| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.evaluation — PySpark 3.5.3 documentation</title> |
| |
| <link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/styles/pydata-sphinx-theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/clipboard.min.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/mllib/evaluation.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="None"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl"> |
| |
| <div id="navbar-start"> |
| |
| |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo"> |
| </a> |
| |
| |
| |
| </div> |
| |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| |
| <div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse"> |
| <div id="navbar-center" class="mr-auto"> |
| |
| <div class="navbar-center-item"> |
| <ul id="navbar-main-elements" class="navbar-nav"> |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| |
| </ul> |
| </div> |
| |
| </div> |
| |
| <div id="navbar-end"> |
| |
| <div class="navbar-end-item"> |
| <!-- |
| Licensed to the Apache Software Foundation (ASF) under one or more |
| contributor license agreements. See the NOTICE file distributed with |
| this work for additional information regarding copyright ownership. |
| The ASF licenses this file to You under the Apache License, Version 2.0 |
| (the "License"); you may not use this file except in compliance with |
| the License. You may obtain a copy of the License at |
| |
| http://www.apache.org/licenses/LICENSE-2.0 |
| |
| Unless required by applicable law or agreed to in writing, software |
| distributed under the License is distributed on an "AS IS" BASIS, |
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| See the License for the specific language governing permissions and |
| limitations under the License. |
| --> |
| |
| <div id="version-button" class="dropdown"> |
| <button type="button" class="btn btn-secondary btn-sm navbar-btn dropdown-toggle" id="version_switcher_button" data-toggle="dropdown"> |
| 3.5.3 |
| <span class="caret"></span> |
| </button> |
| <div id="version_switcher" class="dropdown-menu list-group-flush py-0" aria-labelledby="version_switcher_button"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| |
| <script type="text/javascript"> |
| // Function to construct the target URL from the JSON components |
| function buildURL(entry) { |
| var template = "https://spark.apache.org/docs/{version}/api/python/index.html"; // supplied by jinja |
| template = template.replace("{version}", entry.version); |
| return template; |
| } |
| |
| // Function to check if corresponding page path exists in other version of docs |
| // and, if so, go there instead of the homepage of the other docs version |
| function checkPageExistsAndRedirect(event) { |
| const currentFilePath = "_modules/pyspark/mllib/evaluation.html", |
| otherDocsHomepage = event.target.getAttribute("href"); |
| let tryUrl = `${otherDocsHomepage}${currentFilePath}`; |
| $.ajax({ |
| type: 'HEAD', |
| url: tryUrl, |
| // if the page exists, go there |
| success: function() { |
| location.href = tryUrl; |
| } |
| }).fail(function() { |
| location.href = otherDocsHomepage; |
| }); |
| return false; |
| } |
| |
| // Function to populate the version switcher |
| (function () { |
| // get JSON config |
| $.getJSON("https://spark.apache.org/static/versions.json", function(data, textStatus, jqXHR) { |
| // create the nodes first (before AJAX calls) to ensure the order is |
| // correct (for now, links will go to doc version homepage) |
| $.each(data, function(index, entry) { |
| // if no custom name specified (e.g., "latest"), use version string |
| if (!("name" in entry)) { |
| entry.name = entry.version; |
| } |
| // construct the appropriate URL, and add it to the dropdown |
| entry.url = buildURL(entry); |
| const node = document.createElement("a"); |
| node.setAttribute("class", "list-group-item list-group-item-action py-1"); |
| node.setAttribute("href", `${entry.url}`); |
| node.textContent = `${entry.name}`; |
| node.onclick = checkPageExistsAndRedirect; |
| $("#version_switcher").append(node); |
| }); |
| }); |
| })(); |
| </script> |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form><nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| <div class="bd-toc-item active"> |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| </div> |
| |
| |
| |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.mllib.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">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Generic</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">TypeVar</span><span class="p">,</span> <span class="n">Union</span> |
| |
| <span class="kn">import</span> <span class="nn">sys</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.rdd</span> <span class="kn">import</span> <span class="n">RDD</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">callMLlibFunc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Matrix</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SQLContext</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">ArrayType</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">,</span> <span class="n">StructField</span><span class="p">,</span> <span class="n">StructType</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s2">"BinaryClassificationMetrics"</span><span class="p">,</span> |
| <span class="s2">"RegressionMetrics"</span><span class="p">,</span> |
| <span class="s2">"MulticlassMetrics"</span><span class="p">,</span> |
| <span class="s2">"RankingMetrics"</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| <span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"T"</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="BinaryClassificationMetrics"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.BinaryClassificationMetrics.html#pyspark.mllib.evaluation.BinaryClassificationMetrics">[docs]</a><span class="k">class</span> <span class="nc">BinaryClassificationMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Evaluator for binary classification.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> scoreAndLabels : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of score, label and optional weight.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> scoreAndLabels = sc.parallelize([</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)], 2)</span> |
| <span class="sd"> >>> metrics = BinaryClassificationMetrics(scoreAndLabels)</span> |
| <span class="sd"> >>> metrics.areaUnderROC</span> |
| <span class="sd"> 0.70...</span> |
| <span class="sd"> >>> metrics.areaUnderPR</span> |
| <span class="sd"> 0.83...</span> |
| <span class="sd"> >>> metrics.unpersist()</span> |
| <span class="sd"> >>> scoreAndLabelsWithOptWeight = sc.parallelize([</span> |
| <span class="sd"> ... (0.1, 0.0, 1.0), (0.1, 1.0, 0.4), (0.4, 0.0, 0.2), (0.6, 0.0, 0.6), (0.6, 1.0, 0.9),</span> |
| <span class="sd"> ... (0.6, 1.0, 0.5), (0.8, 1.0, 0.7)], 2)</span> |
| <span class="sd"> >>> metrics = BinaryClassificationMetrics(scoreAndLabelsWithOptWeight)</span> |
| <span class="sd"> >>> metrics.areaUnderROC</span> |
| <span class="sd"> 0.79...</span> |
| <span class="sd"> >>> metrics.areaUnderPR</span> |
| <span class="sd"> 0.88...</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scoreAndLabels</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]):</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">scoreAndLabels</span><span class="o">.</span><span class="n">ctx</span> |
| <span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span> |
| <span class="n">numCol</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">scoreAndLabels</span><span class="o">.</span><span class="n">first</span><span class="p">())</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">StructType</span><span class="p">(</span> |
| <span class="p">[</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"score"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"label"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> |
| <span class="p">]</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="n">numCol</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span> |
| <span class="n">schema</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"weight"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">scoreAndLabels</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">BinaryClassificationMetrics</span> |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">BinaryClassificationMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">areaUnderROC</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Computes the area under the receiver operating characteristic</span> |
| <span class="sd"> (ROC) curve.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"areaUnderROC"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">areaUnderPR</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Computes the area under the precision-recall curve.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"areaUnderPR"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="BinaryClassificationMetrics.unpersist"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.BinaryClassificationMetrics.html#pyspark.mllib.evaluation.BinaryClassificationMetrics.unpersist">[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">unpersist</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Unpersists intermediate RDDs used in the computation.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"unpersist"</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="RegressionMetrics"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.RegressionMetrics.html#pyspark.mllib.evaluation.RegressionMetrics">[docs]</a><span class="k">class</span> <span class="nc">RegressionMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Evaluator for regression.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> predictionAndObservations : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of prediction, observation and optional weight.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> predictionAndObservations = sc.parallelize([</span> |
| <span class="sd"> ... (2.5, 3.0), (0.0, -0.5), (2.0, 2.0), (8.0, 7.0)])</span> |
| <span class="sd"> >>> metrics = RegressionMetrics(predictionAndObservations)</span> |
| <span class="sd"> >>> metrics.explainedVariance</span> |
| <span class="sd"> 8.859...</span> |
| <span class="sd"> >>> metrics.meanAbsoluteError</span> |
| <span class="sd"> 0.5...</span> |
| <span class="sd"> >>> metrics.meanSquaredError</span> |
| <span class="sd"> 0.37...</span> |
| <span class="sd"> >>> metrics.rootMeanSquaredError</span> |
| <span class="sd"> 0.61...</span> |
| <span class="sd"> >>> metrics.r2</span> |
| <span class="sd"> 0.94...</span> |
| <span class="sd"> >>> predictionAndObservationsWithOptWeight = sc.parallelize([</span> |
| <span class="sd"> ... (2.5, 3.0, 0.5), (0.0, -0.5, 1.0), (2.0, 2.0, 0.3), (8.0, 7.0, 0.9)])</span> |
| <span class="sd"> >>> metrics = RegressionMetrics(predictionAndObservationsWithOptWeight)</span> |
| <span class="sd"> >>> metrics.rootMeanSquaredError</span> |
| <span class="sd"> 0.68...</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndObservations</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]):</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndObservations</span><span class="o">.</span><span class="n">ctx</span> |
| <span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span> |
| <span class="n">numCol</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">predictionAndObservations</span><span class="o">.</span><span class="n">first</span><span class="p">())</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">StructType</span><span class="p">(</span> |
| <span class="p">[</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"observation"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> |
| <span class="p">]</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="n">numCol</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span> |
| <span class="n">schema</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"weight"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">predictionAndObservations</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">RegressionMetrics</span> |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">RegressionMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">explainedVariance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sa">r</span><span class="sd">"""</span> |
| <span class="sd"> Returns the explained variance regression score.</span> |
| <span class="sd"> explainedVariance = :math:`1 - \frac{variance(y - \hat{y})}{variance(y)}`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"explainedVariance"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">meanAbsoluteError</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the mean absolute error, which is a risk function corresponding to the</span> |
| <span class="sd"> expected value of the absolute error loss or l1-norm loss.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"meanAbsoluteError"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">meanSquaredError</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the mean squared error, which is a risk function corresponding to the</span> |
| <span class="sd"> expected value of the squared error loss or quadratic loss.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"meanSquaredError"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">rootMeanSquaredError</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the root mean squared error, which is defined as the square root of</span> |
| <span class="sd"> the mean squared error.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"rootMeanSquaredError"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">r2</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns R^2^, the coefficient of determination.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"r2"</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="MulticlassMetrics"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics">[docs]</a><span class="k">class</span> <span class="nc">MulticlassMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Evaluator for multiclass classification.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> predictionAndLabels : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of prediction, label, optional weight and optional probability.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> predictionAndLabels = sc.parallelize([(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"> >>> metrics = MulticlassMetrics(predictionAndLabels)</span> |
| <span class="sd"> >>> metrics.confusionMatrix().toArray()</span> |
| <span class="sd"> array([[ 2., 1., 1.],</span> |
| <span class="sd"> [ 1., 3., 0.],</span> |
| <span class="sd"> [ 0., 0., 1.]])</span> |
| <span class="sd"> >>> metrics.falsePositiveRate(0.0)</span> |
| <span class="sd"> 0.2...</span> |
| <span class="sd"> >>> metrics.precision(1.0)</span> |
| <span class="sd"> 0.75...</span> |
| <span class="sd"> >>> metrics.recall(2.0)</span> |
| <span class="sd"> 1.0...</span> |
| <span class="sd"> >>> metrics.fMeasure(0.0, 2.0)</span> |
| <span class="sd"> 0.52...</span> |
| <span class="sd"> >>> metrics.accuracy</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.weightedFalsePositiveRate</span> |
| <span class="sd"> 0.19...</span> |
| <span class="sd"> >>> metrics.weightedPrecision</span> |
| <span class="sd"> 0.68...</span> |
| <span class="sd"> >>> metrics.weightedRecall</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.weightedFMeasure()</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.weightedFMeasure(2.0)</span> |
| <span class="sd"> 0.65...</span> |
| <span class="sd"> >>> predAndLabelsWithOptWeight = sc.parallelize([(0.0, 0.0, 1.0), (0.0, 1.0, 1.0),</span> |
| <span class="sd"> ... (0.0, 0.0, 1.0), (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"> >>> metrics = MulticlassMetrics(predAndLabelsWithOptWeight)</span> |
| <span class="sd"> >>> metrics.confusionMatrix().toArray()</span> |
| <span class="sd"> array([[ 2., 1., 1.],</span> |
| <span class="sd"> [ 1., 3., 0.],</span> |
| <span class="sd"> [ 0., 0., 1.]])</span> |
| <span class="sd"> >>> metrics.falsePositiveRate(0.0)</span> |
| <span class="sd"> 0.2...</span> |
| <span class="sd"> >>> metrics.precision(1.0)</span> |
| <span class="sd"> 0.75...</span> |
| <span class="sd"> >>> metrics.recall(2.0)</span> |
| <span class="sd"> 1.0...</span> |
| <span class="sd"> >>> metrics.fMeasure(0.0, 2.0)</span> |
| <span class="sd"> 0.52...</span> |
| <span class="sd"> >>> metrics.accuracy</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.weightedFalsePositiveRate</span> |
| <span class="sd"> 0.19...</span> |
| <span class="sd"> >>> metrics.weightedPrecision</span> |
| <span class="sd"> 0.68...</span> |
| <span class="sd"> >>> metrics.weightedRecall</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.weightedFMeasure()</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.weightedFMeasure(2.0)</span> |
| <span class="sd"> 0.65...</span> |
| <span class="sd"> >>> predictionAndLabelsWithProbabilities = sc.parallelize([</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"> >>> metrics = MulticlassMetrics(predictionAndLabelsWithProbabilities)</span> |
| <span class="sd"> >>> metrics.logLoss()</span> |
| <span class="sd"> 0.9682...</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndLabels</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]):</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">ctx</span> |
| <span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span> |
| <span class="n">numCol</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">first</span><span class="p">())</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">StructType</span><span class="p">(</span> |
| <span class="p">[</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"prediction"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"label"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span> |
| <span class="p">]</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="n">numCol</span> <span class="o">>=</span> <span class="mi">3</span><span class="p">:</span> |
| <span class="n">schema</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"weight"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">numCol</span> <span class="o">==</span> <span class="mi">4</span><span class="p">:</span> |
| <span class="n">schema</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"probability"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> <span class="kc">False</span><span class="p">)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">MulticlassMetrics</span> |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MulticlassMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.confusionMatrix"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.confusionMatrix">[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">confusionMatrix</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Matrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns confusion matrix: predicted classes are in columns,</span> |
| <span class="sd"> they are ordered by class label ascending, as in "labels".</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"confusionMatrix"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.truePositiveRate"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.truePositiveRate">[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">truePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns true positive rate for a given label (category).</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"truePositiveRate"</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.falsePositiveRate"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.falsePositiveRate">[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">falsePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns false positive rate for a given label (category).</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"falsePositiveRate"</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.precision"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.precision">[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">precision</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns precision.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"precision"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.recall"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.recall">[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">recall</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns recall.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"recall"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.fMeasure"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.fMeasure">[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">fMeasure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">beta</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns f-measure.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">beta</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"fMeasure"</span><span class="p">,</span> <span class="n">label</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">call</span><span class="p">(</span><span class="s2">"fMeasure"</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span></div> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">accuracy</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns accuracy (equals to the total number of correctly classified instances</span> |
| <span class="sd"> out of the total number of instances).</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"accuracy"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">weightedTruePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns weighted true positive rate.</span> |
| <span class="sd"> (equals to precision, recall and f-measure)</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"weightedTruePositiveRate"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">weightedFalsePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns weighted false positive rate.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"weightedFalsePositiveRate"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">weightedRecall</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns weighted averaged recall.</span> |
| <span class="sd"> (equals to precision, recall and f-measure)</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"weightedRecall"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">weightedPrecision</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns weighted averaged precision.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"weightedPrecision"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.weightedFMeasure"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.weightedFMeasure">[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">weightedFMeasure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">beta</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns weighted averaged f-measure.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">beta</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"weightedFMeasure"</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">call</span><span class="p">(</span><span class="s2">"weightedFMeasure"</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MulticlassMetrics.logLoss"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.MulticlassMetrics.html#pyspark.mllib.evaluation.MulticlassMetrics.logLoss">[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">logLoss</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-15</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns weighted logLoss.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"logLoss"</span><span class="p">,</span> <span class="n">eps</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="RankingMetrics"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics">[docs]</a><span class="k">class</span> <span class="nc">RankingMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">Generic</span><span class="p">[</span><span class="n">T</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Evaluator for ranking algorithms.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> predictionAndLabels : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of (predicted ranking, ground truth set) pairs</span> |
| <span class="sd"> or (predicted ranking, ground truth set,</span> |
| <span class="sd"> relevance value of ground truth set).</span> |
| <span class="sd"> Since 3.4.0, it supports ndcg evaluation with relevance value.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> predictionAndLabels = sc.parallelize([</span> |
| <span class="sd"> ... ([1, 6, 2, 7, 8, 3, 9, 10, 4, 5], [1, 2, 3, 4, 5]),</span> |
| <span class="sd"> ... ([4, 1, 5, 6, 2, 7, 3, 8, 9, 10], [1, 2, 3]),</span> |
| <span class="sd"> ... ([1, 2, 3, 4, 5], [])])</span> |
| <span class="sd"> >>> metrics = RankingMetrics(predictionAndLabels)</span> |
| <span class="sd"> >>> metrics.precisionAt(1)</span> |
| <span class="sd"> 0.33...</span> |
| <span class="sd"> >>> metrics.precisionAt(5)</span> |
| <span class="sd"> 0.26...</span> |
| <span class="sd"> >>> metrics.precisionAt(15)</span> |
| <span class="sd"> 0.17...</span> |
| <span class="sd"> >>> metrics.meanAveragePrecision</span> |
| <span class="sd"> 0.35...</span> |
| <span class="sd"> >>> metrics.meanAveragePrecisionAt(1)</span> |
| <span class="sd"> 0.3333333333333333...</span> |
| <span class="sd"> >>> metrics.meanAveragePrecisionAt(2)</span> |
| <span class="sd"> 0.25...</span> |
| <span class="sd"> >>> metrics.ndcgAt(3)</span> |
| <span class="sd"> 0.33...</span> |
| <span class="sd"> >>> metrics.ndcgAt(10)</span> |
| <span class="sd"> 0.48...</span> |
| <span class="sd"> >>> metrics.recallAt(1)</span> |
| <span class="sd"> 0.06...</span> |
| <span class="sd"> >>> metrics.recallAt(5)</span> |
| <span class="sd"> 0.35...</span> |
| <span class="sd"> >>> metrics.recallAt(15)</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">predictionAndLabels</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span> |
| <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">],</span> <span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">]]],</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">],</span> <span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">],</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]]]</span> |
| <span class="p">],</span> |
| <span class="p">):</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">ctx</span> |
| <span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span> |
| <span class="n">predictionAndLabels</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">sql_ctx</span><span class="o">.</span><span class="n">_inferSchema</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"newRankingMetrics"</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">RankingMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="RankingMetrics.precisionAt"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics.precisionAt">[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">precisionAt</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute the average precision of all the queries, truncated at ranking position k.</span> |
| |
| <span class="sd"> If for a query, the ranking algorithm returns n (n < k) results, the precision value</span> |
| <span class="sd"> will be computed as #(relevant items retrieved) / k. This formula also applies when</span> |
| <span class="sd"> the size of the ground truth set is less than k.</span> |
| |
| <span class="sd"> If a query has an empty ground truth set, zero will be used as precision together</span> |
| <span class="sd"> with a log warning.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"precisionAt"</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">))</span></div> |
| |
| <span class="nd">@property</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">meanAveragePrecision</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the mean average precision (MAP) of all the queries.</span> |
| <span class="sd"> If a query has an empty ground truth set, the average precision will be zero and</span> |
| <span class="sd"> a log warning is generated.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"meanAveragePrecision"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="RankingMetrics.meanAveragePrecisionAt"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics.meanAveragePrecisionAt">[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">meanAveragePrecisionAt</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the mean average precision (MAP) at first k ranking of all the queries.</span> |
| <span class="sd"> If a query has an empty ground truth set, the average precision will be zero and</span> |
| <span class="sd"> a log warning is generated.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"meanAveragePrecisionAt"</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="RankingMetrics.ndcgAt"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics.ndcgAt">[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">ndcgAt</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute the average NDCG value of all the queries, truncated at ranking position k.</span> |
| <span class="sd"> The discounted cumulative gain at position k is computed as:</span> |
| <span class="sd"> sum,,i=1,,^k^ (2^{relevance of ''i''th item}^ - 1) / log(i + 1),</span> |
| <span class="sd"> and the NDCG is obtained by dividing the DCG value on the ground truth set.</span> |
| <span class="sd"> In the current implementation, the relevance value is binary.</span> |
| <span class="sd"> If a query has an empty ground truth set, zero will be used as NDCG together with</span> |
| <span class="sd"> a log warning.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"ndcgAt"</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="RankingMetrics.recallAt"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.evaluation.RankingMetrics.html#pyspark.mllib.evaluation.RankingMetrics.recallAt">[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">recallAt</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute the average recall of all the queries, truncated at ranking position k.</span> |
| |
| <span class="sd"> If for a query, the ranking algorithm returns n results, the recall value</span> |
| <span class="sd"> will be computed as #(relevant items retrieved) / #(ground truth set).</span> |
| <span class="sd"> This formula also applies when the size of the ground truth set is less than k.</span> |
| |
| <span class="sd"> If a query has an empty ground truth set, zero will be used as recall together</span> |
| <span class="sd"> with a log warning.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"recallAt"</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">))</span></div></div> |
| |
| |
| <span class="k">class</span> <span class="nc">MultilabelMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Evaluator for multilabel classification.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> predictionAndLabels : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> an RDD of (predictions, labels) pairs,</span> |
| <span class="sd"> both are non-null Arrays, each with unique elements.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> predictionAndLabels = sc.parallelize([([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"> >>> metrics = MultilabelMetrics(predictionAndLabels)</span> |
| <span class="sd"> >>> metrics.precision(0.0)</span> |
| <span class="sd"> 1.0</span> |
| <span class="sd"> >>> metrics.recall(1.0)</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.f1Measure(2.0)</span> |
| <span class="sd"> 0.5</span> |
| <span class="sd"> >>> metrics.precision()</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.recall()</span> |
| <span class="sd"> 0.64...</span> |
| <span class="sd"> >>> metrics.f1Measure()</span> |
| <span class="sd"> 0.63...</span> |
| <span class="sd"> >>> metrics.microPrecision</span> |
| <span class="sd"> 0.72...</span> |
| <span class="sd"> >>> metrics.microRecall</span> |
| <span class="sd"> 0.66...</span> |
| <span class="sd"> >>> metrics.microF1Measure</span> |
| <span class="sd"> 0.69...</span> |
| <span class="sd"> >>> metrics.hammingLoss</span> |
| <span class="sd"> 0.33...</span> |
| <span class="sd"> >>> metrics.subsetAccuracy</span> |
| <span class="sd"> 0.28...</span> |
| <span class="sd"> >>> metrics.accuracy</span> |
| <span class="sd"> 0.54...</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndLabels</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]]]):</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">ctx</span> |
| <span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span> |
| <span class="n">predictionAndLabels</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">sql_ctx</span><span class="o">.</span><span class="n">_inferSchema</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">MultilabelMetrics</span> |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MultilabelMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</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">precision</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns precision or precision for a given label (category) if specified.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"precision"</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">call</span><span class="p">(</span><span class="s2">"precision"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</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">recall</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns recall or recall for a given label (category) if specified.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"recall"</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">call</span><span class="p">(</span><span class="s2">"recall"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</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">f1Measure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns f1Measure or f1Measure for a given label (category) if specified.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"f1Measure"</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">call</span><span class="p">(</span><span class="s2">"f1Measure"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span> |
| |
| <span class="nd">@property</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">microPrecision</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns micro-averaged label-based precision.</span> |
| <span class="sd"> (equals to micro-averaged document-based precision)</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"microPrecision"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">microRecall</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns micro-averaged label-based recall.</span> |
| <span class="sd"> (equals to micro-averaged document-based recall)</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"microRecall"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">microF1Measure</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns micro-averaged label-based f1-measure.</span> |
| <span class="sd"> (equals to micro-averaged document-based f1-measure)</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"microF1Measure"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">hammingLoss</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns Hamming-loss.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"hammingLoss"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">subsetAccuracy</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns subset accuracy.</span> |
| <span class="sd"> (for equal sets of labels)</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"subsetAccuracy"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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">accuracy</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns accuracy.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"accuracy"</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">numpy</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">import</span> <span class="nn">pyspark.mllib.evaluation</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="c1"># Numpy 1.14+ changed it's string format.</span> |
| <span class="n">numpy</span><span class="o">.</span><span class="n">set_printoptions</span><span class="p">(</span><span class="n">legacy</span><span class="o">=</span><span class="s2">"1.13"</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">TypeError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">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="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"mllib.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="s2">"sc"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span> |
| <span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <div class="footer-item"> |
| <p class="copyright"> |
| © Copyright .<br> |
| </p> |
| </div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br> |
| </p> |
| </div> |
| |
| </div> |
| </footer> |
| </body> |
| </html> |
