| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.util — PySpark 3.5.0 documentation</title> |
| |
| <link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| |
| |
| <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/styles/pydata-sphinx-theme.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/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/mllib/util.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="None"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl"> |
| |
| <div id="navbar-start"> |
| |
| |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo"> |
| </a> |
| |
| |
| |
| </div> |
| |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| |
| <div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse"> |
| <div id="navbar-center" class="mr-auto"> |
| |
| <div class="navbar-center-item"> |
| <ul id="navbar-main-elements" class="navbar-nav"> |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| |
| </ul> |
| </div> |
| |
| </div> |
| |
| <div id="navbar-end"> |
| |
| <div class="navbar-end-item"> |
| <ul id="navbar-icon-links" class="navbar-nav" aria-label="Icon Links"> |
| </ul> |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"><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"> |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| </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.util</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">import</span> <span class="nn">sys</span> |
| <span class="kn">from</span> <span class="nn">functools</span> <span class="kn">import</span> <span class="n">reduce</span> |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">since</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">inherit_doc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">,</span> <span class="n">_convert_to_vector</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Generic</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Type</span><span class="p">,</span> <span class="n">TypeVar</span><span class="p">,</span> <span class="n">cast</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span> |
| <span class="kn">from</span> <span class="nn">pyspark.context</span> <span class="kn">import</span> <span class="n">SparkContext</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.rdd</span> <span class="kn">import</span> <span class="n">RDD</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.dataframe</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| |
| <span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"T"</span><span class="p">)</span> |
| <span class="n">L</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"L"</span><span class="p">,</span> <span class="n">bound</span><span class="o">=</span><span class="s2">"Loader"</span><span class="p">)</span> |
| <span class="n">JL</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"JL"</span><span class="p">,</span> <span class="n">bound</span><span class="o">=</span><span class="s2">"JavaLoader"</span><span class="p">)</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="kn">from</span> <span class="nn">py4j.java_gateway</span> <span class="kn">import</span> <span class="n">JavaObject</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span> |
| |
| |
| <div class="viewcode-block" id="MLUtils"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils">[docs]</a><span class="k">class</span> <span class="nc">MLUtils</span><span class="p">:</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Helper methods to load, save and pre-process data used in MLlib.</span> |
| |
| <span class="sd"> .. versionadded:: 1.0.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_parse_libsvm_line</span><span class="p">(</span><span class="n">line</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Parses a line in LIBSVM format into (label, indices, values).</span> |
| <span class="sd"> """</span> |
| <span class="n">items</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">items</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="n">nnz</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">items</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span> |
| <span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">nnz</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">nnz</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="n">nnz</span><span class="p">):</span> |
| <span class="n">index</span><span class="p">,</span> <span class="n">value</span> <span class="o">=</span> <span class="n">items</span><span class="p">[</span><span class="mi">1</span> <span class="o">+</span> <span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">":"</span><span class="p">)</span> |
| <span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">index</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span> |
| <span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">label</span><span class="p">,</span> <span class="n">indices</span><span class="p">,</span> <span class="n">values</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_convert_labeled_point_to_libsvm</span><span class="p">(</span><span class="n">p</span><span class="p">:</span> <span class="s2">"LabeledPoint"</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Converts a LabeledPoint to a string in LIBSVM format."""</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">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="n">LabeledPoint</span><span class="p">)</span> |
| <span class="n">items</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">label</span><span class="p">)]</span> |
| <span class="n">v</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="n">nnz</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">indices</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="n">nnz</span><span class="p">):</span> |
| <span class="n">items</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="s2">":"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]))</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="nb">len</span><span class="p">(</span><span class="n">v</span><span class="p">)):</span> |
| <span class="n">items</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="s2">":"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="p">[</span><span class="n">i</span><span class="p">]))</span> <span class="c1"># type: ignore[index]</span> |
| <span class="k">return</span> <span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">items</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MLUtils.loadLibSVMFile"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.loadLibSVMFile">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">loadLibSVMFile</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="n">numFeatures</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">minPartitions</span><span class="p">:</span> <span class="n">Optional</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="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"LabeledPoint"</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Loads labeled data in the LIBSVM format into an RDD of</span> |
| <span class="sd"> LabeledPoint. The LIBSVM format is a text-based format used by</span> |
| <span class="sd"> LIBSVM and LIBLINEAR. Each line represents a labeled sparse</span> |
| <span class="sd"> feature vector using the following format:</span> |
| |
| <span class="sd"> label index1:value1 index2:value2 ...</span> |
| |
| <span class="sd"> where the indices are one-based and in ascending order. This</span> |
| <span class="sd"> method parses each line into a LabeledPoint, where the feature</span> |
| <span class="sd"> indices are converted to zero-based.</span> |
| |
| <span class="sd"> .. versionadded:: 1.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> Spark context</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> file or directory path in any Hadoop-supported file system URI</span> |
| <span class="sd"> numFeatures : int, optional</span> |
| <span class="sd"> number of features, which will be determined</span> |
| <span class="sd"> from the input data if a nonpositive value</span> |
| <span class="sd"> is given. This is useful when the dataset is</span> |
| <span class="sd"> already split into multiple files and you</span> |
| <span class="sd"> want to load them separately, because some</span> |
| <span class="sd"> features may not present in certain files,</span> |
| <span class="sd"> which leads to inconsistent feature</span> |
| <span class="sd"> dimensions.</span> |
| <span class="sd"> minPartitions : int, optional</span> |
| <span class="sd"> min number of partitions</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> labeled data stored as an RDD of LabeledPoint</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from tempfile import NamedTemporaryFile</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> tempFile = NamedTemporaryFile(delete=True)</span> |
| <span class="sd"> >>> _ = tempFile.write(b"+1 1:1.0 3:2.0 5:3.0\\n-1\\n-1 2:4.0 4:5.0 6:6.0")</span> |
| <span class="sd"> >>> tempFile.flush()</span> |
| <span class="sd"> >>> examples = MLUtils.loadLibSVMFile(sc, tempFile.name).collect()</span> |
| <span class="sd"> >>> tempFile.close()</span> |
| <span class="sd"> >>> examples[0]</span> |
| <span class="sd"> LabeledPoint(1.0, (6,[0,2,4],[1.0,2.0,3.0]))</span> |
| <span class="sd"> >>> examples[1]</span> |
| <span class="sd"> LabeledPoint(-1.0, (6,[],[]))</span> |
| <span class="sd"> >>> examples[2]</span> |
| <span class="sd"> LabeledPoint(-1.0, (6,[1,3,5],[4.0,5.0,6.0]))</span> |
| <span class="sd"> """</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="n">lines</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">minPartitions</span><span class="p">)</span> |
| <span class="n">parsed</span> <span class="o">=</span> <span class="n">lines</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">l</span><span class="p">:</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">_parse_libsvm_line</span><span class="p">(</span><span class="n">l</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">numFeatures</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">parsed</span><span class="o">.</span><span class="n">cache</span><span class="p">()</span> |
| <span class="n">numFeatures</span> <span class="o">=</span> <span class="n">parsed</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="o">-</span><span class="mi">1</span> <span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">size</span> <span class="o">==</span> <span class="mi">0</span> <span class="k">else</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">][</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span><span class="o">.</span><span class="n">reduce</span><span class="p">(</span><span class="nb">max</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">parsed</span><span class="o">.</span><span class="n">map</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">LabeledPoint</span><span class="p">(</span> |
| <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">sparse</span><span class="p">(</span><span class="n">numFeatures</span><span class="p">,</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">x</span><span class="p">[</span><span class="mi">2</span><span class="p">])</span> <span class="c1"># type: ignore[arg-type]</span> |
| <span class="p">)</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.saveAsLibSVMFile"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.saveAsLibSVMFile">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">saveAsLibSVMFile</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="s2">"LabeledPoint"</span><span class="p">],</span> <span class="nb">dir</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="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Save labeled data in LIBSVM format.</span> |
| |
| <span class="sd"> .. versionadded:: 1.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of LabeledPoint to be saved</span> |
| <span class="sd"> dir : str</span> |
| <span class="sd"> directory to save the data</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from tempfile import NamedTemporaryFile</span> |
| <span class="sd"> >>> from fileinput import input</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> from glob import glob</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, 1.23), (2, 4.56)])),</span> |
| <span class="sd"> ... LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))]</span> |
| <span class="sd"> >>> tempFile = NamedTemporaryFile(delete=True)</span> |
| <span class="sd"> >>> tempFile.close()</span> |
| <span class="sd"> >>> MLUtils.saveAsLibSVMFile(sc.parallelize(examples), tempFile.name)</span> |
| <span class="sd"> >>> ''.join(sorted(input(glob(tempFile.name + "/part-0000*"))))</span> |
| <span class="sd"> '0.0 1:1.01 2:2.02 3:3.03\\n1.1 1:1.23 3:4.56\\n'</span> |
| <span class="sd"> """</span> |
| <span class="n">lines</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">p</span><span class="p">:</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">_convert_labeled_point_to_libsvm</span><span class="p">(</span><span class="n">p</span><span class="p">))</span> |
| <span class="n">lines</span><span class="o">.</span><span class="n">saveAsTextFile</span><span class="p">(</span><span class="nb">dir</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.loadLabeledPoints"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.loadLabeledPoints">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">loadLabeledPoints</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="n">minPartitions</span><span class="p">:</span> <span class="n">Optional</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="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"LabeledPoint"</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Load labeled points saved using RDD.saveAsTextFile.</span> |
| |
| <span class="sd"> .. versionadded:: 1.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> Spark context</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> file or directory path in any Hadoop-supported file system URI</span> |
| <span class="sd"> minPartitions : int, optional</span> |
| <span class="sd"> min number of partitions</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> labeled data stored as an RDD of LabeledPoint</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from tempfile import NamedTemporaryFile</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, -1.23), (2, 4.56e-7)])),</span> |
| <span class="sd"> ... LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))]</span> |
| <span class="sd"> >>> tempFile = NamedTemporaryFile(delete=True)</span> |
| <span class="sd"> >>> tempFile.close()</span> |
| <span class="sd"> >>> sc.parallelize(examples, 1).saveAsTextFile(tempFile.name)</span> |
| <span class="sd"> >>> MLUtils.loadLabeledPoints(sc, tempFile.name).collect()</span> |
| <span class="sd"> [LabeledPoint(1.1, (3,[0,2],[-1.23,4.56e-07])), LabeledPoint(0.0, [1.01,2.02,3.03])]</span> |
| <span class="sd"> """</span> |
| <span class="n">minPartitions</span> <span class="o">=</span> <span class="n">minPartitions</span> <span class="ow">or</span> <span class="nb">min</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">defaultParallelism</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"loadLabeledPoints"</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">minPartitions</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.appendBias"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.appendBias">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">appendBias</span><span class="p">(</span><span class="n">data</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Vector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a new vector with `1.0` (bias) appended to</span> |
| <span class="sd"> the end of the input vector.</span> |
| <span class="sd"> """</span> |
| <span class="n">vec</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vec</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="n">newIndices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">vec</span><span class="p">))</span> |
| <span class="n">newValues</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">vec</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">newIndices</span><span class="p">,</span> <span class="n">newValues</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="mf">1.0</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.loadVectors"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.loadVectors">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">loadVectors</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="n">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Loads vectors saved using `RDD[Vector].saveAsTextFile`</span> |
| <span class="sd"> with the default number of partitions.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"loadVectors"</span><span class="p">,</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="MLUtils.convertVectorColumnsToML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.convertVectorColumnsToML">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">convertVectorColumnsToML</span><span class="p">(</span><span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Converts vector columns in an input DataFrame from the</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector` type to the new</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.Vector` type under the `spark.ml`</span> |
| <span class="sd"> package.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset</span> |
| <span class="sd"> \\*cols : str</span> |
| <span class="sd"> Vector columns to be converted.</span> |
| |
| <span class="sd"> New vector columns will be ignored. If unspecified, all old</span> |
| <span class="sd"> vector columns will be converted excepted nested ones.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> the input dataset with old vector columns converted to the</span> |
| <span class="sd"> new vector type</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import pyspark</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> df = spark.createDataFrame(</span> |
| <span class="sd"> ... [(0, Vectors.sparse(2, [1], [1.0]), Vectors.dense(2.0, 3.0))],</span> |
| <span class="sd"> ... ["id", "x", "y"])</span> |
| <span class="sd"> >>> r1 = MLUtils.convertVectorColumnsToML(df).first()</span> |
| <span class="sd"> >>> isinstance(r1.x, pyspark.ml.linalg.SparseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r1.y, pyspark.ml.linalg.DenseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> r2 = MLUtils.convertVectorColumnsToML(df, "x").first()</span> |
| <span class="sd"> >>> isinstance(r2.x, pyspark.ml.linalg.SparseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r2.y, pyspark.mllib.linalg.DenseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Input dataset must be a DataFrame but got </span><span class="si">{}</span><span class="s2">."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">dataset</span><span class="p">)))</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"convertVectorColumnsToML"</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="n">cols</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.convertVectorColumnsFromML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.convertVectorColumnsFromML">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">convertVectorColumnsFromML</span><span class="p">(</span><span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Converts vector columns in an input DataFrame to the</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector` type from the new</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.Vector` type under the `spark.ml`</span> |
| <span class="sd"> package.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset</span> |
| <span class="sd"> \\*cols : str</span> |
| <span class="sd"> Vector columns to be converted.</span> |
| |
| <span class="sd"> Old vector columns will be ignored. If unspecified, all new</span> |
| <span class="sd"> vector columns will be converted except nested ones.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> the input dataset with new vector columns converted to the</span> |
| <span class="sd"> old vector type</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import pyspark</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import Vectors</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> df = spark.createDataFrame(</span> |
| <span class="sd"> ... [(0, Vectors.sparse(2, [1], [1.0]), Vectors.dense(2.0, 3.0))],</span> |
| <span class="sd"> ... ["id", "x", "y"])</span> |
| <span class="sd"> >>> r1 = MLUtils.convertVectorColumnsFromML(df).first()</span> |
| <span class="sd"> >>> isinstance(r1.x, pyspark.mllib.linalg.SparseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r1.y, pyspark.mllib.linalg.DenseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> r2 = MLUtils.convertVectorColumnsFromML(df, "x").first()</span> |
| <span class="sd"> >>> isinstance(r2.x, pyspark.mllib.linalg.SparseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r2.y, pyspark.ml.linalg.DenseVector)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Input dataset must be a DataFrame but got </span><span class="si">{}</span><span class="s2">."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">dataset</span><span class="p">)))</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"convertVectorColumnsFromML"</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="n">cols</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.convertMatrixColumnsToML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.convertMatrixColumnsToML">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">convertMatrixColumnsToML</span><span class="p">(</span><span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Converts matrix columns in an input DataFrame from the</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Matrix` type to the new</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.Matrix` type under the `spark.ml`</span> |
| <span class="sd"> package.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset</span> |
| <span class="sd"> \\*cols : str</span> |
| <span class="sd"> Matrix columns to be converted.</span> |
| |
| <span class="sd"> New matrix columns will be ignored. If unspecified, all old</span> |
| <span class="sd"> matrix columns will be converted excepted nested ones.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> the input dataset with old matrix columns converted to the</span> |
| <span class="sd"> new matrix type</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import pyspark</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import Matrices</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> df = spark.createDataFrame(</span> |
| <span class="sd"> ... [(0, Matrices.sparse(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4]),</span> |
| <span class="sd"> ... Matrices.dense(2, 2, range(4)))], ["id", "x", "y"])</span> |
| <span class="sd"> >>> r1 = MLUtils.convertMatrixColumnsToML(df).first()</span> |
| <span class="sd"> >>> isinstance(r1.x, pyspark.ml.linalg.SparseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r1.y, pyspark.ml.linalg.DenseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> r2 = MLUtils.convertMatrixColumnsToML(df, "x").first()</span> |
| <span class="sd"> >>> isinstance(r2.x, pyspark.ml.linalg.SparseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r2.y, pyspark.mllib.linalg.DenseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Input dataset must be a DataFrame but got </span><span class="si">{}</span><span class="s2">."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">dataset</span><span class="p">)))</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"convertMatrixColumnsToML"</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="n">cols</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MLUtils.convertMatrixColumnsFromML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.MLUtils.html#pyspark.mllib.clustering.MLUtils.convertMatrixColumnsFromML">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">convertMatrixColumnsFromML</span><span class="p">(</span><span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Converts matrix columns in an input DataFrame to the</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Matrix` type from the new</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.Matrix` type under the `spark.ml`</span> |
| <span class="sd"> package.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset</span> |
| <span class="sd"> \\*cols : str</span> |
| <span class="sd"> Matrix columns to be converted.</span> |
| |
| <span class="sd"> Old matrix columns will be ignored. If unspecified, all new</span> |
| <span class="sd"> matrix columns will be converted except nested ones.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> the input dataset with new matrix columns converted to the</span> |
| <span class="sd"> old matrix type</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import pyspark</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import Matrices</span> |
| <span class="sd"> >>> from pyspark.mllib.util import MLUtils</span> |
| <span class="sd"> >>> df = spark.createDataFrame(</span> |
| <span class="sd"> ... [(0, Matrices.sparse(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4]),</span> |
| <span class="sd"> ... Matrices.dense(2, 2, range(4)))], ["id", "x", "y"])</span> |
| <span class="sd"> >>> r1 = MLUtils.convertMatrixColumnsFromML(df).first()</span> |
| <span class="sd"> >>> isinstance(r1.x, pyspark.mllib.linalg.SparseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r1.y, pyspark.mllib.linalg.DenseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> r2 = MLUtils.convertMatrixColumnsFromML(df, "x").first()</span> |
| <span class="sd"> >>> isinstance(r2.x, pyspark.mllib.linalg.SparseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> isinstance(r2.y, pyspark.ml.linalg.DenseMatrix)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Input dataset must be a DataFrame but got </span><span class="si">{}</span><span class="s2">."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">dataset</span><span class="p">)))</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"convertMatrixColumnsFromML"</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="n">cols</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Saveable"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.Saveable.html#pyspark.mllib.clustering.Saveable">[docs]</a><span class="k">class</span> <span class="nc">Saveable</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Mixin for models and transformers which may be saved as files.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Saveable.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.Saveable.html#pyspark.mllib.clustering.Saveable.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="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Save this model to the given path.</span> |
| |
| <span class="sd"> This saves:</span> |
| <span class="sd"> * human-readable (JSON) model metadata to path/metadata/</span> |
| <span class="sd"> * Parquet formatted data to path/data/</span> |
| |
| <span class="sd"> The model may be loaded using :py:meth:`Loader.load`.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> Spark context used to save model data.</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> Path specifying the directory in which to save</span> |
| <span class="sd"> this model. If the directory already exists,</span> |
| <span class="sd"> this method throws an exception.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div></div> |
| |
| |
| <div class="viewcode-block" id="JavaSaveable"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.JavaSaveable.html#pyspark.mllib.clustering.JavaSaveable">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">JavaSaveable</span><span class="p">(</span><span class="n">Saveable</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Mixin for models that provide save() through their Scala</span> |
| <span class="sd"> implementation.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">_java_model</span><span class="p">:</span> <span class="s2">"JavaObject"</span> |
| |
| <div class="viewcode-block" id="JavaSaveable.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.JavaSaveable.html#pyspark.mllib.clustering.JavaSaveable.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.3.0"</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="w"> </span><span class="sd">"""Save this model to the given path."""</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</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="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"sc should be a SparkContext, got type </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">sc</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">path</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"path should be a string, got type </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</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> |
| |
| |
| <div class="viewcode-block" id="Loader"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.Loader.html#pyspark.mllib.clustering.Loader">[docs]</a><span class="k">class</span> <span class="nc">Loader</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">T</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Mixin for classes which can load saved models from files.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Loader.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.Loader.html#pyspark.mllib.clustering.Loader.load">[docs]</a> <span class="nd">@classmethod</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">Type</span><span class="p">[</span><span class="n">L</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="n">L</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Load a model from the given path. The model should have been</span> |
| <span class="sd"> saved using :py:meth:`Saveable.save`.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> Spark context used for loading model files.</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> Path specifying the directory to which the model was saved.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> object</span> |
| <span class="sd"> model instance</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div></div> |
| |
| |
| <div class="viewcode-block" id="JavaLoader"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.JavaLoader.html#pyspark.mllib.clustering.JavaLoader">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">JavaLoader</span><span class="p">(</span><span class="n">Loader</span><span class="p">[</span><span class="n">T</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Mixin for classes which can load saved models using its Scala</span> |
| <span class="sd"> implementation.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">_java_loader_class</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the full class name of the Java loader. The default</span> |
| <span class="sd"> implementation replaces "pyspark" by "org.apache.spark" in</span> |
| <span class="sd"> the Python full class name.</span> |
| <span class="sd"> """</span> |
| <span class="n">java_package</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__module__</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"pyspark"</span><span class="p">,</span> <span class="s2">"org.apache.spark"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="s2">"."</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">java_package</span><span class="p">,</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="p">])</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">_load_java</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">"JavaObject"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Load a Java model from the given path.</span> |
| <span class="sd"> """</span> |
| <span class="n">java_class</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_java_loader_class</span><span class="p">()</span> |
| <span class="n">java_obj</span><span class="p">:</span> <span class="s2">"JavaObject"</span> <span class="o">=</span> <span class="n">reduce</span><span class="p">(</span><span class="nb">getattr</span><span class="p">,</span> <span class="n">java_class</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">),</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">java_obj</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> |
| |
| <div class="viewcode-block" id="JavaLoader.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.JavaLoader.html#pyspark.mllib.clustering.JavaLoader.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.3.0"</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">Type</span><span class="p">[</span><span class="n">JL</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="n">JL</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Load a model from the given path."""</span> |
| <span class="n">java_model</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span> <span class="c1"># type: ignore[call-arg]</span></div></div> |
| |
| |
| <div class="viewcode-block" id="LinearDataGenerator"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.LinearDataGenerator.html#pyspark.mllib.clustering.LinearDataGenerator">[docs]</a><span class="k">class</span> <span class="nc">LinearDataGenerator</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Utils for generating linear data.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LinearDataGenerator.generateLinearInput"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.LinearDataGenerator.html#pyspark.mllib.clustering.LinearDataGenerator.generateLinearInput">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">generateLinearInput</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">weights</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">,</span> |
| <span class="n">xMean</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">,</span> |
| <span class="n">xVariance</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">,</span> |
| <span class="n">nPoints</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">seed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="s2">"LabeledPoint"</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> intercept : float</span> |
| <span class="sd"> bias factor, the term c in X'w + c</span> |
| <span class="sd"> weights : :py:class:`pyspark.mllib.linalg.Vector` or convertible</span> |
| <span class="sd"> feature vector, the term w in X'w + c</span> |
| <span class="sd"> xMean : :py:class:`pyspark.mllib.linalg.Vector` or convertible</span> |
| <span class="sd"> Point around which the data X is centered.</span> |
| <span class="sd"> xVariance : :py:class:`pyspark.mllib.linalg.Vector` or convertible</span> |
| <span class="sd"> Variance of the given data</span> |
| <span class="sd"> nPoints : int</span> |
| <span class="sd"> Number of points to be generated</span> |
| <span class="sd"> seed : int</span> |
| <span class="sd"> Random Seed</span> |
| <span class="sd"> eps : float</span> |
| <span class="sd"> Used to scale the noise. If eps is set high,</span> |
| <span class="sd"> the amount of gaussian noise added is more.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> list</span> |
| <span class="sd"> of :py:class:`pyspark.mllib.regression.LabeledPoints` of length nPoints</span> |
| <span class="sd"> """</span> |
| <span class="n">weights</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">weight</span><span class="p">)</span> <span class="k">for</span> <span class="n">weight</span> <span class="ow">in</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">weights</span><span class="p">)]</span> |
| <span class="n">xMean</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">)</span> <span class="k">for</span> <span class="n">mean</span> <span class="ow">in</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">xMean</span><span class="p">)]</span> |
| <span class="n">xVariance</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">var</span><span class="p">)</span> <span class="k">for</span> <span class="n">var</span> <span class="ow">in</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">xVariance</span><span class="p">)]</span> |
| <span class="k">return</span> <span class="nb">list</span><span class="p">(</span> |
| <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"generateLinearInputWrapper"</span><span class="p">,</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="n">weights</span><span class="p">,</span> |
| <span class="n">xMean</span><span class="p">,</span> |
| <span class="n">xVariance</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">nPoints</span><span class="p">),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">seed</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">eps</span><span class="p">),</span> |
| <span class="p">)</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="LinearDataGenerator.generateLinearRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.util.LinearDataGenerator.html#pyspark.mllib.clustering.LinearDataGenerator.generateLinearRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">generateLinearRDD</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">nexamples</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">nfeatures</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">nParts</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="n">intercept</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="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"LabeledPoint"</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generate an RDD of LabeledPoints.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"generateLinearRDDWrapper"</span><span class="p">,</span> |
| <span class="n">sc</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">nexamples</span><span class="p">),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">nfeatures</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">eps</span><span class="p">),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">nParts</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</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="n">globs</span> <span class="o">=</span> <span class="nb">globals</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="c1"># The small batch size here ensures that we see multiple batches,</span> |
| <span class="c1"># even in these small test examples:</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[2]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"mllib.util tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"spark"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</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> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <div class="footer-item"> |
| <p class="copyright"> |
| © Copyright .<br> |
| </p> |
| </div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br> |
| </p> |
| </div> |
| |
| </div> |
| </footer> |
| </body> |
| </html> |
