| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.ml.evaluation — PySpark 3.2.2 documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../user_guide/index.html">User Guide</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../reference/index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../migration_guide/index.html">Migration Guide</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.ml.evaluation</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">abc</span> <span class="kn">import</span> <span class="n">abstractmethod</span><span class="p">,</span> <span class="n">ABCMeta</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">since</span><span class="p">,</span> <span class="n">keyword_only</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="n">JavaParams</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.param</span> <span class="kn">import</span> <span class="n">Param</span><span class="p">,</span> <span class="n">Params</span><span class="p">,</span> <span class="n">TypeConverters</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.param.shared</span> <span class="kn">import</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasProbabilityCol</span><span class="p">,</span> \ |
| <span class="n">HasRawPredictionCol</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasWeightCol</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.common</span> <span class="kn">import</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.util</span> <span class="kn">import</span> <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'Evaluator'</span><span class="p">,</span> <span class="s1">'BinaryClassificationEvaluator'</span><span class="p">,</span> <span class="s1">'RegressionEvaluator'</span><span class="p">,</span> |
| <span class="s1">'MulticlassClassificationEvaluator'</span><span class="p">,</span> <span class="s1">'MultilabelClassificationEvaluator'</span><span class="p">,</span> |
| <span class="s1">'ClusteringEvaluator'</span><span class="p">,</span> <span class="s1">'RankingEvaluator'</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="Evaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.Evaluator.html#pyspark.ml.evaluation.Evaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">Evaluator</span><span class="p">(</span><span class="n">Params</span><span class="p">,</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Base class for evaluators that compute metrics from predictions.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| <span class="k">pass</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">_evaluate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluates the output.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a dataset that contains labels/observations and predictions</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> float</span> |
| <span class="sd"> metric</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="Evaluator.evaluate"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.Evaluator.html#pyspark.ml.evaluation.Evaluator.evaluate">[docs]</a> <span class="k">def</span> <span class="nf">evaluate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluates the output with optional parameters.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a dataset that contains labels/observations and predictions</span> |
| <span class="sd"> params : dict, optional</span> |
| <span class="sd"> an optional param map that overrides embedded params</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> float</span> |
| <span class="sd"> metric</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">params</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">params</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">params</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">params</span><span class="p">)</span><span class="o">.</span><span class="n">_evaluate</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_evaluate</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Params must be a param map but got </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">params</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Evaluator.isLargerBetter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.Evaluator.html#pyspark.ml.evaluation.Evaluator.isLargerBetter">[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">isLargerBetter</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Indicates whether the metric returned by :py:meth:`evaluate` should be maximized</span> |
| <span class="sd"> (True, default) or minimized (False).</span> |
| <span class="sd"> A given evaluator may support multiple metrics which may be maximized or minimized.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="kc">True</span></div></div> |
| |
| |
| <span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">JavaEvaluator</span><span class="p">(</span><span class="n">JavaParams</span><span class="p">,</span> <span class="n">Evaluator</span><span class="p">,</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Base class for :py:class:`Evaluator`s that wrap Java/Scala</span> |
| <span class="sd"> implementations.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">_evaluate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluates the output.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a dataset that contains labels/observations and predictions</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> float</span> |
| <span class="sd"> evaluation metric</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transfer_params_to_java</span><span class="p">()</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">isLargerBetter</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transfer_params_to_java</span><span class="p">()</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span><span class="o">.</span><span class="n">isLargerBetter</span><span class="p">()</span> |
| |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">BinaryClassificationEvaluator</span><span class="p">(</span><span class="n">JavaEvaluator</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasRawPredictionCol</span><span class="p">,</span> <span class="n">HasWeightCol</span><span class="p">,</span> |
| <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluator for binary classification, which expects input columns rawPrediction, label</span> |
| <span class="sd"> and an optional weight column.</span> |
| <span class="sd"> The rawPrediction column can be of type double (binary 0/1 prediction, or probability of label</span> |
| <span class="sd"> 1) or of type vector (length-2 vector of raw predictions, scores, or label probabilities).</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import Vectors</span> |
| <span class="sd"> >>> scoreAndLabels = map(lambda x: (Vectors.dense([1.0 - x[0], x[0]]), x[1]),</span> |
| <span class="sd"> ... [(0.1, 0.0), (0.1, 1.0), (0.4, 0.0), (0.6, 0.0), (0.6, 1.0), (0.6, 1.0), (0.8, 1.0)])</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabels, ["raw", "label"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = BinaryClassificationEvaluator()</span> |
| <span class="sd"> >>> evaluator.setRawPredictionCol("raw")</span> |
| <span class="sd"> BinaryClassificationEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.70...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "areaUnderPR"})</span> |
| <span class="sd"> 0.83...</span> |
| <span class="sd"> >>> bce_path = temp_path + "/bce"</span> |
| <span class="sd"> >>> evaluator.save(bce_path)</span> |
| <span class="sd"> >>> evaluator2 = BinaryClassificationEvaluator.load(bce_path)</span> |
| <span class="sd"> >>> str(evaluator2.getRawPredictionCol())</span> |
| <span class="sd"> 'raw'</span> |
| <span class="sd"> >>> scoreAndLabelsAndWeight = map(lambda x: (Vectors.dense([1.0 - x[0], x[0]]), x[1], x[2]),</span> |
| <span class="sd"> ... [(0.1, 0.0, 1.0), (0.1, 1.0, 0.9), (0.4, 0.0, 0.7), (0.6, 0.0, 0.9),</span> |
| <span class="sd"> ... (0.6, 1.0, 1.0), (0.6, 1.0, 0.3), (0.8, 1.0, 1.0)])</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabelsAndWeight, ["raw", "label", "weight"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = BinaryClassificationEvaluator(rawPredictionCol="raw", weightCol="weight")</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.70...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "areaUnderPR"})</span> |
| <span class="sd"> 0.82...</span> |
| <span class="sd"> >>> evaluator.getNumBins()</span> |
| <span class="sd"> 1000</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">metricName</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricName"</span><span class="p">,</span> |
| <span class="s2">"metric name in evaluation (areaUnderROC|areaUnderPR)"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| |
| <span class="n">numBins</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"numBins"</span><span class="p">,</span> <span class="s2">"Number of bins to down-sample the curves "</span> |
| <span class="s2">"(ROC curve, PR curve) in area computation. If 0, no down-sampling will "</span> |
| <span class="s2">"occur. Must be >= 0."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">)</span> |
| |
| <span class="nd">@keyword_only</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="o">*</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s2">"rawPrediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"areaUnderROC"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">numBins</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, rawPredictionCol="rawPrediction", labelCol="label", \</span> |
| <span class="sd"> metricName="areaUnderROC", weightCol=None, numBins=1000)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">BinaryClassificationEvaluator</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="s2">"areaUnderROC"</span><span class="p">,</span> <span class="n">numBins</span><span class="o">=</span><span class="mi">1000</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.setMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.setMetricName">[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">setMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricName`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.getMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.getMetricName">[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">getMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricName or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.setNumBins"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.setNumBins">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setNumBins</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`numBins`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">numBins</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.getNumBins"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.getNumBins">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getNumBins</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of numBins or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numBins</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.setLabelCol">[docs]</a> <span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`labelCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.setRawPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.setRawPredictionCol">[docs]</a> <span class="k">def</span> <span class="nf">setRawPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`rawPredictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">rawPredictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`weightCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BinaryClassificationEvaluator.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.BinaryClassificationEvaluator.html#pyspark.ml.evaluation.BinaryClassificationEvaluator.setParams">[docs]</a> <span class="nd">@keyword_only</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">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s2">"rawPrediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"areaUnderROC"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">numBins</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, rawPredictionCol="rawPrediction", labelCol="label", \</span> |
| <span class="sd"> metricName="areaUnderROC", weightCol=None, numBins=1000)</span> |
| <span class="sd"> Sets params for binary classification evaluator.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="RegressionEvaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">RegressionEvaluator</span><span class="p">(</span><span class="n">JavaEvaluator</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasWeightCol</span><span class="p">,</span> |
| <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluator for Regression, which expects input columns prediction, label</span> |
| <span class="sd"> and an optional weight column.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> scoreAndLabels = [(-28.98343821, -27.0), (20.21491975, 21.5),</span> |
| <span class="sd"> ... (-25.98418959, -22.0), (30.69731842, 33.0), (74.69283752, 71.0)]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabels, ["raw", "label"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = RegressionEvaluator()</span> |
| <span class="sd"> >>> evaluator.setPredictionCol("raw")</span> |
| <span class="sd"> RegressionEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 2.842...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "r2"})</span> |
| <span class="sd"> 0.993...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "mae"})</span> |
| <span class="sd"> 2.649...</span> |
| <span class="sd"> >>> re_path = temp_path + "/re"</span> |
| <span class="sd"> >>> evaluator.save(re_path)</span> |
| <span class="sd"> >>> evaluator2 = RegressionEvaluator.load(re_path)</span> |
| <span class="sd"> >>> str(evaluator2.getPredictionCol())</span> |
| <span class="sd"> 'raw'</span> |
| <span class="sd"> >>> scoreAndLabelsAndWeight = [(-28.98343821, -27.0, 1.0), (20.21491975, 21.5, 0.8),</span> |
| <span class="sd"> ... (-25.98418959, -22.0, 1.0), (30.69731842, 33.0, 0.6), (74.69283752, 71.0, 0.2)]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabelsAndWeight, ["raw", "label", "weight"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = RegressionEvaluator(predictionCol="raw", weightCol="weight")</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 2.740...</span> |
| <span class="sd"> >>> evaluator.getThroughOrigin()</span> |
| <span class="sd"> False</span> |
| <span class="sd"> """</span> |
| <span class="n">metricName</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricName"</span><span class="p">,</span> |
| <span class="sd">"""metric name in evaluation - one of:</span> |
| <span class="sd"> rmse - root mean squared error (default)</span> |
| <span class="sd"> mse - mean squared error</span> |
| <span class="sd"> r2 - r^2 metric</span> |
| <span class="sd"> mae - mean absolute error</span> |
| <span class="sd"> var - explained variance."""</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| |
| <span class="n">throughOrigin</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"throughOrigin"</span><span class="p">,</span> |
| <span class="s2">"whether the regression is through the origin."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toBoolean</span><span class="p">)</span> |
| |
| <span class="nd">@keyword_only</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="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"rmse"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">throughOrigin</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="rmse", weightCol=None, throughOrigin=False)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">RegressionEvaluator</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.evaluation.RegressionEvaluator"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="s2">"rmse"</span><span class="p">,</span> <span class="n">throughOrigin</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.setMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.setMetricName">[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">setMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricName`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.getMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.getMetricName">[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">getMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricName or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.setThroughOrigin"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.setThroughOrigin">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setThroughOrigin</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`throughOrigin`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">throughOrigin</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.getThroughOrigin"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.getThroughOrigin">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getThroughOrigin</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of throughOrigin or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">throughOrigin</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.setLabelCol">[docs]</a> <span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`labelCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.setPredictionCol">[docs]</a> <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`weightCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RegressionEvaluator.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RegressionEvaluator.html#pyspark.ml.evaluation.RegressionEvaluator.setParams">[docs]</a> <span class="nd">@keyword_only</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">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"rmse"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">throughOrigin</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="rmse", weightCol=None, throughOrigin=False)</span> |
| <span class="sd"> Sets params for regression evaluator.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">MulticlassClassificationEvaluator</span><span class="p">(</span><span class="n">JavaEvaluator</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasWeightCol</span><span class="p">,</span> |
| <span class="n">HasProbabilityCol</span><span class="p">,</span> <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluator for Multiclass Classification, which expects input</span> |
| <span class="sd"> columns: prediction, label, weight (optional) and probabilityCol (only for logLoss).</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> scoreAndLabels = [(0.0, 0.0), (0.0, 1.0), (0.0, 0.0),</span> |
| <span class="sd"> ... (1.0, 0.0), (1.0, 1.0), (1.0, 1.0), (1.0, 1.0), (2.0, 2.0), (2.0, 0.0)]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabels, ["prediction", "label"])</span> |
| <span class="sd"> >>> evaluator = MulticlassClassificationEvaluator()</span> |
| <span class="sd"> >>> evaluator.setPredictionCol("prediction")</span> |
| <span class="sd"> MulticlassClassificationEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "accuracy"})</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "truePositiveRateByLabel",</span> |
| <span class="sd"> ... evaluator.metricLabel: 1.0})</span> |
| <span class="sd"> 0.75...</span> |
| <span class="sd"> >>> evaluator.setMetricName("hammingLoss")</span> |
| <span class="sd"> MulticlassClassificationEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.33...</span> |
| <span class="sd"> >>> mce_path = temp_path + "/mce"</span> |
| <span class="sd"> >>> evaluator.save(mce_path)</span> |
| <span class="sd"> >>> evaluator2 = MulticlassClassificationEvaluator.load(mce_path)</span> |
| <span class="sd"> >>> str(evaluator2.getPredictionCol())</span> |
| <span class="sd"> 'prediction'</span> |
| <span class="sd"> >>> scoreAndLabelsAndWeight = [(0.0, 0.0, 1.0), (0.0, 1.0, 1.0), (0.0, 0.0, 1.0),</span> |
| <span class="sd"> ... (1.0, 0.0, 1.0), (1.0, 1.0, 1.0), (1.0, 1.0, 1.0), (1.0, 1.0, 1.0),</span> |
| <span class="sd"> ... (2.0, 2.0, 1.0), (2.0, 0.0, 1.0)]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabelsAndWeight, ["prediction", "label", "weight"])</span> |
| <span class="sd"> >>> evaluator = MulticlassClassificationEvaluator(predictionCol="prediction",</span> |
| <span class="sd"> ... weightCol="weight")</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "accuracy"})</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> predictionAndLabelsWithProbabilities = [</span> |
| <span class="sd"> ... (1.0, 1.0, 1.0, [0.1, 0.8, 0.1]), (0.0, 2.0, 1.0, [0.9, 0.05, 0.05]),</span> |
| <span class="sd"> ... (0.0, 0.0, 1.0, [0.8, 0.2, 0.0]), (1.0, 1.0, 1.0, [0.3, 0.65, 0.05])]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(predictionAndLabelsWithProbabilities, ["prediction",</span> |
| <span class="sd"> ... "label", "weight", "probability"])</span> |
| <span class="sd"> >>> evaluator = MulticlassClassificationEvaluator(predictionCol="prediction",</span> |
| <span class="sd"> ... probabilityCol="probability")</span> |
| <span class="sd"> >>> evaluator.setMetricName("logLoss")</span> |
| <span class="sd"> MulticlassClassificationEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.9682...</span> |
| <span class="sd"> """</span> |
| <span class="n">metricName</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricName"</span><span class="p">,</span> |
| <span class="s2">"metric name in evaluation "</span> |
| <span class="s2">"(f1|accuracy|weightedPrecision|weightedRecall|weightedTruePositiveRate| "</span> |
| <span class="s2">"weightedFalsePositiveRate|weightedFMeasure|truePositiveRateByLabel| "</span> |
| <span class="s2">"falsePositiveRateByLabel|precisionByLabel|recallByLabel|fMeasureByLabel| "</span> |
| <span class="s2">"logLoss|hammingLoss)"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">metricLabel</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricLabel"</span><span class="p">,</span> |
| <span class="s2">"The class whose metric will be computed in truePositiveRateByLabel|"</span> |
| <span class="s2">"falsePositiveRateByLabel|precisionByLabel|recallByLabel|fMeasureByLabel."</span> |
| <span class="s2">" Must be >= 0. The default value is 0."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">)</span> |
| <span class="n">beta</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"beta"</span><span class="p">,</span> |
| <span class="s2">"The beta value used in weightedFMeasure|fMeasureByLabel."</span> |
| <span class="s2">" Must be > 0. The default value is 1."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">)</span> |
| <span class="n">eps</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"eps"</span><span class="p">,</span> |
| <span class="s2">"log-loss is undefined for p=0 or p=1, so probabilities are clipped to "</span> |
| <span class="s2">"max(eps, min(1 - eps, p)). "</span> |
| <span class="s2">"Must be in range (0, 0.5). The default value is 1e-15."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">)</span> |
| |
| <span class="nd">@keyword_only</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="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"f1"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">metricLabel</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">probabilityCol</span><span class="o">=</span><span class="s2">"probability"</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-15</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="f1", weightCol=None, metricLabel=0.0, beta=1.0, \</span> |
| <span class="sd"> probabilityCol="probability", eps=1e-15)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MulticlassClassificationEvaluator</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="s2">"f1"</span><span class="p">,</span> <span class="n">metricLabel</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-15</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setMetricName">[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">setMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricName`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.getMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.getMetricName">[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">getMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricName or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setMetricLabel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setMetricLabel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setMetricLabel</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricLabel`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricLabel</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.getMetricLabel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.getMetricLabel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMetricLabel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricLabel or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricLabel</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setBeta"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setBeta">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setBeta</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`beta`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">beta</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.getBeta"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.getBeta">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getBeta</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of beta or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">beta</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setEps"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setEps">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setEps</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`eps`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">eps</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.getEps"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.getEps">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getEps</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of eps or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">eps</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setLabelCol">[docs]</a> <span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`labelCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setPredictionCol">[docs]</a> <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setProbabilityCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setProbabilityCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setProbabilityCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`probabilityCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">probabilityCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`weightCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassClassificationEvaluator.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator.setParams">[docs]</a> <span class="nd">@keyword_only</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">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"f1"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">metricLabel</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">probabilityCol</span><span class="o">=</span><span class="s2">"probability"</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-15</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="f1", weightCol=None, metricLabel=0.0, beta=1.0, \</span> |
| <span class="sd"> probabilityCol="probability", eps=1e-15)</span> |
| <span class="sd"> Sets params for multiclass classification evaluator.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">MultilabelClassificationEvaluator</span><span class="p">(</span><span class="n">JavaEvaluator</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> |
| <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluator for Multilabel Classification, which expects two input</span> |
| <span class="sd"> columns: prediction and label.</span> |
| |
| <span class="sd"> .. versionadded:: 3.0.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Experimental</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> scoreAndLabels = [([0.0, 1.0], [0.0, 2.0]), ([0.0, 2.0], [0.0, 1.0]),</span> |
| <span class="sd"> ... ([], [0.0]), ([2.0], [2.0]), ([2.0, 0.0], [2.0, 0.0]),</span> |
| <span class="sd"> ... ([0.0, 1.0, 2.0], [0.0, 1.0]), ([1.0], [1.0, 2.0])]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabels, ["prediction", "label"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = MultilabelClassificationEvaluator()</span> |
| <span class="sd"> >>> evaluator.setPredictionCol("prediction")</span> |
| <span class="sd"> MultilabelClassificationEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.63...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "accuracy"})</span> |
| <span class="sd"> 0.54...</span> |
| <span class="sd"> >>> mlce_path = temp_path + "/mlce"</span> |
| <span class="sd"> >>> evaluator.save(mlce_path)</span> |
| <span class="sd"> >>> evaluator2 = MultilabelClassificationEvaluator.load(mlce_path)</span> |
| <span class="sd"> >>> str(evaluator2.getPredictionCol())</span> |
| <span class="sd"> 'prediction'</span> |
| <span class="sd"> """</span> |
| <span class="n">metricName</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricName"</span><span class="p">,</span> |
| <span class="s2">"metric name in evaluation "</span> |
| <span class="s2">"(subsetAccuracy|accuracy|hammingLoss|precision|recall|f1Measure|"</span> |
| <span class="s2">"precisionByLabel|recallByLabel|f1MeasureByLabel|microPrecision|"</span> |
| <span class="s2">"microRecall|microF1Measure)"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">metricLabel</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricLabel"</span><span class="p">,</span> |
| <span class="s2">"The class whose metric will be computed in precisionByLabel|"</span> |
| <span class="s2">"recallByLabel|f1MeasureByLabel. "</span> |
| <span class="s2">"Must be >= 0. The default value is 0."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">)</span> |
| |
| <span class="nd">@keyword_only</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="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"f1Measure"</span><span class="p">,</span> <span class="n">metricLabel</span><span class="o">=</span><span class="mf">0.0</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="f1Measure", metricLabel=0.0)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MultilabelClassificationEvaluator</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.evaluation.MultilabelClassificationEvaluator"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="s2">"f1Measure"</span><span class="p">,</span> <span class="n">metricLabel</span><span class="o">=</span><span class="mf">0.0</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.setMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.setMetricName">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricName`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.getMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.getMetricName">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricName or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.setMetricLabel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.setMetricLabel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setMetricLabel</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricLabel`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricLabel</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.getMetricLabel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.getMetricLabel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMetricLabel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricLabel or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricLabel</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.setLabelCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`labelCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MultilabelClassificationEvaluator.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.MultilabelClassificationEvaluator.html#pyspark.ml.evaluation.MultilabelClassificationEvaluator.setParams">[docs]</a> <span class="nd">@keyword_only</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"f1Measure"</span><span class="p">,</span> <span class="n">metricLabel</span><span class="o">=</span><span class="mf">0.0</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="f1Measure", metricLabel=0.0)</span> |
| <span class="sd"> Sets params for multilabel classification evaluator.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ClusteringEvaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">ClusteringEvaluator</span><span class="p">(</span><span class="n">JavaEvaluator</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasWeightCol</span><span class="p">,</span> |
| <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluator for Clustering results, which expects two input</span> |
| <span class="sd"> columns: prediction and features. The metric computes the Silhouette</span> |
| <span class="sd"> measure using the squared Euclidean distance.</span> |
| |
| <span class="sd"> The Silhouette is a measure for the validation of the consistency</span> |
| <span class="sd"> within clusters. It ranges between 1 and -1, where a value close to</span> |
| <span class="sd"> 1 means that the points in a cluster are close to the other points</span> |
| <span class="sd"> in the same cluster and far from the points of the other clusters.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import Vectors</span> |
| <span class="sd"> >>> featureAndPredictions = map(lambda x: (Vectors.dense(x[0]), x[1]),</span> |
| <span class="sd"> ... [([0.0, 0.5], 0.0), ([0.5, 0.0], 0.0), ([10.0, 11.0], 1.0),</span> |
| <span class="sd"> ... ([10.5, 11.5], 1.0), ([1.0, 1.0], 0.0), ([8.0, 6.0], 1.0)])</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(featureAndPredictions, ["features", "prediction"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = ClusteringEvaluator()</span> |
| <span class="sd"> >>> evaluator.setPredictionCol("prediction")</span> |
| <span class="sd"> ClusteringEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.9079...</span> |
| <span class="sd"> >>> featureAndPredictionsWithWeight = map(lambda x: (Vectors.dense(x[0]), x[1], x[2]),</span> |
| <span class="sd"> ... [([0.0, 0.5], 0.0, 2.5), ([0.5, 0.0], 0.0, 2.5), ([10.0, 11.0], 1.0, 2.5),</span> |
| <span class="sd"> ... ([10.5, 11.5], 1.0, 2.5), ([1.0, 1.0], 0.0, 2.5), ([8.0, 6.0], 1.0, 2.5)])</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(</span> |
| <span class="sd"> ... featureAndPredictionsWithWeight, ["features", "prediction", "weight"])</span> |
| <span class="sd"> >>> evaluator = ClusteringEvaluator()</span> |
| <span class="sd"> >>> evaluator.setPredictionCol("prediction")</span> |
| <span class="sd"> ClusteringEvaluator...</span> |
| <span class="sd"> >>> evaluator.setWeightCol("weight")</span> |
| <span class="sd"> ClusteringEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.9079...</span> |
| <span class="sd"> >>> ce_path = temp_path + "/ce"</span> |
| <span class="sd"> >>> evaluator.save(ce_path)</span> |
| <span class="sd"> >>> evaluator2 = ClusteringEvaluator.load(ce_path)</span> |
| <span class="sd"> >>> str(evaluator2.getPredictionCol())</span> |
| <span class="sd"> 'prediction'</span> |
| <span class="sd"> """</span> |
| <span class="n">metricName</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricName"</span><span class="p">,</span> |
| <span class="s2">"metric name in evaluation (silhouette)"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">distanceMeasure</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"distanceMeasure"</span><span class="p">,</span> <span class="s2">"The distance measure. "</span> <span class="o">+</span> |
| <span class="s2">"Supported options: 'squaredEuclidean' and 'cosine'."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| |
| <span class="nd">@keyword_only</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="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s2">"features"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"silhouette"</span><span class="p">,</span> <span class="n">distanceMeasure</span><span class="o">=</span><span class="s2">"squaredEuclidean"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, predictionCol="prediction", featuresCol="features", \</span> |
| <span class="sd"> metricName="silhouette", distanceMeasure="squaredEuclidean", weightCol=None)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ClusteringEvaluator</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.evaluation.ClusteringEvaluator"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="s2">"silhouette"</span><span class="p">,</span> <span class="n">distanceMeasure</span><span class="o">=</span><span class="s2">"squaredEuclidean"</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.setParams">[docs]</a> <span class="nd">@keyword_only</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.3.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s2">"features"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"silhouette"</span><span class="p">,</span> <span class="n">distanceMeasure</span><span class="o">=</span><span class="s2">"squaredEuclidean"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, predictionCol="prediction", featuresCol="features", \</span> |
| <span class="sd"> metricName="silhouette", distanceMeasure="squaredEuclidean", weightCol=None)</span> |
| <span class="sd"> Sets params for clustering evaluator.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.setMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.setMetricName">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.3.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricName`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.getMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.getMetricName">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.3.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricName or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.setDistanceMeasure"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.setDistanceMeasure">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setDistanceMeasure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`distanceMeasure`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">distanceMeasure</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.getDistanceMeasure"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.getDistanceMeasure">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getDistanceMeasure</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of `distanceMeasure`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">distanceMeasure</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.setFeaturesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.setFeaturesCol">[docs]</a> <span class="k">def</span> <span class="nf">setFeaturesCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`featuresCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">featuresCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.setPredictionCol">[docs]</a> <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ClusteringEvaluator.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.ClusteringEvaluator.html#pyspark.ml.evaluation.ClusteringEvaluator.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.1.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`weightCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="RankingEvaluator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">RankingEvaluator</span><span class="p">(</span><span class="n">JavaEvaluator</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> |
| <span class="n">JavaMLReadable</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Evaluator for Ranking, which expects two input</span> |
| <span class="sd"> columns: prediction and label.</span> |
| |
| <span class="sd"> .. versionadded:: 3.0.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Experimental</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> scoreAndLabels = [([1.0, 6.0, 2.0, 7.0, 8.0, 3.0, 9.0, 10.0, 4.0, 5.0],</span> |
| <span class="sd"> ... [1.0, 2.0, 3.0, 4.0, 5.0]),</span> |
| <span class="sd"> ... ([4.0, 1.0, 5.0, 6.0, 2.0, 7.0, 3.0, 8.0, 9.0, 10.0], [1.0, 2.0, 3.0]),</span> |
| <span class="sd"> ... ([1.0, 2.0, 3.0, 4.0, 5.0], [])]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(scoreAndLabels, ["prediction", "label"])</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> >>> evaluator = RankingEvaluator()</span> |
| <span class="sd"> >>> evaluator.setPredictionCol("prediction")</span> |
| <span class="sd"> RankingEvaluator...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset)</span> |
| <span class="sd"> 0.35...</span> |
| <span class="sd"> >>> evaluator.evaluate(dataset, {evaluator.metricName: "precisionAtK", evaluator.k: 2})</span> |
| <span class="sd"> 0.33...</span> |
| <span class="sd"> >>> ranke_path = temp_path + "/ranke"</span> |
| <span class="sd"> >>> evaluator.save(ranke_path)</span> |
| <span class="sd"> >>> evaluator2 = RankingEvaluator.load(ranke_path)</span> |
| <span class="sd"> >>> str(evaluator2.getPredictionCol())</span> |
| <span class="sd"> 'prediction'</span> |
| <span class="sd"> """</span> |
| <span class="n">metricName</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"metricName"</span><span class="p">,</span> |
| <span class="s2">"metric name in evaluation "</span> |
| <span class="s2">"(meanAveragePrecision|meanAveragePrecisionAtK|"</span> |
| <span class="s2">"precisionAtK|ndcgAtK|recallAtK)"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">k</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"k"</span><span class="p">,</span> |
| <span class="s2">"The ranking position value used in meanAveragePrecisionAtK|precisionAtK|"</span> |
| <span class="s2">"ndcgAtK|recallAtK. Must be > 0. The default value is 10."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">)</span> |
| |
| <span class="nd">@keyword_only</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="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"meanAveragePrecision"</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="meanAveragePrecision", k=10)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">RankingEvaluator</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.evaluation.RankingEvaluator"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="s2">"meanAveragePrecision"</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="RankingEvaluator.setMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.setMetricName">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`metricName`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">metricName</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RankingEvaluator.getMetricName"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.getMetricName">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMetricName</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of metricName or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metricName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RankingEvaluator.setK"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.setK">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setK</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`k`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">k</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RankingEvaluator.getK"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.getK">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getK</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of k or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">k</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RankingEvaluator.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.setLabelCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`labelCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RankingEvaluator.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RankingEvaluator.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.evaluation.RankingEvaluator.html#pyspark.ml.evaluation.RankingEvaluator.setParams">[docs]</a> <span class="nd">@keyword_only</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s2">"label"</span><span class="p">,</span> |
| <span class="n">metricName</span><span class="o">=</span><span class="s2">"meanAveragePrecision"</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">10</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, predictionCol="prediction", labelCol="label", \</span> |
| <span class="sd"> metricName="meanAveragePrecision", k=10)</span> |
| <span class="sd"> Sets params for ranking evaluator.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div> |
| |
| |
| <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="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">tempfile</span> |
| <span class="kn">import</span> <span class="nn">pyspark.ml.evaluation</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="n">pyspark</span><span class="o">.</span><span class="n">ml</span><span class="o">.</span><span class="n">evaluation</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="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">"ml.evaluation tests"</span><span class="p">)</span>\ |
| <span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s1">'spark'</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span> |
| <span class="n">temp_path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s1">'temp_path'</span><span class="p">]</span> <span class="o">=</span> <span class="n">temp_path</span> |
| <span class="k">try</span><span class="p">:</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">finally</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">rmtree</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span> |
| <span class="k">pass</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> |
| </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> |
