| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.classification — PySpark 3.3.1 documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="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.classification</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="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">exp</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">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Union</span><span class="p">,</span> <span class="n">overload</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">RDD</span><span class="p">,</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.streaming.dstream</span> <span class="kn">import</span> <span class="n">DStream</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">_py2java</span><span class="p">,</span> <span class="n">_java2py</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">_convert_to_vector</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">LabeledPoint</span><span class="p">,</span> |
| <span class="n">LinearModel</span><span class="p">,</span> |
| <span class="n">_regression_train_wrapper</span><span class="p">,</span> |
| <span class="n">StreamingLinearAlgorithm</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">Saveable</span><span class="p">,</span> <span class="n">Loader</span><span class="p">,</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vector</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span> |
| |
| <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib._typing</span> <span class="kn">import</span> <span class="n">VectorLike</span> |
| |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s2">"LogisticRegressionModel"</span><span class="p">,</span> |
| <span class="s2">"LogisticRegressionWithSGD"</span><span class="p">,</span> |
| <span class="s2">"LogisticRegressionWithLBFGS"</span><span class="p">,</span> |
| <span class="s2">"SVMModel"</span><span class="p">,</span> |
| <span class="s2">"SVMWithSGD"</span><span class="p">,</span> |
| <span class="s2">"NaiveBayesModel"</span><span class="p">,</span> |
| <span class="s2">"NaiveBayes"</span><span class="p">,</span> |
| <span class="s2">"StreamingLogisticRegressionWithSGD"</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">LinearClassificationModel</span><span class="p">(</span><span class="n">LinearModel</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> A private abstract class representing a multiclass classification</span> |
| <span class="sd"> model. The categories are represented by int values: 0, 1, 2, etc.</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">weights</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">intercept</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">LinearClassificationModel</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setThreshold</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="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the threshold that separates positive predictions from</span> |
| <span class="sd"> negative predictions. An example with prediction score greater</span> |
| <span class="sd"> than or equal to this threshold is identified as a positive,</span> |
| <span class="sd"> and negative otherwise. It is used for binary classification</span> |
| <span class="sd"> only.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="n">value</span> |
| |
| <span class="nd">@property</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">threshold</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns the threshold (if any) used for converting raw</span> |
| <span class="sd"> prediction scores into 0/1 predictions. It is used for</span> |
| <span class="sd"> binary classification only.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> |
| |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">clearThreshold</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Clears the threshold so that `predict` will output raw</span> |
| <span class="sd"> prediction scores. It is used for binary classification only.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">test</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">test</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="o">...</span> |
| |
| <span class="k">def</span> <span class="nf">predict</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">test</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">RDD</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]],</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Predict values for a single data point or an RDD of points</span> |
| <span class="sd"> using the model trained.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span> |
| |
| |
| <div class="viewcode-block" id="LogisticRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionModel.html#pyspark.mllib.classification.LogisticRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionModel</span><span class="p">(</span><span class="n">LinearClassificationModel</span><span class="p">):</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd"> Classification model trained using Multinomial/Binary Logistic</span> |
| <span class="sd"> Regression.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weights : :py:class:`pyspark.mllib.linalg.Vector`</span> |
| <span class="sd"> Weights computed for every feature.</span> |
| <span class="sd"> intercept : float</span> |
| <span class="sd"> Intercept computed for this model. (Only used in Binary Logistic</span> |
| <span class="sd"> Regression. In Multinomial Logistic Regression, the intercepts will</span> |
| <span class="sd"> not be a single value, so the intercepts will be part of the</span> |
| <span class="sd"> weights.)</span> |
| <span class="sd"> numFeatures : int</span> |
| <span class="sd"> The dimension of the features.</span> |
| <span class="sd"> numClasses : int</span> |
| <span class="sd"> The number of possible outcomes for k classes classification problem</span> |
| <span class="sd"> in Multinomial Logistic Regression. By default, it is binary</span> |
| <span class="sd"> logistic regression so numClasses will be set to 2.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0]),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LogisticRegressionWithSGD.train(sc.parallelize(data), iterations=10)</span> |
| <span class="sd"> >>> lrm.predict([1.0, 0.0])</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> lrm.predict([0.0, 1.0])</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> lrm.predict(sc.parallelize([[1.0, 0.0], [0.0, 1.0]])).collect()</span> |
| <span class="sd"> [1, 0]</span> |
| <span class="sd"> >>> lrm.clearThreshold()</span> |
| <span class="sd"> >>> lrm.predict([0.0, 1.0])</span> |
| <span class="sd"> 0.279...</span> |
| |
| <span class="sd"> >>> sparse_data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LogisticRegressionWithSGD.train(sc.parallelize(sparse_data), iterations=10)</span> |
| <span class="sd"> >>> lrm.predict(numpy.array([0.0, 1.0]))</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> lrm.predict(numpy.array([1.0, 0.0]))</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> lrm.predict(SparseVector(2, {1: 1.0}))</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> lrm.predict(SparseVector(2, {0: 1.0}))</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> lrm.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = LogisticRegressionModel.load(sc, path)</span> |
| <span class="sd"> >>> sameModel.predict(numpy.array([0.0, 1.0]))</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> sameModel.predict(SparseVector(2, {0: 1.0}))</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except BaseException:</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> >>> multi_class_data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0, 0.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0, 0.0]),</span> |
| <span class="sd"> ... LabeledPoint(2.0, [0.0, 0.0, 1.0])</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> data = sc.parallelize(multi_class_data)</span> |
| <span class="sd"> >>> mcm = LogisticRegressionWithLBFGS.train(data, iterations=10, numClasses=3)</span> |
| <span class="sd"> >>> mcm.predict([0.0, 0.5, 0.0])</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> mcm.predict([0.8, 0.0, 0.0])</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> mcm.predict([0.0, 0.0, 0.3])</span> |
| <span class="sd"> 2</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">weights</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">intercept</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">numFeatures</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">numClasses</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">LogisticRegressionModel</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</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="nb">int</span><span class="p">(</span><span class="n">numFeatures</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">numClasses</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="mf">0.5</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="o">.</span><span class="n">size</span> <span class="o">//</span> <span class="p">(</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span> |
| <span class="p">)</span> |
| |
| <span class="nd">@property</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">numFeatures</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Dimension of the features.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numFeatures</span> |
| |
| <span class="nd">@property</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">numClasses</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Number of possible outcomes for k classes classification problem</span> |
| <span class="sd"> in Multinomial Logistic Regression.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</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="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</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="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="LogisticRegressionModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionModel.html#pyspark.mllib.classification.LogisticRegressionModel.predict">[docs]</a> <span class="k">def</span> <span class="nf">predict</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="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">RDD</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]],</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Predict values for a single data point or an RDD of points</span> |
| <span class="sd"> using the model trained.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> |
| |
| <span class="n">x</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">numClasses</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="n">margin</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_intercept</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">prob</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="n">margin</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">exp_margin</span> <span class="o">=</span> <span class="n">exp</span><span class="p">(</span><span class="n">margin</span><span class="p">)</span> |
| <span class="n">prob</span> <span class="o">=</span> <span class="n">exp_margin</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">exp_margin</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">prob</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">prob</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="k">else</span> <span class="mi">0</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">best_class</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">max_margin</span> <span class="o">=</span> <span class="mf">0.0</span> |
| <span class="k">if</span> <span class="n">x</span><span class="o">.</span><span class="n">size</span> <span class="o">+</span> <span class="mi">1</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span><span class="p">:</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="n">margin</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">x</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</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="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">])</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">]</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="n">max_margin</span><span class="p">:</span> |
| <span class="n">max_margin</span> <span class="o">=</span> <span class="n">margin</span> |
| <span class="n">best_class</span> <span class="o">=</span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="n">margin</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="n">max_margin</span><span class="p">:</span> |
| <span class="n">max_margin</span> <span class="o">=</span> <span class="n">margin</span> |
| <span class="n">best_class</span> <span class="o">=</span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">best_class</span></div> |
| |
| <div class="viewcode-block" id="LogisticRegressionModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionModel.html#pyspark.mllib.classification.LogisticRegressionModel.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Save this model to the given path.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_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">classification</span><span class="o">.</span><span class="n">LogisticRegressionModel</span><span class="p">(</span> |
| <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</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="bp">self</span><span class="o">.</span><span class="n">numClasses</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</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></div> |
| |
| <div class="viewcode-block" id="LogisticRegressionModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionModel.html#pyspark.mllib.classification.LogisticRegressionModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</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">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"LogisticRegressionModel"</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="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_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">classification</span><span class="o">.</span><span class="n">LogisticRegressionModel</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">weights</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">weights</span><span class="p">())</span> |
| <span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span> |
| <span class="n">numFeatures</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">numFeatures</span><span class="p">()</span> |
| <span class="n">numClasses</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">numClasses</span><span class="p">()</span> |
| <span class="n">threshold</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">getThreshold</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">()</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">LogisticRegressionModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">,</span> <span class="n">numFeatures</span><span class="p">,</span> <span class="n">numClasses</span><span class="p">)</span> |
| <span class="n">model</span><span class="o">.</span><span class="n">setThreshold</span><span class="p">(</span><span class="n">threshold</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">model</span></div> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="s2">"pyspark.mllib.LogisticRegressionModel: intercept = </span><span class="si">{}</span><span class="s2">, "</span> |
| <span class="s2">"numFeatures = </span><span class="si">{}</span><span class="s2">, numClasses = </span><span class="si">{}</span><span class="s2">, threshold = </span><span class="si">{}</span><span class="s2">"</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_intercept</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="bp">self</span><span class="o">.</span><span class="n">_numClasses</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="LogisticRegressionWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionWithSGD.html#pyspark.mllib.classification.LogisticRegressionWithSGD">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionWithSGD</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a classification model for Binary Logistic Regression using Stochastic Gradient Descent.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> .. deprecated:: 2.0.0</span> |
| <span class="sd"> Use ml.classification.LogisticRegression or LogisticRegressionWithLBFGS.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LogisticRegressionWithSGD.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionWithSGD.html#pyspark.mllib.classification.LogisticRegressionWithSGD.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</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="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">iterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span> |
| <span class="n">step</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">initialWeights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">,</span> |
| <span class="n">regType</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"l2"</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">validateData</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">LogisticRegressionModel</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a logistic regression model on the given data.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The training data, an RDD of :py:class:`pyspark.mllib.regression.LabeledPoint`.</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> The number of iterations.</span> |
| <span class="sd"> (default: 100)</span> |
| <span class="sd"> step : float, optional</span> |
| <span class="sd"> The step parameter used in SGD.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of data to be used for each SGD iteration.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> initialWeights : :py:class:`pyspark.mllib.linalg.Vector` or convertible, optional</span> |
| <span class="sd"> The initial weights.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> The regularizer parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> regType : str, optional</span> |
| <span class="sd"> The type of regularizer used for training our model.</span> |
| <span class="sd"> Supported values:</span> |
| |
| <span class="sd"> - "l1" for using L1 regularization</span> |
| <span class="sd"> - "l2" for using L2 regularization (default)</span> |
| <span class="sd"> - None for no regularization</span> |
| |
| <span class="sd"> intercept : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates the use or not of the</span> |
| <span class="sd"> augmented representation for training data (i.e., whether bias</span> |
| <span class="sd"> features are activated or not).</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> validateData : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates if the algorithm should</span> |
| <span class="sd"> validate data before training.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> A condition which decides iteration termination.</span> |
| <span class="sd"> (default: 0.001)</span> |
| <span class="sd"> """</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span> |
| <span class="s2">"Deprecated in 2.0.0. Use ml.classification.LogisticRegression or "</span> |
| <span class="s2">"LogisticRegressionWithLBFGS."</span><span class="p">,</span> |
| <span class="ne">FutureWarning</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">i</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainLogisticRegressionModelWithSGD"</span><span class="p">,</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> |
| <span class="n">regType</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">convergenceTol</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">LogisticRegressionModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="LogisticRegressionWithLBFGS"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionWithLBFGS.html#pyspark.mllib.classification.LogisticRegressionWithLBFGS">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionWithLBFGS</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a classification model for Multinomial/Binary Logistic Regression</span> |
| <span class="sd"> using Limited-memory BFGS.</span> |
| |
| <span class="sd"> Standard feature scaling and L2 regularization are used by default.</span> |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LogisticRegressionWithLBFGS.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.LogisticRegressionWithLBFGS.html#pyspark.mllib.classification.LogisticRegressionWithLBFGS.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</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="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">iterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span> |
| <span class="n">initialWeights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span> |
| <span class="n">regType</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"l2"</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">corrections</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span> |
| <span class="n">tolerance</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span> |
| <span class="n">validateData</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">numClasses</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">LogisticRegressionModel</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a logistic regression model on the given data.</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"> The training data, an RDD of :py:class:`pyspark.mllib.regression.LabeledPoint`.</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> The number of iterations.</span> |
| <span class="sd"> (default: 100)</span> |
| <span class="sd"> initialWeights : :py:class:`pyspark.mllib.linalg.Vector` or convertible, optional</span> |
| <span class="sd"> The initial weights.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> The regularizer parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> regType : str, optional</span> |
| <span class="sd"> The type of regularizer used for training our model.</span> |
| <span class="sd"> Supported values:</span> |
| |
| <span class="sd"> - "l1" for using L1 regularization</span> |
| <span class="sd"> - "l2" for using L2 regularization (default)</span> |
| <span class="sd"> - None for no regularization</span> |
| |
| <span class="sd"> intercept : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates the use or not of the</span> |
| <span class="sd"> augmented representation for training data (i.e., whether bias</span> |
| <span class="sd"> features are activated or not).</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> corrections : int, optional</span> |
| <span class="sd"> The number of corrections used in the LBFGS update.</span> |
| <span class="sd"> If a known updater is used for binary classification,</span> |
| <span class="sd"> it calls the ml implementation and this parameter will</span> |
| <span class="sd"> have no effect. (default: 10)</span> |
| <span class="sd"> tolerance : float, optional</span> |
| <span class="sd"> The convergence tolerance of iterations for L-BFGS.</span> |
| <span class="sd"> (default: 1e-6)</span> |
| <span class="sd"> validateData : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates if the algorithm should</span> |
| <span class="sd"> validate data before training.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> numClasses : int, optional</span> |
| <span class="sd"> The number of classes (i.e., outcomes) a label can take in</span> |
| <span class="sd"> Multinomial Logistic Regression.</span> |
| <span class="sd"> (default: 2)</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0]),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LogisticRegressionWithLBFGS.train(sc.parallelize(data), iterations=10)</span> |
| <span class="sd"> >>> lrm.predict([1.0, 0.0])</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> lrm.predict([0.0, 1.0])</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">i</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainLogisticRegressionModelWithLBFGS"</span><span class="p">,</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> |
| <span class="n">regType</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">corrections</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">tolerance</span><span class="p">),</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">numClasses</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">initialWeights</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">numClasses</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="n">initialWeights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">intercept</span><span class="p">:</span> |
| <span class="n">initialWeights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="n">numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">initialWeights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="n">numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">LogisticRegressionModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="SVMModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.SVMModel.html#pyspark.mllib.classification.SVMModel">[docs]</a><span class="k">class</span> <span class="nc">SVMModel</span><span class="p">(</span><span class="n">LinearClassificationModel</span><span class="p">):</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd"> Model for Support Vector Machines (SVMs).</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weights : :py:class:`pyspark.mllib.linalg.Vector`</span> |
| <span class="sd"> Weights computed for every feature.</span> |
| <span class="sd"> intercept : float</span> |
| <span class="sd"> Intercept computed for this model.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [2.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [3.0])</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> svm = SVMWithSGD.train(sc.parallelize(data), iterations=10)</span> |
| <span class="sd"> >>> svm.predict([1.0])</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> svm.predict(sc.parallelize([[1.0]])).collect()</span> |
| <span class="sd"> [1]</span> |
| <span class="sd"> >>> svm.clearThreshold()</span> |
| <span class="sd"> >>> svm.predict(numpy.array([1.0]))</span> |
| <span class="sd"> 1.44...</span> |
| |
| <span class="sd"> >>> sparse_data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: -1.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> svm = SVMWithSGD.train(sc.parallelize(sparse_data), iterations=10)</span> |
| <span class="sd"> >>> svm.predict(SparseVector(2, {1: 1.0}))</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> svm.predict(SparseVector(2, {0: -1.0}))</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> svm.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = SVMModel.load(sc, path)</span> |
| <span class="sd"> >>> sameModel.predict(SparseVector(2, {1: 1.0}))</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> >>> sameModel.predict(SparseVector(2, {0: -1.0}))</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except BaseException:</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="n">weights</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">intercept</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SVMModel</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="mf">0.0</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</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="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</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="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="SVMModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.SVMModel.html#pyspark.mllib.classification.SVMModel.predict">[docs]</a> <span class="k">def</span> <span class="nf">predict</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="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">RDD</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]],</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Predict values for a single data point or an RDD of points</span> |
| <span class="sd"> using the model trained.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> |
| |
| <span class="n">x</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="n">margin</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">margin</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="k">else</span> <span class="mi">0</span></div> |
| |
| <div class="viewcode-block" id="SVMModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.SVMModel.html#pyspark.mllib.classification.SVMModel.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Save this model to the given path.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_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">classification</span><span class="o">.</span><span class="n">SVMModel</span><span class="p">(</span> |
| <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</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></div> |
| |
| <div class="viewcode-block" id="SVMModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.SVMModel.html#pyspark.mllib.classification.SVMModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</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">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"SVMModel"</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="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_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">classification</span><span class="o">.</span><span class="n">SVMModel</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">weights</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">weights</span><span class="p">())</span> |
| <span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span> |
| <span class="n">threshold</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">getThreshold</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">()</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">SVMModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> |
| <span class="n">model</span><span class="o">.</span><span class="n">setThreshold</span><span class="p">(</span><span class="n">threshold</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">model</span></div></div> |
| |
| |
| <div class="viewcode-block" id="SVMWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.SVMWithSGD.html#pyspark.mllib.classification.SVMWithSGD">[docs]</a><span class="k">class</span> <span class="nc">SVMWithSGD</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a Support Vector Machine (SVM) using Stochastic Gradient Descent.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="SVMWithSGD.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.SVMWithSGD.html#pyspark.mllib.classification.SVMWithSGD.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</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="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">iterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span> |
| <span class="n">step</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">initialWeights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">regType</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"l2"</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">validateData</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">SVMModel</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a support vector machine on the given data.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The training data, an RDD of :py:class:`pyspark.mllib.regression.LabeledPoint`.</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> The number of iterations.</span> |
| <span class="sd"> (default: 100)</span> |
| <span class="sd"> step : float, optional</span> |
| <span class="sd"> The step parameter used in SGD.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> The regularizer parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of data to be used for each SGD iteration.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> initialWeights : :py:class:`pyspark.mllib.linalg.Vector` or convertible, optional</span> |
| <span class="sd"> The initial weights.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> regType : str, optional</span> |
| <span class="sd"> The type of regularizer used for training our model.</span> |
| <span class="sd"> Allowed values:</span> |
| |
| <span class="sd"> - "l1" for using L1 regularization</span> |
| <span class="sd"> - "l2" for using L2 regularization (default)</span> |
| <span class="sd"> - None for no regularization</span> |
| |
| <span class="sd"> intercept : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates the use or not of the</span> |
| <span class="sd"> augmented representation for training data (i.e. whether bias</span> |
| <span class="sd"> features are activated or not).</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> validateData : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates if the algorithm should</span> |
| <span class="sd"> validate data before training.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> A condition which decides iteration termination.</span> |
| <span class="sd"> (default: 0.001)</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">i</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainSVMModelWithSGD"</span><span class="p">,</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="n">regType</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">convergenceTol</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">SVMModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="NaiveBayesModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.NaiveBayesModel.html#pyspark.mllib.classification.NaiveBayesModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">NaiveBayesModel</span><span class="p">(</span><span class="n">Saveable</span><span class="p">,</span> <span class="n">Loader</span><span class="p">[</span><span class="s2">"NaiveBayesModel"</span><span class="p">]):</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd"> Model for Naive Bayes classifiers.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> labels : :py:class:`numpy.ndarray`</span> |
| <span class="sd"> List of labels.</span> |
| <span class="sd"> pi : :py:class:`numpy.ndarray`</span> |
| <span class="sd"> Log of class priors, whose dimension is C, number of labels.</span> |
| <span class="sd"> theta : :py:class:`numpy.ndarray`</span> |
| <span class="sd"> Log of class conditional probabilities, whose dimension is C-by-D,</span> |
| <span class="sd"> where D is number of features.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0, 0.0]),</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0]),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> model = NaiveBayes.train(sc.parallelize(data))</span> |
| <span class="sd"> >>> model.predict(numpy.array([0.0, 1.0]))</span> |
| <span class="sd"> 0.0</span> |
| <span class="sd"> >>> model.predict(numpy.array([1.0, 0.0]))</span> |
| <span class="sd"> 1.0</span> |
| <span class="sd"> >>> model.predict(sc.parallelize([[1.0, 0.0]])).collect()</span> |
| <span class="sd"> [1.0]</span> |
| <span class="sd"> >>> sparse_data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {1: 0.0})),</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {1: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {0: 1.0}))</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> model = NaiveBayes.train(sc.parallelize(sparse_data))</span> |
| <span class="sd"> >>> model.predict(SparseVector(2, {1: 1.0}))</span> |
| <span class="sd"> 0.0</span> |
| <span class="sd"> >>> model.predict(SparseVector(2, {0: 1.0}))</span> |
| <span class="sd"> 1.0</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 = NaiveBayesModel.load(sc, path)</span> |
| <span class="sd"> >>> sameModel.predict(SparseVector(2, {0: 1.0})) == model.predict(SparseVector(2, {0: 1.0}))</span> |
| <span class="sd"> True</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="n">labels</span><span class="p">:</span> <span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">pi</span><span class="p">:</span> <span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">theta</span><span class="p">:</span> <span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">labels</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">pi</span> <span class="o">=</span> <span class="n">pi</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">theta</span> <span class="o">=</span> <span class="n">theta</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</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="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="n">numpy</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">predict</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="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">float64</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="NaiveBayesModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.NaiveBayesModel.html#pyspark.mllib.classification.NaiveBayesModel.predict">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"0.9.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">predict</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="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">float64</span><span class="p">]]:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Return the most likely class for a data vector</span> |
| <span class="sd"> or an RDD of vectors</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">labels</span><span class="p">[</span> |
| <span class="n">numpy</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pi</span> <span class="o">+</span> <span class="n">x</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">theta</span><span class="o">.</span><span class="n">transpose</span><span class="p">()))</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="NaiveBayesModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.NaiveBayesModel.html#pyspark.mllib.classification.NaiveBayesModel.save">[docs]</a> <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Save this model to the given path.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_labels</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">labels</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span> |
| <span class="n">java_pi</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">pi</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span> |
| <span class="n">java_theta</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">theta</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span> |
| <span class="n">java_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">classification</span><span class="o">.</span><span class="n">NaiveBayesModel</span><span class="p">(</span> |
| <span class="n">java_labels</span><span class="p">,</span> <span class="n">java_pi</span><span class="p">,</span> <span class="n">java_theta</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</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></div> |
| |
| <div class="viewcode-block" id="NaiveBayesModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.NaiveBayesModel.html#pyspark.mllib.classification.NaiveBayesModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</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">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"NaiveBayesModel"</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="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_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">classification</span><span class="o">.</span><span class="n">NaiveBayesModel</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="c1"># Can not unpickle array.array from Pickle in Python3 with "bytes"</span> |
| <span class="n">py_labels</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">labels</span><span class="p">(),</span> <span class="s2">"latin1"</span><span class="p">)</span> |
| <span class="n">py_pi</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">pi</span><span class="p">(),</span> <span class="s2">"latin1"</span><span class="p">)</span> |
| <span class="n">py_theta</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">theta</span><span class="p">(),</span> <span class="s2">"latin1"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">NaiveBayesModel</span><span class="p">(</span><span class="n">py_labels</span><span class="p">,</span> <span class="n">py_pi</span><span class="p">,</span> <span class="n">numpy</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">py_theta</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="NaiveBayes"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.NaiveBayes.html#pyspark.mllib.classification.NaiveBayes">[docs]</a><span class="k">class</span> <span class="nc">NaiveBayes</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a Multinomial Naive Bayes model.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="NaiveBayes.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.NaiveBayes.html#pyspark.mllib.classification.NaiveBayes.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="bp">cls</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="n">LabeledPoint</span><span class="p">],</span> <span class="n">lambda_</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">)</span> <span class="o">-></span> <span class="n">NaiveBayesModel</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train a Naive Bayes model given an RDD of (label, features)</span> |
| <span class="sd"> vectors.</span> |
| |
| <span class="sd"> This is the `Multinomial NB <http://tinyurl.com/lsdw6p>`_ which</span> |
| <span class="sd"> can handle all kinds of discrete data. For example, by</span> |
| <span class="sd"> converting documents into TF-IDF vectors, it can be used for</span> |
| <span class="sd"> document classification. By making every vector a 0-1 vector,</span> |
| <span class="sd"> it can also be used as `Bernoulli NB <http://tinyurl.com/p7c96j6>`_.</span> |
| <span class="sd"> The input feature values must be nonnegative.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The training data, an RDD of :py:class:`pyspark.mllib.regression.LabeledPoint`.</span> |
| <span class="sd"> lambda\\_ : float, optional</span> |
| <span class="sd"> The smoothing parameter.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> """</span> |
| <span class="n">first</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">first</span><span class="p">,</span> <span class="n">LabeledPoint</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"`data` should be an RDD of LabeledPoint"</span><span class="p">)</span> |
| <span class="n">labels</span><span class="p">,</span> <span class="n">pi</span><span class="p">,</span> <span class="n">theta</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"trainNaiveBayesModel"</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">lambda_</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">NaiveBayesModel</span><span class="p">(</span><span class="n">labels</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">pi</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">numpy</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">theta</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="StreamingLogisticRegressionWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.html#pyspark.mllib.classification.StreamingLogisticRegressionWithSGD">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">StreamingLogisticRegressionWithSGD</span><span class="p">(</span><span class="n">StreamingLinearAlgorithm</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Train or predict a logistic regression model on streaming data.</span> |
| <span class="sd"> Training uses Stochastic Gradient Descent to update the model based on</span> |
| <span class="sd"> each new batch of incoming data from a DStream.</span> |
| |
| <span class="sd"> Each batch of data is assumed to be an RDD of LabeledPoints.</span> |
| <span class="sd"> The number of data points per batch can vary, but the number</span> |
| <span class="sd"> of features must be constant. An initial weight</span> |
| <span class="sd"> vector must be provided.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> stepSize : float, optional</span> |
| <span class="sd"> Step size for each iteration of gradient descent.</span> |
| <span class="sd"> (default: 0.1)</span> |
| <span class="sd"> numIterations : int, optional</span> |
| <span class="sd"> Number of iterations run for each batch of data.</span> |
| <span class="sd"> (default: 50)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of each batch of data to use for updates.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> L2 Regularization parameter.</span> |
| <span class="sd"> (default: 0.0)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> Value used to determine when to terminate iterations.</span> |
| <span class="sd"> (default: 0.001)</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">stepSize</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span> |
| <span class="n">numIterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">50</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span> <span class="o">=</span> <span class="n">stepSize</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="bp">self</span><span class="o">.</span><span class="n">regParam</span> <span class="o">=</span> <span class="n">regParam</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</span> <span class="o">=</span> <span class="n">miniBatchFraction</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">convergenceTol</span> <span class="o">=</span> <span class="n">convergenceTol</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">LogisticRegressionModel</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">StreamingLogisticRegressionWithSGD</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="StreamingLogisticRegressionWithSGD.setInitialWeights"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.html#pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.setInitialWeights">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.5.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setInitialWeights</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">:</span> <span class="s2">"VectorLike"</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"StreamingLogisticRegressionWithSGD"</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Set the initial value of weights.</span> |
| |
| <span class="sd"> This must be set before running trainOn and predictOn.</span> |
| <span class="sd"> """</span> |
| <span class="n">initialWeights</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">initialWeights</span><span class="p">)</span> |
| |
| <span class="c1"># LogisticRegressionWithSGD does only binary classification.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">LogisticRegressionModel</span><span class="p">(</span> |
| <span class="n">initialWeights</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">initialWeights</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="mi">2</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="StreamingLogisticRegressionWithSGD.trainOn"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.html#pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.trainOn">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.5.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">trainOn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">:</span> <span class="s2">"DStream[LabeledPoint]"</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""Train the model on the incoming dstream."""</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">update</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">])</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="c1"># LogisticRegressionWithSGD.train raises an error for an empty RDD.</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">rdd</span><span class="o">.</span><span class="n">isEmpty</span><span class="p">():</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">LogisticRegressionWithSGD</span><span class="o">.</span><span class="n">train</span><span class="p">(</span> |
| <span class="n">rdd</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">stepSize</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">weights</span><span class="p">,</span> <span class="c1"># type: ignore[union-attr]</span> |
| <span class="n">regParam</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">regParam</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">convergenceTol</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="n">dstream</span><span class="o">.</span><span class="n">foreachRDD</span><span class="p">(</span><span class="n">update</span><span class="p">)</span></div></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</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="kn">import</span> <span class="nn">pyspark.mllib.classification</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">classification</span><span class="o">.</span><span class="vm">__dict__</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="p">(</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.classification tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="p">)</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"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">_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> |
