the terms which occur in fewer than `minDocFreq`</span> |
| <span class="sd"> documents will have an entry of 0.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> x : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of term frequency vectors or a term frequency</span> |
| <span class="sd"> vector</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of TF-IDF vectors or a TF-IDF vector</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> In Python, transform cannot currently be used within</span> |
| <span class="sd"> an RDD transformation or action.</span> |
| <span class="sd"> Call transform directly on the RDD instead.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">JavaVectorTransformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="IDFModel.idf"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDFModel.html#pyspark.mllib.feature.IDFModel.idf">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.4.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">idf</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns the current IDF vector.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s1">'idf'</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="IDFModel.docFreq"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDFModel.html#pyspark.mllib.feature.IDFModel.docFreq">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'3.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">docFreq</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns the document frequency.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s1">'docFreq'</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="IDFModel.numDocs"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDFModel.html#pyspark.mllib.feature.IDFModel.numDocs">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'3.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">numDocs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns number of documents evaluated to compute idf</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s1">'numDocs'</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="IDF"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDF.html#pyspark.mllib.feature.IDF">[docs]</a><span class="k">class</span> <span class="nc">IDF</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Inverse document frequency (IDF).</span> |
| |
| <span class="sd"> The standard formulation is used: `idf = log((m + 1) / (d(t) + 1))`,</span> |
| <span class="sd"> where `m` is the total number of documents and `d(t)` is the number</span> |
| <span class="sd"> of documents that contain term `t`.</span> |
| |
| <span class="sd"> This implementation supports filtering out terms which do not appear</span> |
| <span class="sd"> in a minimum number of documents (controlled by the variable</span> |
| <span class="sd"> `minDocFreq`). For terms that are not in at least `minDocFreq`</span> |
| <span class="sd"> documents, the IDF is found as 0, resulting in TF-IDFs of 0.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> minDocFreq : int</span> |
| <span class="sd"> minimum of documents in which a term should appear for filtering</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> n = 4</span> |
| <span class="sd"> >>> freqs = [Vectors.sparse(n, (1, 3), (1.0, 2.0)),</span> |
| <span class="sd"> ... Vectors.dense([0.0, 1.0, 2.0, 3.0]),</span> |
| <span class="sd"> ... Vectors.sparse(n, [1], [1.0])]</span> |
| <span class="sd"> >>> data = sc.parallelize(freqs)</span> |
| <span class="sd"> >>> idf = IDF()</span> |
| <span class="sd"> >>> model = idf.fit(data)</span> |
| <span class="sd"> >>> tfidf = model.transform(data)</span> |
| <span class="sd"> >>> for r in tfidf.collect(): r</span> |
| <span class="sd"> SparseVector(4, {1: 0.0, 3: 0.5754})</span> |
| <span class="sd"> DenseVector([0.0, 0.0, 1.3863, 0.863])</span> |
| <span class="sd"> SparseVector(4, {1: 0.0})</span> |
| <span class="sd"> >>> model.transform(Vectors.dense([0.0, 1.0, 2.0, 3.0]))</span> |
| <span class="sd"> DenseVector([0.0, 0.0, 1.3863, 0.863])</span> |
| <span class="sd"> >>> model.transform([0.0, 1.0, 2.0, 3.0])</span> |
| <span class="sd"> DenseVector([0.0, 0.0, 1.3863, 0.863])</span> |
| <span class="sd"> >>> model.transform(Vectors.sparse(n, (1, 3), (1.0, 2.0)))</span> |
| <span class="sd"> SparseVector(4, {1: 0.0, 3: 0.5754})</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">minDocFreq</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">minDocFreq</span> <span class="o">=</span> <span class="n">minDocFreq</span> |
| |
| <div class="viewcode-block" id="IDF.fit"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.IDF.html#pyspark.mllib.feature.IDF.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Computes the inverse document frequency.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of term frequency vectors</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"dataset should be an RDD of term frequency vectors"</span><span class="p">)</span> |
| <span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"fitIDF"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">minDocFreq</span><span class="p">,</span> <span class="n">dataset</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">IDFModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Word2VecModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2VecModel.html#pyspark.mllib.feature.Word2VecModel">[docs]</a><span class="k">class</span> <span class="nc">Word2VecModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">,</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> class for Word2Vec model</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Word2VecModel.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2VecModel.html#pyspark.mllib.feature.Word2VecModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">word</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Transforms a word to its vector representation</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> word : str</span> |
| <span class="sd"> a word</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector`</span> |
| <span class="sd"> vector representation of word(s)</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Local use only</span> |
| <span class="sd"> """</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"transform"</span><span class="p">,</span> <span class="n">word</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">Py4JJavaError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2"> not found"</span> <span class="o">%</span> <span class="n">word</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Word2VecModel.findSynonyms"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2VecModel.html#pyspark.mllib.feature.Word2VecModel.findSynonyms">[docs]</a> <span class="k">def</span> <span class="nf">findSynonyms</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">word</span><span class="p">,</span> <span class="n">num</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Find synonyms of a word</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| |
| <span class="sd"> word : str or :py:class:`pyspark.mllib.linalg.Vector`</span> |
| <span class="sd"> a word or a vector representation of word</span> |
| <span class="sd"> num : int</span> |
| <span class="sd"> number of synonyms to find</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`collections.abc.Iterable`</span> |
| <span class="sd"> array of (word, cosineSimilarity)</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Local use only</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">word</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">word</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">word</span><span class="p">)</span> |
| <span class="n">words</span><span class="p">,</span> <span class="n">similarity</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"findSynonyms"</span><span class="p">,</span> <span class="n">word</span><span class="p">,</span> <span class="n">num</span><span class="p">)</span> |
| <span class="k">return</span> <span class="nb">zip</span><span class="p">(</span><span class="n">words</span><span class="p">,</span> <span class="n">similarity</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Word2VecModel.getVectors"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2VecModel.html#pyspark.mllib.feature.Word2VecModel.getVectors">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.4.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getVectors</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns a map of words to their vector representations.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"getVectors"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Word2VecModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2VecModel.html#pyspark.mllib.feature.Word2VecModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.5.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="bp">cls</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="sd">"""</span> |
| <span class="sd"> Load a model from the given path.</span> |
| <span class="sd"> """</span> |
| <span class="n">jmodel</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">feature</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="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">api</span><span class="o">.</span><span class="n">python</span><span class="o">.</span><span class="n">Word2VecModelWrapper</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">Word2VecModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Word2Vec"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec">[docs]</a><span class="k">class</span> <span class="nc">Word2Vec</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Word2Vec creates vector representation of words in a text corpus.</span> |
| <span class="sd"> The algorithm first constructs a vocabulary from the corpus</span> |
| <span class="sd"> and then learns vector representation of words in the vocabulary.</span> |
| <span class="sd"> The vector representation can be used as features in</span> |
| <span class="sd"> natural language processing and machine learning algorithms.</span> |
| |
| <span class="sd"> We used skip-gram model in our implementation and hierarchical</span> |
| <span class="sd"> softmax method to train the model. The variable names in the</span> |
| <span class="sd"> implementation matches the original C implementation.</span> |
| |
| <span class="sd"> For original C implementation,</span> |
| <span class="sd"> see https://code.google.com/p/word2vec/</span> |
| <span class="sd"> For research papers, see</span> |
| <span class="sd"> Efficient Estimation of Word Representations in Vector Space</span> |
| <span class="sd"> and Distributed Representations of Words and Phrases and their</span> |
| <span class="sd"> Compositionality.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> sentence = "a b " * 100 + "a c " * 10</span> |
| <span class="sd"> >>> localDoc = [sentence, sentence]</span> |
| <span class="sd"> >>> doc = sc.parallelize(localDoc).map(lambda line: line.split(" "))</span> |
| <span class="sd"> >>> model = Word2Vec().setVectorSize(10).setSeed(42).fit(doc)</span> |
| |
| <span class="sd"> Querying for synonyms of a word will not return that word:</span> |
| |
| <span class="sd"> >>> syms = model.findSynonyms("a", 2)</span> |
| <span class="sd"> >>> [s[0] for s in syms]</span> |
| <span class="sd"> ['b', 'c']</span> |
| |
| <span class="sd"> But querying for synonyms of a vector may return the word whose</span> |
| <span class="sd"> representation is that vector:</span> |
| |
| <span class="sd"> >>> vec = model.transform("a")</span> |
| <span class="sd"> >>> syms = model.findSynonyms(vec, 2)</span> |
| <span class="sd"> >>> [s[0] for s in syms]</span> |
| <span class="sd"> ['a', 'b']</span> |
| |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> model.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = Word2VecModel.load(sc, path)</span> |
| <span class="sd"> >>> model.transform("a") == sameModel.transform("a")</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> syms = sameModel.findSynonyms("a", 2)</span> |
| <span class="sd"> >>> [s[0] for s in syms]</span> |
| <span class="sd"> ['b', 'c']</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except OSError:</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Construct Word2Vec instance</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">vectorSize</span> <span class="o">=</span> <span class="mi">100</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">learningRate</span> <span class="o">=</span> <span class="mf">0.025</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numPartitions</span> <span class="o">=</span> <span class="mi">1</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span> <span class="o">=</span> <span class="mi">1</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">minCount</span> <span class="o">=</span> <span class="mi">5</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">windowSize</span> <span class="o">=</span> <span class="mi">5</span> |
| |
| <div class="viewcode-block" id="Word2Vec.setVectorSize"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setVectorSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setVectorSize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vectorSize</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets vector size (default: 100).</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">vectorSize</span> <span class="o">=</span> <span class="n">vectorSize</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.setLearningRate"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setLearningRate">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setLearningRate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">learningRate</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets initial learning rate (default: 0.025).</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">learningRate</span> <span class="o">=</span> <span class="n">learningRate</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.setNumPartitions"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setNumPartitions">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setNumPartitions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets number of partitions (default: 1). Use a small number for</span> |
| <span class="sd"> accuracy.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numPartitions</span> <span class="o">=</span> <span class="n">numPartitions</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.setNumIterations"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setNumIterations">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setNumIterations</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numIterations</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets number of iterations (default: 1), which should be smaller</span> |
| <span class="sd"> than or equal to number of partitions.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span> <span class="o">=</span> <span class="n">numIterations</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.setSeed"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setSeed">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.2.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setSeed</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">seed</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets random seed.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="o">=</span> <span class="n">seed</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.setMinCount"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setMinCount">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.4.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setMinCount</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">minCount</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets minCount, the minimum number of times a token must appear</span> |
| <span class="sd"> to be included in the word2vec model's vocabulary (default: 5).</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">minCount</span> <span class="o">=</span> <span class="n">minCount</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.setWindowSize"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.setWindowSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'2.0.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWindowSize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">windowSize</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets window size (default: 5).</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">windowSize</span> <span class="o">=</span> <span class="n">windowSize</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="Word2Vec.fit"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.Word2Vec.html#pyspark.mllib.feature.Word2Vec.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Computes the vector representation of each word in vocabulary.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> training data. RDD of list of string</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`Word2VecModel`</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"data should be an RDD of list of string"</span><span class="p">)</span> |
| <span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"trainWord2VecModel"</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">vectorSize</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">learningRate</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numPartitions</span><span class="p">),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">minCount</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">windowSize</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">Word2VecModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ElementwiseProduct"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ElementwiseProduct.html#pyspark.mllib.feature.ElementwiseProduct">[docs]</a><span class="k">class</span> <span class="nc">ElementwiseProduct</span><span class="p">(</span><span class="n">VectorTransformer</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Scales each column of the vector, with the supplied weight vector.</span> |
| <span class="sd"> i.e the elementwise product.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> weight = Vectors.dense([1.0, 2.0, 3.0])</span> |
| <span class="sd"> >>> eprod = ElementwiseProduct(weight)</span> |
| <span class="sd"> >>> a = Vectors.dense([2.0, 1.0, 3.0])</span> |
| <span class="sd"> >>> eprod.transform(a)</span> |
| <span class="sd"> DenseVector([2.0, 2.0, 9.0])</span> |
| <span class="sd"> >>> b = Vectors.dense([9.0, 3.0, 4.0])</span> |
| <span class="sd"> >>> rdd = sc.parallelize([a, b])</span> |
| <span class="sd"> >>> eprod.transform(rdd).collect()</span> |
| <span class="sd"> [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])]</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scalingVector</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">scalingVector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">scalingVector</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ElementwiseProduct.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.feature.ElementwiseProduct.html#pyspark.mllib.feature.ElementwiseProduct.transform">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s1">'1.5.0'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Computes the Hadamard product of the vector.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="n">vector</span> <span class="o">=</span> <span class="n">vector</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">)</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">vector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"elementwiseProductVector"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">scalingVector</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span></div></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">():</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="n">globs</span> <span class="o">=</span> <span class="nb">globals</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span>\ |
| <span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">)</span>\ |
| <span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"mllib.feature tests"</span><span class="p">)</span>\ |
| <span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s1">'sc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span> |
| <span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| |
| </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> |
