| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>pyspark.ml.stat — PySpark 4.0.0-preview1 documentation</title> |
| |
| |
| |
| <script data-cfasync="false"> |
| document.documentElement.dataset.mode = localStorage.getItem("mode") || ""; |
| document.documentElement.dataset.theme = localStorage.getItem("theme") || "light"; |
| </script> |
| |
| <!-- Loaded before other Sphinx assets --> |
| <link href="../../../_static/styles/theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../../../_static/styles/bootstrap.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| |
| |
| <link href="../../../_static/vendor/fontawesome/6.1.2/css/all.min.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-solid-900.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-brands-400.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-regular-400.woff2" /> |
| |
| <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <!-- Pre-loaded scripts that we'll load fully later --> |
| <link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52" /> |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52" /> |
| |
| <script data-url_root="../../../" id="documentation_options" 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/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>DOCUMENTATION_OPTIONS.pagename = '_modules/pyspark/ml/stat';</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/ml/stat.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"> |
| |
| |
| <!-- Matomo --> |
| <script type="text/javascript"> |
| var _paq = window._paq = window._paq || []; |
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */ |
| _paq.push(["disableCookies"]); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '40']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo Code --> |
| |
| </head> |
| |
| |
| <body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode=""> |
| |
| |
| |
| <a class="skip-link" href="#main-content">Skip to main content</a> |
| |
| <input type="checkbox" |
| class="sidebar-toggle" |
| name="__primary" |
| id="__primary"/> |
| <label class="overlay overlay-primary" for="__primary"></label> |
| |
| <input type="checkbox" |
| class="sidebar-toggle" |
| name="__secondary" |
| id="__secondary"/> |
| <label class="overlay overlay-secondary" for="__secondary"></label> |
| |
| <div class="search-button__wrapper"> |
| <div class="search-button__overlay"></div> |
| <div class="search-button__search-container"> |
| <form class="bd-search d-flex align-items-center" |
| action="../../../search.html" |
| method="get"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| <input type="search" |
| class="form-control" |
| name="q" |
| id="search-input" |
| placeholder="Search the docs ..." |
| aria-label="Search the docs ..." |
| autocomplete="off" |
| autocorrect="off" |
| autocapitalize="off" |
| spellcheck="false"/> |
| <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span> |
| </form></div> |
| </div> |
| |
| <nav class="bd-header navbar navbar-expand-lg bd-navbar"> |
| <div class="bd-header__inner bd-page-width"> |
| <label class="sidebar-toggle primary-toggle" for="__primary"> |
| <span class="fa-solid fa-bars"></span> |
| </label> |
| |
| <div class="navbar-header-items__start"> |
| |
| <div class="navbar-item"> |
| |
| |
| <a class="navbar-brand logo" href="../../../index.html"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <img src="../../../_static/spark-logo-light.png" class="logo__image only-light" alt="Logo image"/> |
| <script>document.write(`<img src="../../../_static/spark-logo-dark.png" class="logo__image only-dark" alt="Logo image"/>`);</script> |
| |
| |
| </a></div> |
| |
| </div> |
| |
| |
| <div class="col-lg-9 navbar-header-items"> |
| |
| <div class="me-auto navbar-header-items__center"> |
| |
| <div class="navbar-item"><nav class="navbar-nav"> |
| <p class="sidebar-header-items__title" |
| role="heading" |
| aria-level="1" |
| aria-label="Site Navigation"> |
| Site Navigation |
| </p> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| <div class="navbar-header-items__end"> |
| |
| <div class="navbar-item navbar-persistent--container"> |
| |
| <script> |
| document.write(` |
| <button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| </button> |
| `); |
| </script> |
| </div> |
| |
| |
| <div class="navbar-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"> |
| 4.0.0-preview1 |
| <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/ml/stat.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 class="navbar-item"> |
| <script> |
| document.write(` |
| <button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span> |
| <span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span> |
| <span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span> |
| </button> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links navbar-nav" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span> |
| <label class="sr-only">GitHub</label></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span> |
| <label class="sr-only">PyPI</label></a> |
| </li> |
| </ul></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <div class="navbar-persistent--mobile"> |
| <script> |
| document.write(` |
| <button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| </button> |
| `); |
| </script> |
| </div> |
| |
| |
| |
| </div> |
| |
| </nav> |
| |
| <div class="bd-container"> |
| <div class="bd-container__inner bd-page-width"> |
| |
| <div class="bd-sidebar-primary bd-sidebar hide-on-wide"> |
| |
| |
| |
| <div class="sidebar-header-items sidebar-primary__section"> |
| |
| |
| <div class="sidebar-header-items__center"> |
| |
| <div class="navbar-item"><nav class="navbar-nav"> |
| <p class="sidebar-header-items__title" |
| role="heading" |
| aria-level="1" |
| aria-label="Site Navigation"> |
| Site Navigation |
| </p> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| |
| <div class="sidebar-header-items__end"> |
| |
| <div class="navbar-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"> |
| 4.0.0-preview1 |
| <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/ml/stat.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 class="navbar-item"> |
| <script> |
| document.write(` |
| <button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span> |
| <span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span> |
| <span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span> |
| </button> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links navbar-nav" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span> |
| <label class="sr-only">GitHub</label></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span> |
| <label class="sr-only">PyPI</label></a> |
| </li> |
| </ul></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <div class="sidebar-primary-items__end sidebar-primary__section"> |
| </div> |
| |
| <div id="rtd-footer-container"></div> |
| |
| |
| </div> |
| |
| <main id="main-content" class="bd-main"> |
| |
| |
| <div class="bd-content"> |
| <div class="bd-article-container"> |
| |
| <div class="bd-header-article"> |
| <div class="header-article-items header-article__inner"> |
| |
| <div class="header-article-items__start"> |
| |
| <div class="header-article-item"> |
| |
| |
| |
| <nav aria-label="Breadcrumbs"> |
| <ul class="bd-breadcrumbs" role="navigation" aria-label="Breadcrumb"> |
| |
| <li class="breadcrumb-item breadcrumb-home"> |
| <a href="../../../index.html" class="nav-link" aria-label="Home"> |
| <i class="fa-solid fa-home"></i> |
| </a> |
| </li> |
| |
| <li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li> |
| |
| <li class="breadcrumb-item active" aria-current="page">pyspark.ml.stat</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <h1>Source code for pyspark.ml.stat</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">typing</span> <span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">TYPE_CHECKING</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.ml.common</span> <span class="kn">import</span> <span class="n">_java2py</span><span class="p">,</span> <span class="n">_py2java</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="kn">import</span> <span class="n">Matrix</span><span class="p">,</span> <span class="n">Vector</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="n">JavaWrapper</span><span class="p">,</span> <span class="n">_jvm</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.column</span> <span class="kn">import</span> <span class="n">Column</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.dataframe</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">lit</span> |
| |
| <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">py4j.java_gateway</span> <span class="kn">import</span> <span class="n">JavaObject</span> |
| |
| |
| <div class="viewcode-block" id="ChiSquareTest"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.ChiSquareTest.html#pyspark.ml.stat.ChiSquareTest">[docs]</a><span class="k">class</span> <span class="nc">ChiSquareTest</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Conduct Pearson's independence test for every feature against the label. For each feature,</span> |
| <span class="sd"> the (feature, label) pairs are converted into a contingency matrix for which the Chi-squared</span> |
| <span class="sd"> statistic is computed. All label and feature values must be categorical.</span> |
| |
| <span class="sd"> The null hypothesis is that the occurrence of the outcomes is statistically independent.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="ChiSquareTest.test"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.ChiSquareTest.html#pyspark.ml.stat.ChiSquareTest.test">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">test</span><span class="p">(</span> |
| <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">flatten</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Perform a Pearson's independence test using dataset.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| <span class="sd"> .. versionchanged:: 3.1.0</span> |
| <span class="sd"> Added optional ``flatten`` argument.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> DataFrame of categorical labels and categorical features.</span> |
| <span class="sd"> Real-valued features will be treated as categorical for each distinct value.</span> |
| <span class="sd"> featuresCol : str</span> |
| <span class="sd"> Name of features column in dataset, of type `Vector` (`VectorUDT`).</span> |
| <span class="sd"> labelCol : str</span> |
| <span class="sd"> Name of label column in dataset, of any numerical type.</span> |
| <span class="sd"> flatten : bool, optional</span> |
| <span class="sd"> if True, flattens the returned dataframe.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> DataFrame containing the test result for every feature against the label.</span> |
| <span class="sd"> If flatten is True, this DataFrame will contain one row per feature with the following</span> |
| <span class="sd"> fields:</span> |
| |
| <span class="sd"> - `featureIndex: int`</span> |
| <span class="sd"> - `pValue: float`</span> |
| <span class="sd"> - `degreesOfFreedom: int`</span> |
| <span class="sd"> - `statistic: float`</span> |
| |
| <span class="sd"> If flatten is False, this DataFrame will contain a single Row with the following fields:</span> |
| |
| <span class="sd"> - `pValues: Vector`</span> |
| <span class="sd"> - `degreesOfFreedom: Array[int]`</span> |
| <span class="sd"> - `statistics: Vector`</span> |
| |
| <span class="sd"> Each of these fields has one value per feature.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import Vectors</span> |
| <span class="sd"> >>> from pyspark.ml.stat import ChiSquareTest</span> |
| <span class="sd"> >>> dataset = [[0, Vectors.dense([0, 0, 1])],</span> |
| <span class="sd"> ... [0, Vectors.dense([1, 0, 1])],</span> |
| <span class="sd"> ... [1, Vectors.dense([2, 1, 1])],</span> |
| <span class="sd"> ... [1, Vectors.dense([3, 1, 1])]]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(dataset, ["label", "features"])</span> |
| <span class="sd"> >>> chiSqResult = ChiSquareTest.test(dataset, 'features', 'label')</span> |
| <span class="sd"> >>> chiSqResult.select("degreesOfFreedom").collect()[0]</span> |
| <span class="sd"> Row(degreesOfFreedom=[3, 1, 0])</span> |
| <span class="sd"> >>> chiSqResult = ChiSquareTest.test(dataset, 'features', 'label', True)</span> |
| <span class="sd"> >>> row = chiSqResult.orderBy("featureIndex").collect()</span> |
| <span class="sd"> >>> row[0].statistic</span> |
| <span class="sd"> 4.0</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark.core.context</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> |
| <span class="k">assert</span> <span class="n">sc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">javaTestObj</span> <span class="o">=</span> <span class="n">_jvm</span><span class="p">()</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">ml</span><span class="o">.</span><span class="n">stat</span><span class="o">.</span><span class="n">ChiSquareTest</span> |
| <span class="n">args</span> <span class="o">=</span> <span class="p">[</span><span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">arg</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">featuresCol</span><span class="p">,</span> <span class="n">labelCol</span><span class="p">,</span> <span class="n">flatten</span><span class="p">)]</span> |
| <span class="k">return</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">javaTestObj</span><span class="o">.</span><span class="n">test</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Correlation"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Correlation.html#pyspark.ml.stat.Correlation">[docs]</a><span class="k">class</span> <span class="nc">Correlation</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute the correlation matrix for the input dataset of Vectors using the specified method.</span> |
| <span class="sd"> Methods currently supported: `pearson` (default), `spearman`.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> For Spearman, a rank correlation, we need to create an RDD[Double] for each column</span> |
| <span class="sd"> and sort it in order to retrieve the ranks and then join the columns back into an RDD[Vector],</span> |
| <span class="sd"> which is fairly costly. Cache the input Dataset before calling corr with `method = 'spearman'`</span> |
| <span class="sd"> to avoid recomputing the common lineage.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Correlation.corr"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Correlation.html#pyspark.ml.stat.Correlation.corr">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">corr</span><span class="p">(</span><span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">column</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">method</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"pearson"</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute the correlation matrix with specified method using dataset.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> A DataFrame.</span> |
| <span class="sd"> column : str</span> |
| <span class="sd"> The name of the column of vectors for which the correlation coefficient needs</span> |
| <span class="sd"> to be computed. This must be a column of the dataset, and it must contain</span> |
| <span class="sd"> Vector objects.</span> |
| <span class="sd"> method : str, optional</span> |
| <span class="sd"> String specifying the method to use for computing correlation.</span> |
| <span class="sd"> Supported: `pearson` (default), `spearman`.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> A DataFrame that contains the correlation matrix of the column of vectors. This</span> |
| <span class="sd"> DataFrame contains a single row and a single column of name `METHODNAME(COLUMN)`.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import DenseMatrix, Vectors</span> |
| <span class="sd"> >>> from pyspark.ml.stat import Correlation</span> |
| <span class="sd"> >>> dataset = [[Vectors.dense([1, 0, 0, -2])],</span> |
| <span class="sd"> ... [Vectors.dense([4, 5, 0, 3])],</span> |
| <span class="sd"> ... [Vectors.dense([6, 7, 0, 8])],</span> |
| <span class="sd"> ... [Vectors.dense([9, 0, 0, 1])]]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(dataset, ['features'])</span> |
| <span class="sd"> >>> pearsonCorr = Correlation.corr(dataset, 'features', 'pearson').collect()[0][0]</span> |
| <span class="sd"> >>> print(str(pearsonCorr).replace('nan', 'NaN'))</span> |
| <span class="sd"> DenseMatrix([[ 1. , 0.0556..., NaN, 0.4004...],</span> |
| <span class="sd"> [ 0.0556..., 1. , NaN, 0.9135...],</span> |
| <span class="sd"> [ NaN, NaN, 1. , NaN],</span> |
| <span class="sd"> [ 0.4004..., 0.9135..., NaN, 1. ]])</span> |
| <span class="sd"> >>> spearmanCorr = Correlation.corr(dataset, 'features', method='spearman').collect()[0][0]</span> |
| <span class="sd"> >>> print(str(spearmanCorr).replace('nan', 'NaN'))</span> |
| <span class="sd"> DenseMatrix([[ 1. , 0.1054..., NaN, 0.4 ],</span> |
| <span class="sd"> [ 0.1054..., 1. , NaN, 0.9486... ],</span> |
| <span class="sd"> [ NaN, NaN, 1. , NaN],</span> |
| <span class="sd"> [ 0.4 , 0.9486... , NaN, 1. ]])</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark.core.context</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> |
| <span class="k">assert</span> <span class="n">sc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">javaCorrObj</span> <span class="o">=</span> <span class="n">_jvm</span><span class="p">()</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">ml</span><span class="o">.</span><span class="n">stat</span><span class="o">.</span><span class="n">Correlation</span> |
| <span class="n">args</span> <span class="o">=</span> <span class="p">[</span><span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">arg</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">column</span><span class="p">,</span> <span class="n">method</span><span class="p">)]</span> |
| <span class="k">return</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">javaCorrObj</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="KolmogorovSmirnovTest"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.KolmogorovSmirnovTest.html#pyspark.ml.stat.KolmogorovSmirnovTest">[docs]</a><span class="k">class</span> <span class="nc">KolmogorovSmirnovTest</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Conduct the two-sided Kolmogorov Smirnov (KS) test for data sampled from a continuous</span> |
| <span class="sd"> distribution.</span> |
| |
| <span class="sd"> By comparing the largest difference between the empirical cumulative</span> |
| <span class="sd"> distribution of the sample data and the theoretical distribution we can provide a test for the</span> |
| <span class="sd"> the null hypothesis that the sample data comes from that theoretical distribution.</span> |
| |
| <span class="sd"> .. versionadded:: 2.4.0</span> |
| |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="KolmogorovSmirnovTest.test"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.KolmogorovSmirnovTest.html#pyspark.ml.stat.KolmogorovSmirnovTest.test">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">test</span><span class="p">(</span><span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">sampleCol</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">distName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="n">params</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Conduct a one-sample, two-sided Kolmogorov-Smirnov test for probability distribution</span> |
| <span class="sd"> equality. Currently supports the normal distribution, taking as parameters the mean and</span> |
| <span class="sd"> standard deviation.</span> |
| |
| <span class="sd"> .. versionadded:: 2.4.0</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 or a DataFrame containing the sample of data to test.</span> |
| <span class="sd"> sampleCol : str</span> |
| <span class="sd"> Name of sample column in dataset, of any numerical type.</span> |
| <span class="sd"> distName : str</span> |
| <span class="sd"> a `string` name for a theoretical distribution, currently only support "norm".</span> |
| <span class="sd"> params : float</span> |
| <span class="sd"> a list of `float` values specifying the parameters to be used for the theoretical</span> |
| <span class="sd"> distribution. For "norm" distribution, the parameters includes mean and variance.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> A DataFrame that contains the Kolmogorov-Smirnov test result for the input sampled data.</span> |
| <span class="sd"> This DataFrame will contain a single Row with the following fields:</span> |
| |
| <span class="sd"> - `pValue: Double`</span> |
| <span class="sd"> - `statistic: Double`</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.stat import KolmogorovSmirnovTest</span> |
| <span class="sd"> >>> dataset = [[-1.0], [0.0], [1.0]]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(dataset, ['sample'])</span> |
| <span class="sd"> >>> ksResult = KolmogorovSmirnovTest.test(dataset, 'sample', 'norm', 0.0, 1.0).first()</span> |
| <span class="sd"> >>> round(ksResult.pValue, 3)</span> |
| <span class="sd"> 1.0</span> |
| <span class="sd"> >>> round(ksResult.statistic, 3)</span> |
| <span class="sd"> 0.175</span> |
| <span class="sd"> >>> dataset = [[2.0], [3.0], [4.0]]</span> |
| <span class="sd"> >>> dataset = spark.createDataFrame(dataset, ['sample'])</span> |
| <span class="sd"> >>> ksResult = KolmogorovSmirnovTest.test(dataset, 'sample', 'norm', 3.0, 1.0).first()</span> |
| <span class="sd"> >>> round(ksResult.pValue, 3)</span> |
| <span class="sd"> 1.0</span> |
| <span class="sd"> >>> round(ksResult.statistic, 3)</span> |
| <span class="sd"> 0.175</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark.core.context</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> |
| <span class="k">assert</span> <span class="n">sc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">javaTestObj</span> <span class="o">=</span> <span class="n">_jvm</span><span class="p">()</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">ml</span><span class="o">.</span><span class="n">stat</span><span class="o">.</span><span class="n">KolmogorovSmirnovTest</span> |
| <span class="n">dataset</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">dataset</span><span class="p">)</span> |
| <span class="n">params</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">param</span><span class="p">)</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">params</span><span class="p">]</span> <span class="c1"># type: ignore[assignment]</span> |
| <span class="k">return</span> <span class="n">_java2py</span><span class="p">(</span> |
| <span class="n">sc</span><span class="p">,</span> <span class="n">javaTestObj</span><span class="o">.</span><span class="n">test</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">sampleCol</span><span class="p">,</span> <span class="n">distName</span><span class="p">,</span> <span class="n">_jvm</span><span class="p">()</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toSeq</span><span class="p">(</span><span class="n">params</span><span class="p">))</span> |
| <span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Summarizer"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer">[docs]</a><span class="k">class</span> <span class="nc">Summarizer</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Tools for vectorized statistics on MLlib Vectors.</span> |
| <span class="sd"> The methods in this package provide various statistics for Vectors contained inside DataFrames.</span> |
| <span class="sd"> This class lets users pick the statistics they would like to extract for a given column.</span> |
| |
| <span class="sd"> .. versionadded:: 2.4.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.stat import Summarizer</span> |
| <span class="sd"> >>> from pyspark.sql import Row</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import Vectors</span> |
| <span class="sd"> >>> summarizer = Summarizer.metrics("mean", "count")</span> |
| <span class="sd"> >>> df = sc.parallelize([Row(weight=1.0, features=Vectors.dense(1.0, 1.0, 1.0)),</span> |
| <span class="sd"> ... Row(weight=0.0, features=Vectors.dense(1.0, 2.0, 3.0))]).toDF()</span> |
| <span class="sd"> >>> df.select(summarizer.summary(df.features, df.weight)).show(truncate=False)</span> |
| <span class="sd"> +-----------------------------------+</span> |
| <span class="sd"> |aggregate_metrics(features, weight)|</span> |
| <span class="sd"> +-----------------------------------+</span> |
| <span class="sd"> |{[1.0,1.0,1.0], 1} |</span> |
| <span class="sd"> +-----------------------------------+</span> |
| <span class="sd"> >>> df.select(summarizer.summary(df.features)).show(truncate=False)</span> |
| <span class="sd"> +--------------------------------+</span> |
| <span class="sd"> |aggregate_metrics(features, 1.0)|</span> |
| <span class="sd"> +--------------------------------+</span> |
| <span class="sd"> |{[1.0,1.5,2.0], 2} |</span> |
| <span class="sd"> +--------------------------------+</span> |
| <span class="sd"> >>> df.select(Summarizer.mean(df.features, df.weight)).show(truncate=False)</span> |
| <span class="sd"> +--------------+</span> |
| <span class="sd"> |mean(features)|</span> |
| <span class="sd"> +--------------+</span> |
| <span class="sd"> |[1.0,1.0,1.0] |</span> |
| <span class="sd"> +--------------+</span> |
| <span class="sd"> >>> df.select(Summarizer.mean(df.features)).show(truncate=False)</span> |
| <span class="sd"> +--------------+</span> |
| <span class="sd"> |mean(features)|</span> |
| <span class="sd"> +--------------+</span> |
| <span class="sd"> |[1.0,1.5,2.0] |</span> |
| <span class="sd"> +--------------+</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Summarizer.mean"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.mean">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">mean</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of mean summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"mean"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.sum"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.sum">[docs]</a> <span class="nd">@staticmethod</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">sum</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of sum summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"sum"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.variance"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.variance">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">variance</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of variance summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"variance"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.std"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.std">[docs]</a> <span class="nd">@staticmethod</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">std</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of std summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"std"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.count"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.count">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">count</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of count summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"count"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.numNonZeros"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.numNonZeros">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">numNonZeros</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of numNonZero summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"numNonZeros"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.max"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.max">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">max</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of max summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"max"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.min"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.min">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">min</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of min summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"min"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.normL1"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.normL1">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">normL1</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of normL1 summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"normL1"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Summarizer.normL2"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.normL2">[docs]</a> <span class="nd">@staticmethod</span> |
| <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">normL2</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> return a column of normL2 summary</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">"normL2"</span><span class="p">)</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_check_param</span><span class="p">(</span><span class="n">featuresCol</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">])</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Column</span><span class="p">,</span> <span class="n">Column</span><span class="p">]:</span> |
| <span class="k">if</span> <span class="n">weightCol</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">weightCol</span> <span class="o">=</span> <span class="n">lit</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">featuresCol</span><span class="p">,</span> <span class="n">Column</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">weightCol</span><span class="p">,</span> <span class="n">Column</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"featureCol and weightCol should be a Column"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">],</span> <span class="n">metric</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span> <span class="o">=</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_check_param</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">Column</span><span class="p">(</span> |
| <span class="n">JavaWrapper</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.stat.Summarizer."</span> <span class="o">+</span> <span class="n">metric</span><span class="p">,</span> <span class="n">col</span><span class="o">.</span><span class="n">_jc</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">.</span><span class="n">_jc</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="Summarizer.metrics"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.metrics">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">metrics</span><span class="p">(</span><span class="o">*</span><span class="n">metrics</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"SummaryBuilder"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Given a list of metrics, provides a builder that it turns computes metrics from a column.</span> |
| |
| <span class="sd"> See the documentation of :py:class:`Summarizer` for an example.</span> |
| |
| <span class="sd"> The following metrics are accepted (case sensitive):</span> |
| <span class="sd"> - mean: a vector that contains the coefficient-wise mean.</span> |
| <span class="sd"> - sum: a vector that contains the coefficient-wise sum.</span> |
| <span class="sd"> - variance: a vector that contains the coefficient-wise variance.</span> |
| <span class="sd"> - std: a vector that contains the coefficient-wise standard deviation.</span> |
| <span class="sd"> - count: the count of all vectors seen.</span> |
| <span class="sd"> - numNonzeros: a vector with the number of non-zeros for each coefficients</span> |
| <span class="sd"> - max: the maximum for each coefficient.</span> |
| <span class="sd"> - min: the minimum for each coefficient.</span> |
| <span class="sd"> - normL2: the Euclidean norm for each coefficient.</span> |
| <span class="sd"> - normL1: the L1 norm of each coefficient (sum of the absolute values).</span> |
| |
| <span class="sd"> .. versionadded:: 2.4.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Currently, the performance of this interface is about 2x~3x slower than using the RDD</span> |
| <span class="sd"> interface.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> metrics : str</span> |
| <span class="sd"> metrics that can be provided.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.ml.stat.SummaryBuilder`</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark.core.context</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.classic.column</span> <span class="kn">import</span> <span class="n">_to_seq</span> |
| |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> |
| <span class="k">assert</span> <span class="n">sc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">js</span> <span class="o">=</span> <span class="n">JavaWrapper</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span> |
| <span class="s2">"org.apache.spark.ml.stat.Summarizer.metrics"</span><span class="p">,</span> <span class="n">_to_seq</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">metrics</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">SummaryBuilder</span><span class="p">(</span><span class="n">js</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="SummaryBuilder"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.SummaryBuilder.html#pyspark.ml.stat.SummaryBuilder">[docs]</a><span class="k">class</span> <span class="nc">SummaryBuilder</span><span class="p">(</span><span class="n">JavaWrapper</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A builder object that provides summary statistics about a given column.</span> |
| |
| <span class="sd"> Users should not directly create such builders, but instead use one of the methods in</span> |
| <span class="sd"> :py:class:`pyspark.ml.stat.Summarizer`</span> |
| |
| <span class="sd"> .. versionadded:: 2.4.0</span> |
| |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jSummaryBuilder</span><span class="p">:</span> <span class="s2">"JavaObject"</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SummaryBuilder</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">jSummaryBuilder</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="SummaryBuilder.summary"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.SummaryBuilder.html#pyspark.ml.stat.SummaryBuilder.summary">[docs]</a> <span class="k">def</span> <span class="nf">summary</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns an aggregate object that contains the summary of the column with the requested</span> |
| <span class="sd"> metrics.</span> |
| |
| <span class="sd"> .. versionadded:: 2.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> featuresCol : str</span> |
| <span class="sd"> a column that contains features Vector object.</span> |
| <span class="sd"> weightCol : str, optional</span> |
| <span class="sd"> a column that contains weight value. Default weight is 1.0.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.Column`</span> |
| <span class="sd"> an aggregate column that contains the statistics. The exact content of this</span> |
| <span class="sd"> structure is determined during the creation of the builder.</span> |
| <span class="sd"> """</span> |
| <span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span> <span class="o">=</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_check_param</span><span class="p">(</span><span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="k">return</span> <span class="n">Column</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="n">summary</span><span class="p">(</span><span class="n">featuresCol</span><span class="o">.</span><span class="n">_jc</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">.</span><span class="n">_jc</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="MultivariateGaussian"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.MultivariateGaussian.html#pyspark.ml.stat.MultivariateGaussian">[docs]</a><span class="k">class</span> <span class="nc">MultivariateGaussian</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Represents a (mean, cov) tuple</span> |
| |
| <span class="sd"> .. versionadded:: 3.0.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.linalg import DenseMatrix, Vectors</span> |
| <span class="sd"> >>> from pyspark.ml.stat import MultivariateGaussian</span> |
| <span class="sd"> >>> m = MultivariateGaussian(Vectors.dense([11,12]), DenseMatrix(2, 2, (1.0, 3.0, 5.0, 2.0)))</span> |
| <span class="sd"> >>> (m.mean, m.cov.toArray())</span> |
| <span class="sd"> (DenseVector([11.0, 12.0]), array([[ 1., 5.],</span> |
| <span class="sd"> [ 3., 2.]]))</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mean</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">cov</span><span class="p">:</span> <span class="n">Matrix</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mean</span> <span class="o">=</span> <span class="n">mean</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cov</span> <span class="o">=</span> <span class="n">cov</span></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">numpy</span> |
| <span class="kn">import</span> <span class="nn">pyspark.ml.stat</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</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">ml</span><span class="o">.</span><span class="n">stat</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.stat tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</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">sc</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"spark"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span> |
| |
| <span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</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="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">NORMALIZE_WHITESPACE</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> |
| </pre></div> |
| |
| </article> |
| |
| |
| |
| <footer class="bd-footer-article"> |
| |
| <div class="footer-article-items footer-article__inner"> |
| |
| <div class="footer-article-item"><!-- Previous / next buttons --> |
| <div class="prev-next-area"> |
| </div></div> |
| |
| </div> |
| |
| </footer> |
| |
| </div> |
| |
| |
| |
| |
| </div> |
| <footer class="bd-footer-content"> |
| |
| </footer> |
| |
| </main> |
| </div> |
| </div> |
| |
| <!-- Scripts loaded after <body> so the DOM is not blocked --> |
| <script src="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52"></script> |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52"></script> |
| |
| <footer class="bd-footer"> |
| <div class="bd-footer__inner bd-page-width"> |
| |
| <div class="footer-items__start"> |
| |
| <div class="footer-item"><p class="copyright"> |
| Copyright @ 2024 The Apache Software Foundation, Licensed under the <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache License, Version 2.0</a>. |
| </p></div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 4.5.0. |
| <br/> |
| </p> |
| </div> |
| |
| </div> |
| |
| |
| <div class="footer-items__end"> |
| |
| <div class="footer-item"><p class="theme-version"> |
| Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.13.3. |
| </p></div> |
| |
| </div> |
| |
| </div> |
| |
| </footer> |
| </body> |
| </html> |