| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>pyspark.ml.base — PySpark 4.0.0-preview2 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/base';</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/ml/base.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="https://spark.apache.org/images/spark-logo.png" class="logo__image only-light" alt="Logo image"/> |
| <script>document.write(`<img src="https://spark.apache.org/images/spark-logo-rev.svg" 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-preview2 |
| <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/base.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-preview2 |
| <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/base.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.base</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <h1>Source code for pyspark.ml.base</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">abc</span> <span class="kn">import</span> <span class="n">ABCMeta</span><span class="p">,</span> <span class="n">abstractmethod</span> |
| <span class="kn">import</span> <span class="nn">copy</span> |
| <span class="kn">import</span> <span class="nn">threading</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">Any</span><span class="p">,</span> |
| <span class="n">Callable</span><span class="p">,</span> |
| <span class="n">Generic</span><span class="p">,</span> |
| <span class="n">Iterator</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">Sequence</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="p">,</span> |
| <span class="n">cast</span><span class="p">,</span> |
| <span class="n">overload</span><span class="p">,</span> |
| <span class="n">TYPE_CHECKING</span><span class="p">,</span> |
| <span class="p">)</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.param</span> <span class="kn">import</span> <span class="n">P</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.common</span> <span class="kn">import</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.param.shared</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">HasInputCol</span><span class="p">,</span> |
| <span class="n">HasOutputCol</span><span class="p">,</span> |
| <span class="n">HasLabelCol</span><span class="p">,</span> |
| <span class="n">HasFeaturesCol</span><span class="p">,</span> |
| <span class="n">HasPredictionCol</span><span class="p">,</span> |
| <span class="n">Params</span><span class="p">,</span> |
| <span class="p">)</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">udf</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">DataType</span><span class="p">,</span> <span class="n">StructField</span><span class="p">,</span> <span class="n">StructType</span> |
| |
| <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml._typing</span> <span class="kn">import</span> <span class="n">ParamMap</span> |
| |
| <span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"T"</span><span class="p">)</span> |
| <span class="n">M</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"M"</span><span class="p">,</span> <span class="n">bound</span><span class="o">=</span><span class="s2">"Transformer"</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_FitMultipleIterator</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">M</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Used by default implementation of Estimator.fitMultiple to produce models in a thread safe</span> |
| <span class="sd"> iterator. This class handles the simple case of fitMultiple where each param map should be</span> |
| <span class="sd"> fit independently.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> fitSingleModel : function</span> |
| <span class="sd"> Callable[[int], Transformer] which fits an estimator to a dataset.</span> |
| <span class="sd"> `fitSingleModel` may be called up to `numModels` times, with a unique index each time.</span> |
| <span class="sd"> Each call to `fitSingleModel` with an index should return the Model associated with</span> |
| <span class="sd"> that index.</span> |
| <span class="sd"> numModel : int</span> |
| <span class="sd"> Number of models this iterator should produce.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> See :py:meth:`Estimator.fitMultiple` for more info.</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">fitSingleModel</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="nb">int</span><span class="p">],</span> <span class="n">M</span><span class="p">],</span> <span class="n">numModels</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">""" """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fitSingleModel</span> <span class="o">=</span> <span class="n">fitSingleModel</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numModel</span> <span class="o">=</span> <span class="n">numModels</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">counter</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">lock</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">Lock</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="fm">__iter__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">M</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="bp">self</span> |
| |
| <span class="k">def</span> <span class="fm">__next__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">M</span><span class="p">]:</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">lock</span><span class="p">:</span> |
| <span class="n">index</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">counter</span> |
| <span class="k">if</span> <span class="n">index</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">numModel</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">StopIteration</span><span class="p">(</span><span class="s2">"No models remaining."</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">counter</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">index</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fitSingleModel</span><span class="p">(</span><span class="n">index</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">next</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">M</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""For python2 compatibility."""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="fm">__next__</span><span class="p">()</span> |
| |
| |
| <div class="viewcode-block" id="Estimator"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Estimator.html#pyspark.ml.Estimator">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">Estimator</span><span class="p">(</span><span class="n">Params</span><span class="p">,</span> <span class="n">Generic</span><span class="p">[</span><span class="n">M</span><span class="p">],</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Abstract class for estimators that fit models to data.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">_fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-></span> <span class="n">M</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Fits a model to the input dataset. This is called by the default implementation of fit.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :class:`Transformer`</span> |
| <span class="sd"> fitted model</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="Estimator.fitMultiple"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Estimator.html#pyspark.ml.Estimator.fitMultiple">[docs]</a> <span class="k">def</span> <span class="nf">fitMultiple</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">paramMaps</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">M</span><span class="p">]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Fits a model to the input dataset for each param map in `paramMaps`.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset.</span> |
| <span class="sd"> paramMaps : :py:class:`collections.abc.Sequence`</span> |
| <span class="sd"> A Sequence of param maps.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`_FitMultipleIterator`</span> |
| <span class="sd"> A thread safe iterable which contains one model for each param map. Each</span> |
| <span class="sd"> call to `next(modelIterator)` will return `(index, model)` where model was fit</span> |
| <span class="sd"> using `paramMaps[index]`. `index` values may not be sequential.</span> |
| <span class="sd"> """</span> |
| <span class="n">estimator</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">fitSingleModel</span><span class="p">(</span><span class="n">index</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">M</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">estimator</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">paramMaps</span><span class="p">[</span><span class="n">index</span><span class="p">])</span> |
| |
| <span class="k">return</span> <span class="n">_FitMultipleIterator</span><span class="p">(</span><span class="n">fitSingleModel</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">paramMaps</span><span class="p">))</span></div> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">]</span> <span class="o">=</span> <span class="o">...</span><span class="p">)</span> <span class="o">-></span> <span class="n">M</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">M</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="Estimator.fit"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Estimator.html#pyspark.ml.Estimator.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> |
| <span class="n">params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="s2">"ParamMap"</span><span class="p">]]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">M</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="n">M</span><span class="p">]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Fits a model to the input dataset with optional parameters.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset.</span> |
| <span class="sd"> params : dict or list or tuple, optional</span> |
| <span class="sd"> an optional param map that overrides embedded params. If a list/tuple of</span> |
| <span class="sd"> param maps is given, this calls fit on each param map and returns a list of</span> |
| <span class="sd"> models.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`Transformer` or a list of :py:class:`Transformer`</span> |
| <span class="sd"> fitted model(s)</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">params</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">params</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="n">models</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">M</span><span class="p">]]</span> <span class="o">=</span> <span class="p">[</span><span class="kc">None</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">params</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">index</span><span class="p">,</span> <span class="n">model</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">fitMultiple</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span> |
| <span class="n">models</span><span class="p">[</span><span class="n">index</span><span class="p">]</span> <span class="o">=</span> <span class="n">model</span> |
| <span class="k">return</span> <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">M</span><span class="p">],</span> <span class="n">models</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">params</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">params</span><span class="p">)</span><span class="o">.</span><span class="n">_fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"Params must be either a param map or a list/tuple of param maps, "</span> |
| <span class="s2">"but got </span><span class="si">%s</span><span class="s2">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">)</span> |
| <span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Transformer"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Transformer.html#pyspark.ml.Transformer">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">Transformer</span><span class="p">(</span><span class="n">Params</span><span class="p">,</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Abstract class for transformers that transform one dataset into another.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</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"> Transforms the input dataset.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> transformed dataset</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="Transformer.transform"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Transformer.html#pyspark.ml.Transformer.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"ParamMap"</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">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Transforms the input dataset with optional parameters.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> input dataset</span> |
| <span class="sd"> params : dict, optional</span> |
| <span class="sd"> an optional param map that overrides embedded params.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> transformed dataset</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">params</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">params</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">params</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">params</span><span class="p">)</span><span class="o">.</span><span class="n">_transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Params must be a param map but got </span><span class="si">%s</span><span class="s2">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Model"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Model.html#pyspark.ml.Model">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">Model</span><span class="p">(</span><span class="n">Transformer</span><span class="p">,</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Abstract class for models that are fitted by estimators.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">pass</span></div> |
| |
| |
| <div class="viewcode-block" id="UnaryTransformer"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">UnaryTransformer</span><span class="p">(</span><span class="n">HasInputCol</span><span class="p">,</span> <span class="n">HasOutputCol</span><span class="p">,</span> <span class="n">Transformer</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Abstract class for transformers that take one input column, apply transformation,</span> |
| <span class="sd"> and output the result as a new column.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="UnaryTransformer.setInputCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer.setInputCol">[docs]</a> <span class="k">def</span> <span class="nf">setInputCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`inputCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">inputCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="UnaryTransformer.setOutputCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer.setOutputCol">[docs]</a> <span class="k">def</span> <span class="nf">setOutputCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`outputCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">outputCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="UnaryTransformer.createTransformFunc"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer.createTransformFunc">[docs]</a> <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">createTransformFunc</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Callable</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="n">Any</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Creates the transform function using the given param map. The input param map already takes</span> |
| <span class="sd"> account of the embedded param map. So the param values should be determined</span> |
| <span class="sd"> solely by the input param map.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="UnaryTransformer.outputDataType"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer.outputDataType">[docs]</a> <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">outputDataType</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataType</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the data type of the output column.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="UnaryTransformer.validateInputType"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer.validateInputType">[docs]</a> <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">validateInputType</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">inputType</span><span class="p">:</span> <span class="n">DataType</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"> Validates the input type. Throw an exception if it is invalid.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="UnaryTransformer.transformSchema"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.UnaryTransformer.html#pyspark.ml.UnaryTransformer.transformSchema">[docs]</a> <span class="k">def</span> <span class="nf">transformSchema</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">:</span> <span class="n">StructType</span><span class="p">)</span> <span class="o">-></span> <span class="n">StructType</span><span class="p">:</span> |
| <span class="n">inputType</span> <span class="o">=</span> <span class="n">schema</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">getInputCol</span><span class="p">()]</span><span class="o">.</span><span class="n">dataType</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">validateInputType</span><span class="p">(</span><span class="n">inputType</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOutputCol</span><span class="p">()</span> <span class="ow">in</span> <span class="n">schema</span><span class="o">.</span><span class="n">names</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Output column </span><span class="si">%s</span><span class="s2"> already exists."</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOutputCol</span><span class="p">())</span> |
| <span class="n">outputFields</span> <span class="o">=</span> <span class="n">copy</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">schema</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> |
| <span class="n">outputFields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">StructField</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">getOutputCol</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">outputDataType</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="k">return</span> <span class="n">StructType</span><span class="p">(</span><span class="n">outputFields</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">transformSchema</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span> |
| <span class="n">transformUDF</span> <span class="o">=</span> <span class="n">udf</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">createTransformFunc</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">outputDataType</span><span class="p">())</span> |
| <span class="n">transformedDataset</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">withColumn</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">getOutputCol</span><span class="p">(),</span> <span class="n">transformUDF</span><span class="p">(</span><span class="n">dataset</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">getInputCol</span><span class="p">()])</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">transformedDataset</span></div> |
| |
| |
| <span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">_PredictorParams</span><span class="p">(</span><span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Params for :py:class:`Predictor` and :py:class:`PredictorModel`.</span> |
| |
| <span class="sd"> .. versionadded:: 3.0.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">pass</span> |
| |
| |
| <div class="viewcode-block" id="Predictor"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Predictor.html#pyspark.ml.Predictor">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">Predictor</span><span class="p">(</span><span class="n">Estimator</span><span class="p">[</span><span class="n">M</span><span class="p">],</span> <span class="n">_PredictorParams</span><span class="p">,</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Estimator for prediction tasks (regression and classification).</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Predictor.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Predictor.html#pyspark.ml.Predictor.setLabelCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`labelCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Predictor.setFeaturesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Predictor.html#pyspark.ml.Predictor.setFeaturesCol">[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">setFeaturesCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`featuresCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">featuresCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Predictor.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.Predictor.html#pyspark.ml.Predictor.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="PredictionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.PredictionModel.html#pyspark.ml.PredictionModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">PredictionModel</span><span class="p">(</span><span class="n">Model</span><span class="p">,</span> <span class="n">_PredictorParams</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="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Model for prediction tasks (regression and classification).</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="PredictionModel.setFeaturesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.PredictionModel.html#pyspark.ml.PredictionModel.setFeaturesCol">[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">setFeaturesCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`featuresCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">featuresCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="PredictionModel.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.PredictionModel.html#pyspark.ml.PredictionModel.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="n">P</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">P</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.1.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">numFeatures</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the number of features the model was trained on. If unknown, returns -1</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="PredictionModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.PredictionModel.html#pyspark.ml.PredictionModel.predict">[docs]</a> <span class="nd">@abstractmethod</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">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="n">T</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"> Predict label for the given features.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span></div></div> |
| </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> |
