Google Git
Sign in
apache / spark-website / f7fc275b5cd176e4d65d70f1b933e7fcce370584 / . / site / docs / 4.0.0-preview1 / api / python / _modules / pyspark / ml / regression.html
blob: 8f9a4485114efb785a28c98dba07ff400ccd2bcf [file] [log] [blame]
<!DOCTYPE html>
<html >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>pyspark.ml.regression &#8212; 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/regression';</script>
<link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/ml/regression.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/regression.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/regression.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.regression</li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article" role="main">
<h1>Source code for pyspark.ml.regression</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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">Any</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Generic</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">TypeVar</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span>
<span class="kn">from</span> <span class="nn">abc</span> <span class="kn">import</span> <span class="n">ABCMeta</span>
<span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">keyword_only</span><span class="p">,</span> <span class="n">since</span>
<span class="kn">from</span> <span class="nn">pyspark.ml</span> <span class="kn">import</span> <span class="n">Predictor</span><span class="p">,</span> <span class="n">PredictionModel</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.base</span> <span class="kn">import</span> <span class="n">_PredictorParams</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">HasFeaturesCol</span><span class="p">,</span>
<span class="n">HasLabelCol</span><span class="p">,</span>
<span class="n">HasPredictionCol</span><span class="p">,</span>
<span class="n">HasWeightCol</span><span class="p">,</span>
<span class="n">Param</span><span class="p">,</span>
<span class="n">Params</span><span class="p">,</span>
<span class="n">TypeConverters</span><span class="p">,</span>
<span class="n">HasMaxIter</span><span class="p">,</span>
<span class="n">HasTol</span><span class="p">,</span>
<span class="n">HasFitIntercept</span><span class="p">,</span>
<span class="n">HasAggregationDepth</span><span class="p">,</span>
<span class="n">HasMaxBlockSizeInMB</span><span class="p">,</span>
<span class="n">HasRegParam</span><span class="p">,</span>
<span class="n">HasSolver</span><span class="p">,</span>
<span class="n">HasStepSize</span><span class="p">,</span>
<span class="n">HasSeed</span><span class="p">,</span>
<span class="n">HasElasticNetParam</span><span class="p">,</span>
<span class="n">HasStandardization</span><span class="p">,</span>
<span class="n">HasLoss</span><span class="p">,</span>
<span class="n">HasVarianceCol</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.tree</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">_DecisionTreeModel</span><span class="p">,</span>
<span class="n">_DecisionTreeParams</span><span class="p">,</span>
<span class="n">_TreeEnsembleModel</span><span class="p">,</span>
<span class="n">_RandomForestParams</span><span class="p">,</span>
<span class="n">_GBTParams</span><span class="p">,</span>
<span class="n">_TreeRegressorParams</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.base</span> <span class="kn">import</span> <span class="n">Transformer</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="kn">import</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">Matrix</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.util</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">,</span>
<span class="n">HasTrainingSummary</span><span class="p">,</span>
<span class="n">GeneralJavaMLWritable</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">JavaEstimator</span><span class="p">,</span>
<span class="n">JavaModel</span><span class="p">,</span>
<span class="n">JavaPredictor</span><span class="p">,</span>
<span class="n">JavaPredictionModel</span><span class="p">,</span>
<span class="n">JavaTransformer</span><span class="p">,</span>
<span class="n">JavaWrapper</span><span class="p">,</span>
<span class="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.sql</span> <span class="kn">import</span> <span class="n">DataFrame</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>
<span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">&quot;T&quot;</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">&quot;M&quot;</span><span class="p">,</span> <span class="n">bound</span><span class="o">=</span><span class="n">Transformer</span><span class="p">)</span>
<span class="n">JM</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">&quot;JM&quot;</span><span class="p">,</span> <span class="n">bound</span><span class="o">=</span><span class="n">JavaTransformer</span><span class="p">)</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">,</span>
<span class="s2">&quot;AFTSurvivalRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">,</span>
<span class="s2">&quot;DecisionTreeRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;GBTRegressor&quot;</span><span class="p">,</span>
<span class="s2">&quot;GBTRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">,</span>
<span class="s2">&quot;GeneralizedLinearRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;GeneralizedLinearRegressionSummary&quot;</span><span class="p">,</span>
<span class="s2">&quot;GeneralizedLinearRegressionTrainingSummary&quot;</span><span class="p">,</span>
<span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">,</span>
<span class="s2">&quot;IsotonicRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;LinearRegression&quot;</span><span class="p">,</span>
<span class="s2">&quot;LinearRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;LinearRegressionSummary&quot;</span><span class="p">,</span>
<span class="s2">&quot;LinearRegressionTrainingSummary&quot;</span><span class="p">,</span>
<span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">,</span>
<span class="s2">&quot;RandomForestRegressionModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;FMRegressor&quot;</span><span class="p">,</span>
<span class="s2">&quot;FMRegressionModel&quot;</span><span class="p">,</span>
<span class="p">]</span>
<span class="k">class</span> <span class="nc">Regressor</span><span class="p">(</span><span class="n">Predictor</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">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">&quot;&quot;&quot;</span>
<span class="sd"> Regressor for regression tasks.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">pass</span>
<span class="k">class</span> <span class="nc">RegressionModel</span><span class="p">(</span><span class="n">PredictionModel</span><span class="p">[</span><span class="n">T</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">&quot;&quot;&quot;</span>
<span class="sd"> Model produced by a ``Regressor``.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">pass</span>
<span class="k">class</span> <span class="nc">_JavaRegressor</span><span class="p">(</span><span class="n">Regressor</span><span class="p">,</span> <span class="n">JavaPredictor</span><span class="p">[</span><span class="n">JM</span><span class="p">],</span> <span class="n">Generic</span><span class="p">[</span><span class="n">JM</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">&quot;&quot;&quot;</span>
<span class="sd"> Java Regressor for regression tasks.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">pass</span>
<span class="k">class</span> <span class="nc">_JavaRegressionModel</span><span class="p">(</span><span class="n">RegressionModel</span><span class="p">,</span> <span class="n">JavaPredictionModel</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">&quot;&quot;&quot;</span>
<span class="sd"> Java Model produced by a ``_JavaRegressor``.</span>
<span class="sd"> To be mixed in with :class:`pyspark.ml.JavaModel`</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">pass</span>
<span class="k">class</span> <span class="nc">_LinearRegressionParams</span><span class="p">(</span>
<span class="n">_PredictorParams</span><span class="p">,</span>
<span class="n">HasRegParam</span><span class="p">,</span>
<span class="n">HasElasticNetParam</span><span class="p">,</span>
<span class="n">HasMaxIter</span><span class="p">,</span>
<span class="n">HasTol</span><span class="p">,</span>
<span class="n">HasFitIntercept</span><span class="p">,</span>
<span class="n">HasStandardization</span><span class="p">,</span>
<span class="n">HasWeightCol</span><span class="p">,</span>
<span class="n">HasSolver</span><span class="p">,</span>
<span class="n">HasAggregationDepth</span><span class="p">,</span>
<span class="n">HasLoss</span><span class="p">,</span>
<span class="n">HasMaxBlockSizeInMB</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`LinearRegression` and :py:class:`LinearRegressionModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">solver</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;solver&quot;</span><span class="p">,</span>
<span class="s2">&quot;The solver algorithm for optimization. Supported &quot;</span> <span class="o">+</span> <span class="s2">&quot;options: auto, normal, l-bfgs.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">loss</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;loss&quot;</span><span class="p">,</span>
<span class="s2">&quot;The loss function to be optimized. Supported &quot;</span> <span class="o">+</span> <span class="s2">&quot;options: squaredError, huber.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">epsilon</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;epsilon&quot;</span><span class="p">,</span>
<span class="s2">&quot;The shape parameter to control the amount of &quot;</span>
<span class="o">+</span> <span class="s2">&quot;robustness. Must be &gt; 1.0. Only valid when loss is huber&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_LinearRegressionParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span>
<span class="n">regParam</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">tol</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span>
<span class="n">loss</span><span class="o">=</span><span class="s2">&quot;squaredError&quot;</span><span class="p">,</span>
<span class="n">epsilon</span><span class="o">=</span><span class="mf">1.35</span><span class="p">,</span>
<span class="n">maxBlockSizeInMB</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.3.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getEpsilon</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of epsilon or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">epsilon</span><span class="p">)</span>
<div class="viewcode-block" id="LinearRegression"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">LinearRegression</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;LinearRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_LinearRegressionParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;LinearRegression&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Linear regression.</span>
<span class="sd"> The learning objective is to minimize the specified loss function, with regularization.</span>
<span class="sd"> This supports two kinds of loss:</span>
<span class="sd"> * squaredError (a.k.a squared loss)</span>
<span class="sd"> * huber (a hybrid of squared error for relatively small errors and absolute error for \</span>
<span class="sd"> relatively large ones, and we estimate the scale parameter from training data)</span>
<span class="sd"> This supports multiple types of regularization:</span>
<span class="sd"> * none (a.k.a. ordinary least squares)</span>
<span class="sd"> * L2 (ridge regression)</span>
<span class="sd"> * L1 (Lasso)</span>
<span class="sd"> * L2 + L1 (elastic net)</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> Fitting with huber loss only supports none and L2 regularization.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, 2.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, 2.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;weight&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; lr = LinearRegression(regParam=0.0, solver=&quot;normal&quot;, weightCol=&quot;weight&quot;)</span>
<span class="sd"> &gt;&gt;&gt; lr.setMaxIter(5)</span>
<span class="sd"> LinearRegression...</span>
<span class="sd"> &gt;&gt;&gt; lr.getMaxIter()</span>
<span class="sd"> 5</span>
<span class="sd"> &gt;&gt;&gt; lr.setRegParam(0.1)</span>
<span class="sd"> LinearRegression...</span>
<span class="sd"> &gt;&gt;&gt; lr.getRegParam()</span>
<span class="sd"> 0.1</span>
<span class="sd"> &gt;&gt;&gt; lr.setRegParam(0.0)</span>
<span class="sd"> LinearRegression...</span>
<span class="sd"> &gt;&gt;&gt; model = lr.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.setFeaturesCol(&quot;features&quot;)</span>
<span class="sd"> LinearRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.setPredictionCol(&quot;newPrediction&quot;)</span>
<span class="sd"> LinearRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.getMaxIter()</span>
<span class="sd"> 5</span>
<span class="sd"> &gt;&gt;&gt; model.getMaxBlockSizeInMB()</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; abs(model.predict(test0.head().features) - (-1.0)) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; abs(model.transform(test0).head().newPrediction - (-1.0)) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; abs(model.coefficients[0] - 1.0) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; abs(model.intercept - 0.0) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; test1 = spark.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; abs(model.transform(test1).head().newPrediction - 1.0) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; lr.setParams(featuresCol=&quot;vector&quot;)</span>
<span class="sd"> LinearRegression...</span>
<span class="sd"> &gt;&gt;&gt; lr_path = temp_path + &quot;/lr&quot;</span>
<span class="sd"> &gt;&gt;&gt; lr.save(lr_path)</span>
<span class="sd"> &gt;&gt;&gt; lr2 = LinearRegression.load(lr_path)</span>
<span class="sd"> &gt;&gt;&gt; lr2.getMaxIter()</span>
<span class="sd"> 5</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/lr_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = LinearRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.coefficients[0] == model2.coefficients[0]</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.intercept == model2.intercept</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).take(1) == model2.transform(test0).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.numFeatures</span>
<span class="sd"> 1</span>
<span class="sd"> &gt;&gt;&gt; model.write().format(&quot;pmml&quot;).save(model_path + &quot;_2&quot;)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
<span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">elasticNetParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">standardization</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">solver</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;auto&quot;</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="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">loss</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;squaredError&quot;</span><span class="p">,</span>
<span class="n">epsilon</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.35</span><span class="p">,</span>
<span class="n">maxBlockSizeInMB</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxIter=100, regParam=0.0, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \</span>
<span class="sd"> standardization=True, solver=&quot;auto&quot;, weightCol=None, aggregationDepth=2, \</span>
<span class="sd"> loss=&quot;squaredError&quot;, epsilon=1.35, maxBlockSizeInMB=0.0)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">LinearRegression</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s2">&quot;org.apache.spark.ml.regression.LinearRegression&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span>
<span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="LinearRegression.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
<span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">elasticNetParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">standardization</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">solver</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;auto&quot;</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="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">loss</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;squaredError&quot;</span><span class="p">,</span>
<span class="n">epsilon</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.35</span><span class="p">,</span>
<span class="n">maxBlockSizeInMB</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxIter=100, regParam=0.0, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \</span>
<span class="sd"> standardization=True, solver=&quot;auto&quot;, weightCol=None, aggregationDepth=2, \</span>
<span class="sd"> loss=&quot;squaredError&quot;, epsilon=1.35, maxBlockSizeInMB=0.0)</span>
<span class="sd"> Sets params for linear regression.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">LinearRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="LinearRegression.setEpsilon"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setEpsilon">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.3.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setEpsilon</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`epsilon`.</span>
<span class="sd"> &quot;&quot;&quot;</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">epsilon</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setMaxIter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setMaxIter">[docs]</a> <span class="k">def</span> <span class="nf">setMaxIter</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxIter`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxIter</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setRegParam"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setRegParam">[docs]</a> <span class="k">def</span> <span class="nf">setRegParam</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`regParam`.</span>
<span class="sd"> &quot;&quot;&quot;</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">regParam</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setTol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setTol">[docs]</a> <span class="k">def</span> <span class="nf">setTol</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`tol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">tol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setElasticNetParam"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setElasticNetParam">[docs]</a> <span class="k">def</span> <span class="nf">setElasticNetParam</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`elasticNetParam`.</span>
<span class="sd"> &quot;&quot;&quot;</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">elasticNetParam</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setFitIntercept"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setFitIntercept">[docs]</a> <span class="k">def</span> <span class="nf">setFitIntercept</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`fitIntercept`.</span>
<span class="sd"> &quot;&quot;&quot;</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">fitIntercept</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setStandardization"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setStandardization">[docs]</a> <span class="k">def</span> <span class="nf">setStandardization</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`standardization`.</span>
<span class="sd"> &quot;&quot;&quot;</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">standardization</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setWeightCol">[docs]</a> <span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`weightCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setSolver"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setSolver">[docs]</a> <span class="k">def</span> <span class="nf">setSolver</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`solver`.</span>
<span class="sd"> &quot;&quot;&quot;</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">solver</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setAggregationDepth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setAggregationDepth">[docs]</a> <span class="k">def</span> <span class="nf">setAggregationDepth</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`aggregationDepth`.</span>
<span class="sd"> &quot;&quot;&quot;</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">aggregationDepth</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setLoss"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setLoss">[docs]</a> <span class="k">def</span> <span class="nf">setLoss</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`loss`.</span>
<span class="sd"> &quot;&quot;&quot;</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">lossType</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegression.setMaxBlockSizeInMB"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegression.html#pyspark.ml.regression.LinearRegression.setMaxBlockSizeInMB">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.1.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxBlockSizeInMB</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxBlockSizeInMB`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxBlockSizeInMB</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="LinearRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegressionModel.html#pyspark.ml.regression.LinearRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">LinearRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">,</span>
<span class="n">_LinearRegressionParams</span><span class="p">,</span>
<span class="n">GeneralJavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;LinearRegressionModel&quot;</span><span class="p">],</span>
<span class="n">HasTrainingSummary</span><span class="p">[</span><span class="s2">&quot;LinearRegressionSummary&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`LinearRegression`.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">coefficients</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model coefficients.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;coefficients&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">intercept</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;intercept&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.3.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">scale</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The value by which :math:`\|y - X&#39;w\|` is scaled down when loss is &quot;huber&quot;, otherwise 1.0.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;scale&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<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="o">-&gt;</span> <span class="s2">&quot;LinearRegressionTrainingSummary&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets summary (residuals, MSE, r-squared ) of model on</span>
<span class="sd"> training set. An exception is thrown if</span>
<span class="sd"> `trainingSummary is None`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hasSummary</span><span class="p">:</span>
<span class="k">return</span> <span class="n">LinearRegressionTrainingSummary</span><span class="p">(</span><span class="nb">super</span><span class="p">(</span><span class="n">LinearRegressionModel</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">summary</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
<span class="s2">&quot;No training summary available for this </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span>
<span class="p">)</span>
<div class="viewcode-block" id="LinearRegressionModel.evaluate"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegressionModel.html#pyspark.ml.regression.LinearRegressionModel.evaluate">[docs]</a> <span class="k">def</span> <span class="nf">evaluate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;LinearRegressionSummary&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Evaluates the model on a test dataset.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> Test dataset to evaluate model on, where dataset is an</span>
<span class="sd"> instance of :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">&quot;dataset must be a DataFrame but got </span><span class="si">%s</span><span class="s2">.&quot;</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">dataset</span><span class="p">))</span>
<span class="n">java_lr_summary</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;evaluate&quot;</span><span class="p">,</span> <span class="n">dataset</span><span class="p">)</span>
<span class="k">return</span> <span class="n">LinearRegressionSummary</span><span class="p">(</span><span class="n">java_lr_summary</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="LinearRegressionSummary"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegressionSummary.html#pyspark.ml.regression.LinearRegressionSummary">[docs]</a><span class="k">class</span> <span class="nc">LinearRegressionSummary</span><span class="p">(</span><span class="n">JavaWrapper</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Linear regression results evaluated on a dataset.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predictions</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">DataFrame</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Dataframe outputted by the model&#39;s `transform` method.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predictions&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Field in &quot;predictions&quot; which gives the predicted value of</span>
<span class="sd"> the label at each instance.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predictionCol&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">labelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Field in &quot;predictions&quot; which gives the true label of each</span>
<span class="sd"> instance.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;labelCol&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">featuresCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Field in &quot;predictions&quot; which gives the features of each instance</span>
<span class="sd"> as a vector.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;featuresCol&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">explainedVariance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns the explained variance regression score.</span>
<span class="sd"> explainedVariance = :math:`1 - \frac{variance(y - \hat{y})}{variance(y)}`</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> This ignores instance weights (setting all to 1.0) from</span>
<span class="sd"> `LinearRegression.weightCol`. This will change in later Spark</span>
<span class="sd"> versions.</span>
<span class="sd"> For additional information see</span>
<span class="sd"> `Explained variation on Wikipedia \</span>
<span class="sd"> &lt;http://en.wikipedia.org/wiki/Explained_variation&gt;`_</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;explainedVariance&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">meanAbsoluteError</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns the mean absolute error, which is a risk function</span>
<span class="sd"> corresponding to the expected value of the absolute error</span>
<span class="sd"> loss or l1-norm loss.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> This ignores instance weights (setting all to 1.0) from</span>
<span class="sd"> `LinearRegression.weightCol`. This will change in later Spark</span>
<span class="sd"> versions.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;meanAbsoluteError&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">meanSquaredError</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns the mean squared error, which is a risk function</span>
<span class="sd"> corresponding to the expected value of the squared error</span>
<span class="sd"> loss or quadratic loss.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> This ignores instance weights (setting all to 1.0) from</span>
<span class="sd"> `LinearRegression.weightCol`. This will change in later Spark</span>
<span class="sd"> versions.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;meanSquaredError&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">rootMeanSquaredError</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns the root mean squared error, which is defined as the</span>
<span class="sd"> square root of the mean squared error.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> This ignores instance weights (setting all to 1.0) from</span>
<span class="sd"> `LinearRegression.weightCol`. This will change in later Spark</span>
<span class="sd"> versions.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;rootMeanSquaredError&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">r2</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns R^2, the coefficient of determination.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> This ignores instance weights (setting all to 1.0) from</span>
<span class="sd"> `LinearRegression.weightCol`. This will change in later Spark</span>
<span class="sd"> versions.</span>
<span class="sd"> See also `Wikipedia coefficient of determination \</span>
<span class="sd"> &lt;http://en.wikipedia.org/wiki/Coefficient_of_determination&gt;`_</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;r2&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">r2adj</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns Adjusted R^2, the adjusted coefficient of determination.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> This ignores instance weights (setting all to 1.0) from</span>
<span class="sd"> `LinearRegression.weightCol`. This will change in later Spark versions.</span>
<span class="sd"> `Wikipedia coefficient of determination, Adjusted R^2 \</span>
<span class="sd"> &lt;https://en.wikipedia.org/wiki/Coefficient_of_determination#Adjusted_R2&gt;`_</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;r2adj&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">residuals</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">DataFrame</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Residuals (label - predicted value)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;residuals&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">numInstances</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Number of instances in DataFrame predictions</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;numInstances&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.2.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">degreesOfFreedom</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Degrees of freedom.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;degreesOfFreedom&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">devianceResiduals</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The weighted residuals, the usual residuals rescaled by the</span>
<span class="sd"> square root of the instance weights.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;devianceResiduals&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">coefficientStandardErrors</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Standard error of estimated coefficients and intercept.</span>
<span class="sd"> This value is only available when using the &quot;normal&quot; solver.</span>
<span class="sd"> If :py:attr:`LinearRegression.fitIntercept` is set to True,</span>
<span class="sd"> then the last element returned corresponds to the intercept.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> LinearRegression.solver</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;coefficientStandardErrors&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">tValues</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> T-statistic of estimated coefficients and intercept.</span>
<span class="sd"> This value is only available when using the &quot;normal&quot; solver.</span>
<span class="sd"> If :py:attr:`LinearRegression.fitIntercept` is set to True,</span>
<span class="sd"> then the last element returned corresponds to the intercept.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> LinearRegression.solver</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;tValues&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">pValues</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Two-sided p-value of estimated coefficients and intercept.</span>
<span class="sd"> This value is only available when using the &quot;normal&quot; solver.</span>
<span class="sd"> If :py:attr:`LinearRegression.fitIntercept` is set to True,</span>
<span class="sd"> then the last element returned corresponds to the intercept.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> LinearRegression.solver</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;pValues&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="LinearRegressionTrainingSummary"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.LinearRegressionTrainingSummary.html#pyspark.ml.regression.LinearRegressionTrainingSummary">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">LinearRegressionTrainingSummary</span><span class="p">(</span><span class="n">LinearRegressionSummary</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Linear regression training results. Currently, the training summary ignores the</span>
<span class="sd"> training weights except for the objective trace.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">objectiveHistory</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Objective function (scaled loss + regularization) at each</span>
<span class="sd"> iteration.</span>
<span class="sd"> This value is only available when using the &quot;l-bfgs&quot; solver.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> LinearRegression.solver</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;objectiveHistory&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">totalIterations</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Number of training iterations until termination.</span>
<span class="sd"> This value is only available when using the &quot;l-bfgs&quot; solver.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> LinearRegression.solver</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;totalIterations&quot;</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">_IsotonicRegressionParams</span><span class="p">(</span><span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasWeightCol</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`IsotonicRegression` and :py:class:`IsotonicRegressionModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">isotonic</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;isotonic&quot;</span><span class="p">,</span>
<span class="s2">&quot;whether the output sequence should be isotonic/increasing (true) or&quot;</span>
<span class="o">+</span> <span class="s2">&quot;antitonic/decreasing (false).&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toBoolean</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">featureIndex</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;featureIndex&quot;</span><span class="p">,</span>
<span class="s2">&quot;The index of the feature if featuresCol is a vector column, no effect otherwise.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_IsotonicRegressionParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">isotonic</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">featureIndex</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getIsotonic</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of isotonic or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">isotonic</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getFeatureIndex</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of featureIndex or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">featureIndex</span><span class="p">)</span>
<div class="viewcode-block" id="IsotonicRegression"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">IsotonicRegression</span><span class="p">(</span>
<span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">_IsotonicRegressionParams</span><span class="p">,</span> <span class="n">HasWeightCol</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">,</span> <span class="n">JavaMLReadable</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Currently implemented using parallelized pool adjacent violators algorithm.</span>
<span class="sd"> Only univariate (single feature) algorithm supported.</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; ir = IsotonicRegression()</span>
<span class="sd"> &gt;&gt;&gt; model = ir.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.setFeaturesCol(&quot;features&quot;)</span>
<span class="sd"> IsotonicRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.numFeatures</span>
<span class="sd"> 1</span>
<span class="sd"> &gt;&gt;&gt; test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).head().prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.predict(test0.head().features[model.getFeatureIndex()])</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.boundaries</span>
<span class="sd"> DenseVector([0.0, 1.0])</span>
<span class="sd"> &gt;&gt;&gt; ir_path = temp_path + &quot;/ir&quot;</span>
<span class="sd"> &gt;&gt;&gt; ir.save(ir_path)</span>
<span class="sd"> &gt;&gt;&gt; ir2 = IsotonicRegression.load(ir_path)</span>
<span class="sd"> &gt;&gt;&gt; ir2.getIsotonic()</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/ir_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = IsotonicRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.boundaries == model2.boundaries</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.predictions == model2.predictions</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).take(1) == model2.transform(test0).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</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="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">isotonic</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">featureIndex</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> weightCol=None, isotonic=True, featureIndex=0):</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">IsotonicRegression</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s2">&quot;org.apache.spark.ml.regression.IsotonicRegression&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span>
<span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="IsotonicRegression.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</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="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">isotonic</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">featureIndex</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> weightCol=None, isotonic=True, featureIndex=0):</span>
<span class="sd"> Set the params for IsotonicRegression.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">IsotonicRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="IsotonicRegression.setIsotonic"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setIsotonic">[docs]</a> <span class="k">def</span> <span class="nf">setIsotonic</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`isotonic`.</span>
<span class="sd"> &quot;&quot;&quot;</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">isotonic</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="IsotonicRegression.setFeatureIndex"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setFeatureIndex">[docs]</a> <span class="k">def</span> <span class="nf">setFeatureIndex</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`featureIndex`.</span>
<span class="sd"> &quot;&quot;&quot;</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">featureIndex</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="IsotonicRegression.setFeaturesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setFeaturesCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</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">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`featuresCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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="IsotonicRegression.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`predictionCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="IsotonicRegression.setLabelCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setLabelCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setLabelCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`labelCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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="IsotonicRegression.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegression.html#pyspark.ml.regression.IsotonicRegression.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`weightCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="IsotonicRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegressionModel.html#pyspark.ml.regression.IsotonicRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">IsotonicRegressionModel</span><span class="p">(</span>
<span class="n">JavaModel</span><span class="p">,</span>
<span class="n">_IsotonicRegressionParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;IsotonicRegressionModel&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`IsotonicRegression`.</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="IsotonicRegressionModel.setFeaturesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegressionModel.html#pyspark.ml.regression.IsotonicRegressionModel.setFeaturesCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</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">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`featuresCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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="IsotonicRegressionModel.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegressionModel.html#pyspark.ml.regression.IsotonicRegressionModel.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`predictionCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="IsotonicRegressionModel.setFeatureIndex"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegressionModel.html#pyspark.ml.regression.IsotonicRegressionModel.setFeatureIndex">[docs]</a> <span class="k">def</span> <span class="nf">setFeatureIndex</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;IsotonicRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`featureIndex`.</span>
<span class="sd"> &quot;&quot;&quot;</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">featureIndex</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">boundaries</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Boundaries in increasing order for which predictions are known.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;boundaries&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predictions</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Predictions associated with the boundaries at the same index, monotone because of isotonic</span>
<span class="sd"> regression.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predictions&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</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">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns the number of features the model was trained on. If unknown, returns -1</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;numFeatures&quot;</span><span class="p">)</span>
<div class="viewcode-block" id="IsotonicRegressionModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.IsotonicRegressionModel.html#pyspark.ml.regression.IsotonicRegressionModel.predict">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Predict label for the given features.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predict&quot;</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span></div></div>
<span class="k">class</span> <span class="nc">_DecisionTreeRegressorParams</span><span class="p">(</span><span class="n">_DecisionTreeParams</span><span class="p">,</span> <span class="n">_TreeRegressorParams</span><span class="p">,</span> <span class="n">HasVarianceCol</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`DecisionTreeRegressor` and :py:class:`DecisionTreeRegressionModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_DecisionTreeRegressorParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">leafCol</span><span class="o">=</span><span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span>
<div class="viewcode-block" id="DecisionTreeRegressor"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">DecisionTreeRegressor</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;DecisionTreeRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_DecisionTreeRegressorParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> `Decision tree &lt;http://en.wikipedia.org/wiki/Decision_tree_learning&gt;`_</span>
<span class="sd"> learning algorithm for regression.</span>
<span class="sd"> It supports both continuous and categorical features.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; dt = DecisionTreeRegressor(maxDepth=2)</span>
<span class="sd"> &gt;&gt;&gt; dt.setVarianceCol(&quot;variance&quot;)</span>
<span class="sd"> DecisionTreeRegressor...</span>
<span class="sd"> &gt;&gt;&gt; model = dt.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.getVarianceCol()</span>
<span class="sd"> &#39;variance&#39;</span>
<span class="sd"> &gt;&gt;&gt; model.setLeafCol(&quot;leafId&quot;)</span>
<span class="sd"> DecisionTreeRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.depth</span>
<span class="sd"> 1</span>
<span class="sd"> &gt;&gt;&gt; model.numNodes</span>
<span class="sd"> 3</span>
<span class="sd"> &gt;&gt;&gt; model.featureImportances</span>
<span class="sd"> SparseVector(1, {0: 1.0})</span>
<span class="sd"> &gt;&gt;&gt; model.numFeatures</span>
<span class="sd"> 1</span>
<span class="sd"> &gt;&gt;&gt; test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.predict(test0.head().features)</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; result = model.transform(test0).head()</span>
<span class="sd"> &gt;&gt;&gt; result.prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.predictLeaf(test0.head().features)</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; result.leafId</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; test1 = spark.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> &gt;&gt;&gt; dtr_path = temp_path + &quot;/dtr&quot;</span>
<span class="sd"> &gt;&gt;&gt; dt.save(dtr_path)</span>
<span class="sd"> &gt;&gt;&gt; dt2 = DecisionTreeRegressor.load(dtr_path)</span>
<span class="sd"> &gt;&gt;&gt; dt2.getMaxDepth()</span>
<span class="sd"> 2</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/dtr_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = DecisionTreeRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.numNodes == model2.numNodes</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.depth == model2.depth</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test1).head().variance</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).take(1) == model2.transform(test0).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; df3 = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, 0.2, Vectors.dense(1.0)),</span>
<span class="sd"> ... (1.0, 0.8, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, 1.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;weight&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; dt3 = DecisionTreeRegressor(maxDepth=2, weightCol=&quot;weight&quot;, varianceCol=&quot;variance&quot;)</span>
<span class="sd"> &gt;&gt;&gt; model3 = dt3.fit(df3)</span>
<span class="sd"> &gt;&gt;&gt; print(model3.toDebugString)</span>
<span class="sd"> DecisionTreeRegressionModel...depth=1, numNodes=3...</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</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="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">varianceCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">leafCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \</span>
<span class="sd"> impurity=&quot;variance&quot;, seed=None, varianceCol=None, weightCol=None, \</span>
<span class="sd"> leafCol=&quot;&quot;, minWeightFractionPerNode=0.0)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DecisionTreeRegressor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s2">&quot;org.apache.spark.ml.regression.DecisionTreeRegressor&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span>
<span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="DecisionTreeRegressor.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</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="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">varianceCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">leafCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \</span>
<span class="sd"> impurity=&quot;variance&quot;, seed=None, varianceCol=None, weightCol=None, \</span>
<span class="sd"> leafCol=&quot;&quot;, minWeightFractionPerNode=0.0)</span>
<span class="sd"> Sets params for the DecisionTreeRegressor.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">DecisionTreeRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="DecisionTreeRegressor.setMaxDepth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setMaxDepth">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxDepth</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxDepth`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxDepth</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setMaxBins"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setMaxBins">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxBins</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxBins`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxBins</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setMinInstancesPerNode"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setMinInstancesPerNode">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinInstancesPerNode</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minInstancesPerNode`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minInstancesPerNode</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setMinWeightFractionPerNode"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setMinWeightFractionPerNode">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinWeightFractionPerNode</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minWeightFractionPerNode`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minWeightFractionPerNode</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setMinInfoGain"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setMinInfoGain">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinInfoGain</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minInfoGain`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minInfoGain</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setMaxMemoryInMB"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setMaxMemoryInMB">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxMemoryInMB</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxMemoryInMB`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxMemoryInMB</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setCacheNodeIds"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setCacheNodeIds">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setCacheNodeIds</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`cacheNodeIds`.</span>
<span class="sd"> &quot;&quot;&quot;</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">cacheNodeIds</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setImpurity"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setImpurity">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setImpurity</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`impurity`.</span>
<span class="sd"> &quot;&quot;&quot;</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">impurity</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setCheckpointInterval"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setCheckpointInterval">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setCheckpointInterval</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`checkpointInterval`.</span>
<span class="sd"> &quot;&quot;&quot;</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">checkpointInterval</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setSeed"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setSeed">[docs]</a> <span class="k">def</span> <span class="nf">setSeed</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`seed`.</span>
<span class="sd"> &quot;&quot;&quot;</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">seed</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`weightCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="DecisionTreeRegressor.setVarianceCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressor.html#pyspark.ml.regression.DecisionTreeRegressor.setVarianceCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setVarianceCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`varianceCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">varianceCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="DecisionTreeRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressionModel.html#pyspark.ml.regression.DecisionTreeRegressionModel">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">DecisionTreeRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">,</span>
<span class="n">_DecisionTreeModel</span><span class="p">,</span>
<span class="n">_DecisionTreeRegressorParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;DecisionTreeRegressionModel&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`DecisionTreeRegressor`.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="DecisionTreeRegressionModel.setVarianceCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.DecisionTreeRegressionModel.html#pyspark.ml.regression.DecisionTreeRegressionModel.setVarianceCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setVarianceCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DecisionTreeRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`varianceCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">varianceCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">featureImportances</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Estimate of the importance of each feature.</span>
<span class="sd"> This generalizes the idea of &quot;Gini&quot; importance to other losses,</span>
<span class="sd"> following the explanation of Gini importance from &quot;Random Forests&quot; documentation</span>
<span class="sd"> by Leo Breiman and Adele Cutler, and following the implementation from scikit-learn.</span>
<span class="sd"> This feature importance is calculated as follows:</span>
<span class="sd"> - importance(feature j) = sum (over nodes which split on feature j) of the gain,</span>
<span class="sd"> where gain is scaled by the number of instances passing through node</span>
<span class="sd"> - Normalize importances for tree to sum to 1.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> Feature importance for single decision trees can have high variance due to</span>
<span class="sd"> correlated predictor variables. Consider using a :py:class:`RandomForestRegressor`</span>
<span class="sd"> to determine feature importance instead.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;featureImportances&quot;</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">_RandomForestRegressorParams</span><span class="p">(</span><span class="n">_RandomForestParams</span><span class="p">,</span> <span class="n">_TreeRegressorParams</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`RandomForestRegressor` and :py:class:`RandomForestRegressionModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_RandomForestRegressorParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">subsamplingRate</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">numTrees</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span>
<span class="n">featureSubsetStrategy</span><span class="o">=</span><span class="s2">&quot;auto&quot;</span><span class="p">,</span>
<span class="n">leafCol</span><span class="o">=</span><span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">bootstrap</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="p">)</span>
<div class="viewcode-block" id="RandomForestRegressor"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">RandomForestRegressor</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;RandomForestRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_RandomForestRegressorParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> `Random Forest &lt;http://en.wikipedia.org/wiki/Random_forest&gt;`_</span>
<span class="sd"> learning algorithm for regression.</span>
<span class="sd"> It supports both continuous and categorical features.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from numpy import allclose</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; rf = RandomForestRegressor(numTrees=2, maxDepth=2)</span>
<span class="sd"> &gt;&gt;&gt; rf.getMinWeightFractionPerNode()</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; rf.setSeed(42)</span>
<span class="sd"> RandomForestRegressor...</span>
<span class="sd"> &gt;&gt;&gt; model = rf.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.getBootstrap()</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.getSeed()</span>
<span class="sd"> 42</span>
<span class="sd"> &gt;&gt;&gt; model.setLeafCol(&quot;leafId&quot;)</span>
<span class="sd"> RandomForestRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.featureImportances</span>
<span class="sd"> SparseVector(1, {0: 1.0})</span>
<span class="sd"> &gt;&gt;&gt; allclose(model.treeWeights, [1.0, 1.0])</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.predict(test0.head().features)</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.predictLeaf(test0.head().features)</span>
<span class="sd"> DenseVector([0.0, 0.0])</span>
<span class="sd"> &gt;&gt;&gt; result = model.transform(test0).head()</span>
<span class="sd"> &gt;&gt;&gt; result.prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; result.leafId</span>
<span class="sd"> DenseVector([0.0, 0.0])</span>
<span class="sd"> &gt;&gt;&gt; model.numFeatures</span>
<span class="sd"> 1</span>
<span class="sd"> &gt;&gt;&gt; model.trees</span>
<span class="sd"> [DecisionTreeRegressionModel...depth=..., DecisionTreeRegressionModel...]</span>
<span class="sd"> &gt;&gt;&gt; model.getNumTrees</span>
<span class="sd"> 2</span>
<span class="sd"> &gt;&gt;&gt; test1 = spark.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test1).head().prediction</span>
<span class="sd"> 0.5</span>
<span class="sd"> &gt;&gt;&gt; rfr_path = temp_path + &quot;/rfr&quot;</span>
<span class="sd"> &gt;&gt;&gt; rf.save(rfr_path)</span>
<span class="sd"> &gt;&gt;&gt; rf2 = RandomForestRegressor.load(rfr_path)</span>
<span class="sd"> &gt;&gt;&gt; rf2.getNumTrees()</span>
<span class="sd"> 2</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/rfr_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = RandomForestRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.featureImportances == model2.featureImportances</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).take(1) == model2.transform(test0).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</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="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">subsamplingRate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">numTrees</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">20</span><span class="p">,</span>
<span class="n">featureSubsetStrategy</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;auto&quot;</span><span class="p">,</span>
<span class="n">leafCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">bootstrap</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \</span>
<span class="sd"> impurity=&quot;variance&quot;, subsamplingRate=1.0, seed=None, numTrees=20, \</span>
<span class="sd"> featureSubsetStrategy=&quot;auto&quot;, leafCol=&quot;, minWeightFractionPerNode=0.0&quot;, \</span>
<span class="sd"> weightCol=None, bootstrap=True)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">RandomForestRegressor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s2">&quot;org.apache.spark.ml.regression.RandomForestRegressor&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span>
<span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="RandomForestRegressor.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</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="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">subsamplingRate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">numTrees</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">20</span><span class="p">,</span>
<span class="n">featureSubsetStrategy</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;auto&quot;</span><span class="p">,</span>
<span class="n">leafCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">bootstrap</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \</span>
<span class="sd"> impurity=&quot;variance&quot;, subsamplingRate=1.0, seed=None, numTrees=20, \</span>
<span class="sd"> featureSubsetStrategy=&quot;auto&quot;, leafCol=&quot;&quot;, minWeightFractionPerNode=0.0, \</span>
<span class="sd"> weightCol=None, bootstrap=True)</span>
<span class="sd"> Sets params for linear regression.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">RandomForestRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="RandomForestRegressor.setMaxDepth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setMaxDepth">[docs]</a> <span class="k">def</span> <span class="nf">setMaxDepth</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxDepth`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxDepth</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setMaxBins"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setMaxBins">[docs]</a> <span class="k">def</span> <span class="nf">setMaxBins</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxBins`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxBins</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setMinInstancesPerNode"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setMinInstancesPerNode">[docs]</a> <span class="k">def</span> <span class="nf">setMinInstancesPerNode</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minInstancesPerNode`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minInstancesPerNode</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setMinInfoGain"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setMinInfoGain">[docs]</a> <span class="k">def</span> <span class="nf">setMinInfoGain</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minInfoGain`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minInfoGain</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setMaxMemoryInMB"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setMaxMemoryInMB">[docs]</a> <span class="k">def</span> <span class="nf">setMaxMemoryInMB</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxMemoryInMB`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxMemoryInMB</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setCacheNodeIds"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setCacheNodeIds">[docs]</a> <span class="k">def</span> <span class="nf">setCacheNodeIds</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`cacheNodeIds`.</span>
<span class="sd"> &quot;&quot;&quot;</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">cacheNodeIds</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setImpurity"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setImpurity">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setImpurity</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`impurity`.</span>
<span class="sd"> &quot;&quot;&quot;</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">impurity</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setNumTrees"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setNumTrees">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setNumTrees</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`numTrees`.</span>
<span class="sd"> &quot;&quot;&quot;</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">numTrees</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setBootstrap"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setBootstrap">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setBootstrap</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`bootstrap`.</span>
<span class="sd"> &quot;&quot;&quot;</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">bootstrap</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setSubsamplingRate"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setSubsamplingRate">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setSubsamplingRate</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`subsamplingRate`.</span>
<span class="sd"> &quot;&quot;&quot;</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">subsamplingRate</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setFeatureSubsetStrategy"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setFeatureSubsetStrategy">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFeatureSubsetStrategy</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`featureSubsetStrategy`.</span>
<span class="sd"> &quot;&quot;&quot;</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">featureSubsetStrategy</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setCheckpointInterval"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setCheckpointInterval">[docs]</a> <span class="k">def</span> <span class="nf">setCheckpointInterval</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`checkpointInterval`.</span>
<span class="sd"> &quot;&quot;&quot;</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">checkpointInterval</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setSeed"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setSeed">[docs]</a> <span class="k">def</span> <span class="nf">setSeed</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`seed`.</span>
<span class="sd"> &quot;&quot;&quot;</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">seed</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`weightCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="RandomForestRegressor.setMinWeightFractionPerNode"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressor.html#pyspark.ml.regression.RandomForestRegressor.setMinWeightFractionPerNode">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinWeightFractionPerNode</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;RandomForestRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minWeightFractionPerNode`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minWeightFractionPerNode</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="RandomForestRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.RandomForestRegressionModel.html#pyspark.ml.regression.RandomForestRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">RandomForestRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">[</span><span class="n">Vector</span><span class="p">],</span>
<span class="n">_TreeEnsembleModel</span><span class="p">,</span>
<span class="n">_RandomForestRegressorParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;RandomForestRegressionModel&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`RandomForestRegressor`.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">trees</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">DecisionTreeRegressionModel</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Trees in this ensemble. Warning: These have null parent Estimators.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="p">[</span><span class="n">DecisionTreeRegressionModel</span><span class="p">(</span><span class="n">m</span><span class="p">)</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;trees&quot;</span><span class="p">))]</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">featureImportances</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Estimate of the importance of each feature.</span>
<span class="sd"> Each feature&#39;s importance is the average of its importance across all trees in the ensemble</span>
<span class="sd"> The importance vector is normalized to sum to 1. This method is suggested by Hastie et al.</span>
<span class="sd"> (Hastie, Tibshirani, Friedman. &quot;The Elements of Statistical Learning, 2nd Edition.&quot; 2001.)</span>
<span class="sd"> and follows the implementation from scikit-learn.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> DecisionTreeRegressionModel.featureImportances</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;featureImportances&quot;</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">_GBTRegressorParams</span><span class="p">(</span><span class="n">_GBTParams</span><span class="p">,</span> <span class="n">_TreeRegressorParams</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`GBTRegressor` and :py:class:`GBTRegressorModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">supportedLossTypes</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;squared&quot;</span><span class="p">,</span> <span class="s2">&quot;absolute&quot;</span><span class="p">]</span>
<span class="n">lossType</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;lossType&quot;</span><span class="p">,</span>
<span class="s2">&quot;Loss function which GBT tries to minimize (case-insensitive). &quot;</span>
<span class="o">+</span> <span class="s2">&quot;Supported options: &quot;</span>
<span class="o">+</span> <span class="s2">&quot;, &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">supportedLossTypes</span><span class="p">),</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_GBTRegressorParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">subsamplingRate</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">lossType</span><span class="o">=</span><span class="s2">&quot;squared&quot;</span><span class="p">,</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span>
<span class="n">stepSize</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">featureSubsetStrategy</span><span class="o">=</span><span class="s2">&quot;all&quot;</span><span class="p">,</span>
<span class="n">validationTol</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span>
<span class="n">leafCol</span><span class="o">=</span><span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getLossType</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of lossType or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">lossType</span><span class="p">)</span>
<div class="viewcode-block" id="GBTRegressor"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">GBTRegressor</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;GBTRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_GBTRegressorParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;GBTRegressor&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> `Gradient-Boosted Trees (GBTs) &lt;http://en.wikipedia.org/wiki/Gradient_boosting&gt;`_</span>
<span class="sd"> learning algorithm for regression.</span>
<span class="sd"> It supports both continuous and categorical features.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from numpy import allclose</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; gbt = GBTRegressor(maxDepth=2, seed=42, leafCol=&quot;leafId&quot;)</span>
<span class="sd"> &gt;&gt;&gt; gbt.setMaxIter(5)</span>
<span class="sd"> GBTRegressor...</span>
<span class="sd"> &gt;&gt;&gt; gbt.setMinWeightFractionPerNode(0.049)</span>
<span class="sd"> GBTRegressor...</span>
<span class="sd"> &gt;&gt;&gt; gbt.getMaxIter()</span>
<span class="sd"> 5</span>
<span class="sd"> &gt;&gt;&gt; print(gbt.getImpurity())</span>
<span class="sd"> variance</span>
<span class="sd"> &gt;&gt;&gt; print(gbt.getFeatureSubsetStrategy())</span>
<span class="sd"> all</span>
<span class="sd"> &gt;&gt;&gt; model = gbt.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.featureImportances</span>
<span class="sd"> SparseVector(1, {0: 1.0})</span>
<span class="sd"> &gt;&gt;&gt; model.numFeatures</span>
<span class="sd"> 1</span>
<span class="sd"> &gt;&gt;&gt; allclose(model.treeWeights, [1.0, 0.1, 0.1, 0.1, 0.1])</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.predict(test0.head().features)</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.predictLeaf(test0.head().features)</span>
<span class="sd"> DenseVector([0.0, 0.0, 0.0, 0.0, 0.0])</span>
<span class="sd"> &gt;&gt;&gt; result = model.transform(test0).head()</span>
<span class="sd"> &gt;&gt;&gt; result.prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; result.leafId</span>
<span class="sd"> DenseVector([0.0, 0.0, 0.0, 0.0, 0.0])</span>
<span class="sd"> &gt;&gt;&gt; test1 = spark.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> &gt;&gt;&gt; gbtr_path = temp_path + &quot;gbtr&quot;</span>
<span class="sd"> &gt;&gt;&gt; gbt.save(gbtr_path)</span>
<span class="sd"> &gt;&gt;&gt; gbt2 = GBTRegressor.load(gbtr_path)</span>
<span class="sd"> &gt;&gt;&gt; gbt2.getMaxDepth()</span>
<span class="sd"> 2</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;gbtr_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = GBTRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.featureImportances == model2.featureImportances</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.treeWeights == model2.treeWeights</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).take(1) == model2.transform(test0).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.trees</span>
<span class="sd"> [DecisionTreeRegressionModel...depth=..., DecisionTreeRegressionModel...]</span>
<span class="sd"> &gt;&gt;&gt; validation = spark.createDataFrame([(0.0, Vectors.dense(-1.0))],</span>
<span class="sd"> ... [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.evaluateEachIteration(validation, &quot;squared&quot;)</span>
<span class="sd"> [0.0, 0.0, 0.0, 0.0, 0.0]</span>
<span class="sd"> &gt;&gt;&gt; gbt = gbt.setValidationIndicatorCol(&quot;validationIndicator&quot;)</span>
<span class="sd"> &gt;&gt;&gt; gbt.getValidationIndicatorCol()</span>
<span class="sd"> &#39;validationIndicator&#39;</span>
<span class="sd"> &gt;&gt;&gt; gbt.getValidationTol()</span>
<span class="sd"> 0.01</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</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="n">subsamplingRate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">lossType</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;squared&quot;</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">20</span><span class="p">,</span>
<span class="n">stepSize</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">impurity</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">featureSubsetStrategy</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;all&quot;</span><span class="p">,</span>
<span class="n">validationTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span>
<span class="n">validationIndicatorCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">leafCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0, \</span>
<span class="sd"> checkpointInterval=10, lossType=&quot;squared&quot;, maxIter=20, stepSize=0.1, seed=None, \</span>
<span class="sd"> impurity=&quot;variance&quot;, featureSubsetStrategy=&quot;all&quot;, validationTol=0.01, \</span>
<span class="sd"> validationIndicatorCol=None, leafCol=&quot;&quot;, minWeightFractionPerNode=0.0,</span>
<span class="sd"> weightCol=None)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">GBTRegressor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span><span class="s2">&quot;org.apache.spark.ml.regression.GBTRegressor&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="GBTRegressor.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span>
<span class="n">maxBins</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">,</span>
<span class="n">minInstancesPerNode</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">minInfoGain</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</span><span class="p">,</span>
<span class="n">cacheNodeIds</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="n">subsamplingRate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">lossType</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;squared&quot;</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">20</span><span class="p">,</span>
<span class="n">stepSize</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">impurity</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;variance&quot;</span><span class="p">,</span>
<span class="n">featureSubsetStrategy</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;all&quot;</span><span class="p">,</span>
<span class="n">validationTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span>
<span class="n">validationIndicatorCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">leafCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">,</span>
<span class="n">minWeightFractionPerNode</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0, \</span>
<span class="sd"> checkpointInterval=10, lossType=&quot;squared&quot;, maxIter=20, stepSize=0.1, seed=None, \</span>
<span class="sd"> impurity=&quot;variance&quot;, featureSubsetStrategy=&quot;all&quot;, validationTol=0.01, \</span>
<span class="sd"> validationIndicatorCol=None, leafCol=&quot;&quot;, minWeightFractionPerNode=0.0, \</span>
<span class="sd"> weightCol=None)</span>
<span class="sd"> Sets params for Gradient Boosted Tree Regression.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">GBTRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="GBTRegressor.setMaxDepth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMaxDepth">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxDepth</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxDepth`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxDepth</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setMaxBins"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMaxBins">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxBins</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxBins`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxBins</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setMinInstancesPerNode"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMinInstancesPerNode">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinInstancesPerNode</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minInstancesPerNode`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minInstancesPerNode</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setMinInfoGain"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMinInfoGain">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinInfoGain</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minInfoGain`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minInfoGain</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setMaxMemoryInMB"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMaxMemoryInMB">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxMemoryInMB</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxMemoryInMB`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxMemoryInMB</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setCacheNodeIds"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setCacheNodeIds">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setCacheNodeIds</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`cacheNodeIds`.</span>
<span class="sd"> &quot;&quot;&quot;</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">cacheNodeIds</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setImpurity"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setImpurity">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setImpurity</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`impurity`.</span>
<span class="sd"> &quot;&quot;&quot;</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">impurity</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setLossType"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setLossType">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setLossType</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`lossType`.</span>
<span class="sd"> &quot;&quot;&quot;</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">lossType</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setSubsamplingRate"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setSubsamplingRate">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setSubsamplingRate</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`subsamplingRate`.</span>
<span class="sd"> &quot;&quot;&quot;</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">subsamplingRate</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setFeatureSubsetStrategy"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setFeatureSubsetStrategy">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFeatureSubsetStrategy</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`featureSubsetStrategy`.</span>
<span class="sd"> &quot;&quot;&quot;</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">featureSubsetStrategy</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setValidationIndicatorCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setValidationIndicatorCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setValidationIndicatorCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`validationIndicatorCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">validationIndicatorCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setMaxIter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMaxIter">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxIter</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxIter`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxIter</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setCheckpointInterval"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setCheckpointInterval">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setCheckpointInterval</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`checkpointInterval`.</span>
<span class="sd"> &quot;&quot;&quot;</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">checkpointInterval</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setSeed"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setSeed">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setSeed</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`seed`.</span>
<span class="sd"> &quot;&quot;&quot;</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">seed</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setStepSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setStepSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setStepSize</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`stepSize`.</span>
<span class="sd"> &quot;&quot;&quot;</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">stepSize</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`weightCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GBTRegressor.setMinWeightFractionPerNode"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressor.html#pyspark.ml.regression.GBTRegressor.setMinWeightFractionPerNode">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMinWeightFractionPerNode</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GBTRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`minWeightFractionPerNode`.</span>
<span class="sd"> &quot;&quot;&quot;</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">minWeightFractionPerNode</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="GBTRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressionModel.html#pyspark.ml.regression.GBTRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">GBTRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">[</span><span class="n">Vector</span><span class="p">],</span>
<span class="n">_TreeEnsembleModel</span><span class="p">,</span>
<span class="n">_GBTRegressorParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;GBTRegressionModel&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`GBTRegressor`.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">featureImportances</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Estimate of the importance of each feature.</span>
<span class="sd"> Each feature&#39;s importance is the average of its importance across all trees in the ensemble</span>
<span class="sd"> The importance vector is normalized to sum to 1. This method is suggested by Hastie et al.</span>
<span class="sd"> (Hastie, Tibshirani, Friedman. &quot;The Elements of Statistical Learning, 2nd Edition.&quot; 2001.)</span>
<span class="sd"> and follows the implementation from scikit-learn.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> DecisionTreeRegressionModel.featureImportances</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;featureImportances&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">trees</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">DecisionTreeRegressionModel</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Trees in this ensemble. Warning: These have null parent Estimators.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="p">[</span><span class="n">DecisionTreeRegressionModel</span><span class="p">(</span><span class="n">m</span><span class="p">)</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;trees&quot;</span><span class="p">))]</span>
<div class="viewcode-block" id="GBTRegressionModel.evaluateEachIteration"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GBTRegressionModel.html#pyspark.ml.regression.GBTRegressionModel.evaluateEachIteration">[docs]</a> <span class="k">def</span> <span class="nf">evaluateEachIteration</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">loss</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Method to compute error or loss for every iteration of gradient boosting.</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"> Test dataset to evaluate model on, where dataset is an</span>
<span class="sd"> instance of :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> loss : str</span>
<span class="sd"> The loss function used to compute error.</span>
<span class="sd"> Supported options: squared, absolute</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;evaluateEachIteration&quot;</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">loss</span><span class="p">)</span></div></div>
<span class="k">class</span> <span class="nc">_AFTSurvivalRegressionParams</span><span class="p">(</span>
<span class="n">_PredictorParams</span><span class="p">,</span> <span class="n">HasMaxIter</span><span class="p">,</span> <span class="n">HasTol</span><span class="p">,</span> <span class="n">HasFitIntercept</span><span class="p">,</span> <span class="n">HasAggregationDepth</span><span class="p">,</span> <span class="n">HasMaxBlockSizeInMB</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`AFTSurvivalRegression` and :py:class:`AFTSurvivalRegressionModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">censorCol</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;censorCol&quot;</span><span class="p">,</span>
<span class="s2">&quot;censor column name. The value of this column could be 0 or 1. &quot;</span>
<span class="o">+</span> <span class="s2">&quot;If the value is 1, it means the event has occurred i.e. &quot;</span>
<span class="o">+</span> <span class="s2">&quot;uncensored; otherwise censored.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">quantileProbabilities</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;quantileProbabilities&quot;</span><span class="p">,</span>
<span class="s2">&quot;quantile probabilities array. Values of the quantile probabilities array &quot;</span>
<span class="o">+</span> <span class="s2">&quot;should be in the range (0, 1) and the array should be non-empty.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toListFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">quantilesCol</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;quantilesCol&quot;</span><span class="p">,</span>
<span class="s2">&quot;quantiles column name. This column will output quantiles of &quot;</span>
<span class="o">+</span> <span class="s2">&quot;corresponding quantileProbabilities if it is set.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_AFTSurvivalRegressionParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">censorCol</span><span class="o">=</span><span class="s2">&quot;censor&quot;</span><span class="p">,</span>
<span class="n">quantileProbabilities</span><span class="o">=</span><span class="p">[</span><span class="mf">0.01</span><span class="p">,</span> <span class="mf">0.05</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.25</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.75</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.95</span><span class="p">,</span> <span class="mf">0.99</span><span class="p">],</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span>
<span class="n">tol</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span>
<span class="n">maxBlockSizeInMB</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getCensorCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of censorCol or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">censorCol</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getQuantileProbabilities</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of quantileProbabilities or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">quantileProbabilities</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getQuantilesCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of quantilesCol or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">quantilesCol</span><span class="p">)</span>
<div class="viewcode-block" id="AFTSurvivalRegression"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">AFTSurvivalRegression</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;AFTSurvivalRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_AFTSurvivalRegressionParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Accelerated Failure Time (AFT) Model Survival Regression</span>
<span class="sd"> Fit a parametric AFT survival regression model based on the Weibull distribution</span>
<span class="sd"> of the survival time.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> For more information see Wikipedia page on</span>
<span class="sd"> `AFT Model &lt;https://en.wikipedia.org/wiki/Accelerated_failure_time_model&gt;`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0), 1.0),</span>
<span class="sd"> ... (1e-40, Vectors.sparse(1, [], []), 0.0)], [&quot;label&quot;, &quot;features&quot;, &quot;censor&quot;])</span>
<span class="sd"> &gt;&gt;&gt; aftsr = AFTSurvivalRegression()</span>
<span class="sd"> &gt;&gt;&gt; aftsr.setMaxIter(10)</span>
<span class="sd"> AFTSurvivalRegression...</span>
<span class="sd"> &gt;&gt;&gt; aftsr.getMaxIter()</span>
<span class="sd"> 10</span>
<span class="sd"> &gt;&gt;&gt; aftsr.clear(aftsr.maxIter)</span>
<span class="sd"> &gt;&gt;&gt; model = aftsr.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.getMaxBlockSizeInMB()</span>
<span class="sd"> 0.0</span>
<span class="sd"> &gt;&gt;&gt; model.setFeaturesCol(&quot;features&quot;)</span>
<span class="sd"> AFTSurvivalRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.predict(Vectors.dense(6.3))</span>
<span class="sd"> 1.0</span>
<span class="sd"> &gt;&gt;&gt; model.predictQuantiles(Vectors.dense(6.3))</span>
<span class="sd"> DenseVector([0.0101, 0.0513, 0.1054, 0.2877, 0.6931, 1.3863, 2.3026, 2.9957, 4.6052])</span>
<span class="sd"> &gt;&gt;&gt; model.transform(df).show()</span>
<span class="sd"> +-------+---------+------+----------+</span>
<span class="sd"> | label| features|censor|prediction|</span>
<span class="sd"> +-------+---------+------+----------+</span>
<span class="sd"> | 1.0| [1.0]| 1.0| 1.0|</span>
<span class="sd"> |1.0E-40|(1,[],[])| 0.0| 1.0|</span>
<span class="sd"> +-------+---------+------+----------+</span>
<span class="sd"> ...</span>
<span class="sd"> &gt;&gt;&gt; aftsr_path = temp_path + &quot;/aftsr&quot;</span>
<span class="sd"> &gt;&gt;&gt; aftsr.save(aftsr_path)</span>
<span class="sd"> &gt;&gt;&gt; aftsr2 = AFTSurvivalRegression.load(aftsr_path)</span>
<span class="sd"> &gt;&gt;&gt; aftsr2.getMaxIter()</span>
<span class="sd"> 100</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/aftsr_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = AFTSurvivalRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.coefficients == model2.coefficients</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.intercept == model2.intercept</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.scale == model2.scale</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(df).take(1) == model2.transform(df).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">censorCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;censor&quot;</span><span class="p">,</span>
<span class="n">quantileProbabilities</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
<span class="mf">0.01</span><span class="p">,</span>
<span class="mf">0.05</span><span class="p">,</span>
<span class="mf">0.1</span><span class="p">,</span>
<span class="mf">0.25</span><span class="p">,</span>
<span class="mf">0.5</span><span class="p">,</span>
<span class="mf">0.75</span><span class="p">,</span>
<span class="mf">0.9</span><span class="p">,</span>
<span class="mf">0.95</span><span class="p">,</span>
<span class="mf">0.99</span><span class="p">,</span>
<span class="p">],</span> <span class="c1"># noqa: B005</span>
<span class="n">quantilesCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">maxBlockSizeInMB</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> fitIntercept=True, maxIter=100, tol=1E-6, censorCol=&quot;censor&quot;, \</span>
<span class="sd"> quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99], \</span>
<span class="sd"> quantilesCol=None, aggregationDepth=2, maxBlockSizeInMB=0.0)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">AFTSurvivalRegression</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s2">&quot;org.apache.spark.ml.regression.AFTSurvivalRegression&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span>
<span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="AFTSurvivalRegression.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">censorCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;censor&quot;</span><span class="p">,</span>
<span class="n">quantileProbabilities</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
<span class="mf">0.01</span><span class="p">,</span>
<span class="mf">0.05</span><span class="p">,</span>
<span class="mf">0.1</span><span class="p">,</span>
<span class="mf">0.25</span><span class="p">,</span>
<span class="mf">0.5</span><span class="p">,</span>
<span class="mf">0.75</span><span class="p">,</span>
<span class="mf">0.9</span><span class="p">,</span>
<span class="mf">0.95</span><span class="p">,</span>
<span class="mf">0.99</span><span class="p">,</span>
<span class="p">],</span> <span class="c1"># noqa: B005</span>
<span class="n">quantilesCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">maxBlockSizeInMB</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> fitIntercept=True, maxIter=100, tol=1E-6, censorCol=&quot;censor&quot;, \</span>
<span class="sd"> quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99], \</span>
<span class="sd"> quantilesCol=None, aggregationDepth=2, maxBlockSizeInMB=0.0):</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">AFTSurvivalRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="AFTSurvivalRegression.setCensorCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setCensorCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setCensorCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`censorCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">censorCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setQuantileProbabilities"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setQuantileProbabilities">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setQuantileProbabilities</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">List</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`quantileProbabilities`.</span>
<span class="sd"> &quot;&quot;&quot;</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">quantileProbabilities</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setQuantilesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setQuantilesCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setQuantilesCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`quantilesCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">quantilesCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setMaxIter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setMaxIter">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxIter</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxIter`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxIter</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setTol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setTol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setTol</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`tol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">tol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setFitIntercept"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setFitIntercept">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFitIntercept</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`fitIntercept`.</span>
<span class="sd"> &quot;&quot;&quot;</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">fitIntercept</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setAggregationDepth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setAggregationDepth">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.1.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setAggregationDepth</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`aggregationDepth`.</span>
<span class="sd"> &quot;&quot;&quot;</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">aggregationDepth</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegression.setMaxBlockSizeInMB"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegression.html#pyspark.ml.regression.AFTSurvivalRegression.setMaxBlockSizeInMB">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.1.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxBlockSizeInMB</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxBlockSizeInMB`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxBlockSizeInMB</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="AFTSurvivalRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegressionModel.html#pyspark.ml.regression.AFTSurvivalRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">AFTSurvivalRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">[</span><span class="n">Vector</span><span class="p">],</span>
<span class="n">_AFTSurvivalRegressionParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;AFTSurvivalRegressionModel&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`AFTSurvivalRegression`.</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="AFTSurvivalRegressionModel.setQuantileProbabilities"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegressionModel.html#pyspark.ml.regression.AFTSurvivalRegressionModel.setQuantileProbabilities">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setQuantileProbabilities</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">List</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`quantileProbabilities`.</span>
<span class="sd"> &quot;&quot;&quot;</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">quantileProbabilities</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="AFTSurvivalRegressionModel.setQuantilesCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegressionModel.html#pyspark.ml.regression.AFTSurvivalRegressionModel.setQuantilesCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setQuantilesCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;AFTSurvivalRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`quantilesCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">quantilesCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">coefficients</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model coefficients.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;coefficients&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">intercept</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;intercept&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">scale</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model scale parameter.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;scale&quot;</span><span class="p">)</span>
<div class="viewcode-block" id="AFTSurvivalRegressionModel.predictQuantiles"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.AFTSurvivalRegressionModel.html#pyspark.ml.regression.AFTSurvivalRegressionModel.predictQuantiles">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predictQuantiles</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">features</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Predicted Quantiles</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predictQuantiles&quot;</span><span class="p">,</span> <span class="n">features</span><span class="p">)</span></div></div>
<span class="k">class</span> <span class="nc">_GeneralizedLinearRegressionParams</span><span class="p">(</span>
<span class="n">_PredictorParams</span><span class="p">,</span>
<span class="n">HasFitIntercept</span><span class="p">,</span>
<span class="n">HasMaxIter</span><span class="p">,</span>
<span class="n">HasTol</span><span class="p">,</span>
<span class="n">HasRegParam</span><span class="p">,</span>
<span class="n">HasWeightCol</span><span class="p">,</span>
<span class="n">HasSolver</span><span class="p">,</span>
<span class="n">HasAggregationDepth</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`GeneralizedLinearRegression` and</span>
<span class="sd"> :py:class:`GeneralizedLinearRegressionModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">family</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;family&quot;</span><span class="p">,</span>
<span class="s2">&quot;The name of family which is a description of &quot;</span>
<span class="o">+</span> <span class="s2">&quot;the error distribution to be used in the model. Supported options: &quot;</span>
<span class="o">+</span> <span class="s2">&quot;gaussian (default), binomial, poisson, gamma and tweedie.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">link</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;link&quot;</span><span class="p">,</span>
<span class="s2">&quot;The name of link function which provides the &quot;</span>
<span class="o">+</span> <span class="s2">&quot;relationship between the linear predictor and the mean of the distribution &quot;</span>
<span class="o">+</span> <span class="s2">&quot;function. Supported options: identity, log, inverse, logit, probit, cloglog &quot;</span>
<span class="o">+</span> <span class="s2">&quot;and sqrt.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">linkPredictionCol</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;linkPredictionCol&quot;</span><span class="p">,</span>
<span class="s2">&quot;link prediction (linear &quot;</span> <span class="o">+</span> <span class="s2">&quot;predictor) column name&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">variancePower</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;variancePower&quot;</span><span class="p">,</span>
<span class="s2">&quot;The power in the variance function &quot;</span>
<span class="o">+</span> <span class="s2">&quot;of the Tweedie distribution which characterizes the relationship &quot;</span>
<span class="o">+</span> <span class="s2">&quot;between the variance and mean of the distribution. Only applicable &quot;</span>
<span class="o">+</span> <span class="s2">&quot;for the Tweedie family. Supported values: 0 and [1, Inf).&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">linkPower</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;linkPower&quot;</span><span class="p">,</span>
<span class="s2">&quot;The index in the power link function. &quot;</span> <span class="o">+</span> <span class="s2">&quot;Only applicable to the Tweedie family.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">solver</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;solver&quot;</span><span class="p">,</span>
<span class="s2">&quot;The solver algorithm for optimization. Supported &quot;</span> <span class="o">+</span> <span class="s2">&quot;options: irls.&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">offsetCol</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;offsetCol&quot;</span><span class="p">,</span>
<span class="s2">&quot;The offset column name. If this is not set &quot;</span>
<span class="o">+</span> <span class="s2">&quot;or empty, we treat all instance offsets as 0.0&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_GeneralizedLinearRegressionParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">family</span><span class="o">=</span><span class="s2">&quot;gaussian&quot;</span><span class="p">,</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">25</span><span class="p">,</span>
<span class="n">tol</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span>
<span class="n">regParam</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">solver</span><span class="o">=</span><span class="s2">&quot;irls&quot;</span><span class="p">,</span>
<span class="n">variancePower</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span>
<span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getFamily</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of family or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">family</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getLinkPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of linkPredictionCol or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">linkPredictionCol</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getLink</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of link or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">link</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.2.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getVariancePower</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of variancePower or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">variancePower</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.2.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getLinkPower</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of linkPower or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">linkPower</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.3.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getOffsetCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of offsetCol or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">offsetCol</span><span class="p">)</span>
<div class="viewcode-block" id="GeneralizedLinearRegression"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">GeneralizedLinearRegression</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;GeneralizedLinearRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_GeneralizedLinearRegressionParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Generalized Linear Regression.</span>
<span class="sd"> Fit a Generalized Linear Model specified by giving a symbolic description of the linear</span>
<span class="sd"> predictor (link function) and a description of the error distribution (family). It supports</span>
<span class="sd"> &quot;gaussian&quot;, &quot;binomial&quot;, &quot;poisson&quot;, &quot;gamma&quot; and &quot;tweedie&quot; as family. Valid link functions for</span>
<span class="sd"> each family is listed below. The first link function of each family is the default one.</span>
<span class="sd"> * &quot;gaussian&quot; -&gt; &quot;identity&quot;, &quot;log&quot;, &quot;inverse&quot;</span>
<span class="sd"> * &quot;binomial&quot; -&gt; &quot;logit&quot;, &quot;probit&quot;, &quot;cloglog&quot;</span>
<span class="sd"> * &quot;poisson&quot; -&gt; &quot;log&quot;, &quot;identity&quot;, &quot;sqrt&quot;</span>
<span class="sd"> * &quot;gamma&quot; -&gt; &quot;inverse&quot;, &quot;identity&quot;, &quot;log&quot;</span>
<span class="sd"> * &quot;tweedie&quot; -&gt; power link function specified through &quot;linkPower&quot;. \</span>
<span class="sd"> The default link power in the tweedie family is 1 - variancePower.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> For more information see Wikipedia page on</span>
<span class="sd"> `GLM &lt;https://en.wikipedia.org/wiki/Generalized_linear_model&gt;`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(0.0, 0.0)),</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0, 2.0)),</span>
<span class="sd"> ... (2.0, Vectors.dense(0.0, 0.0)),</span>
<span class="sd"> ... (2.0, Vectors.dense(1.0, 1.0)),], [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; glr = GeneralizedLinearRegression(family=&quot;gaussian&quot;, link=&quot;identity&quot;, linkPredictionCol=&quot;p&quot;)</span>
<span class="sd"> &gt;&gt;&gt; glr.setRegParam(0.1)</span>
<span class="sd"> GeneralizedLinearRegression...</span>
<span class="sd"> &gt;&gt;&gt; glr.getRegParam()</span>
<span class="sd"> 0.1</span>
<span class="sd"> &gt;&gt;&gt; glr.clear(glr.regParam)</span>
<span class="sd"> &gt;&gt;&gt; glr.setMaxIter(10)</span>
<span class="sd"> GeneralizedLinearRegression...</span>
<span class="sd"> &gt;&gt;&gt; glr.getMaxIter()</span>
<span class="sd"> 10</span>
<span class="sd"> &gt;&gt;&gt; glr.clear(glr.maxIter)</span>
<span class="sd"> &gt;&gt;&gt; model = glr.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.setFeaturesCol(&quot;features&quot;)</span>
<span class="sd"> GeneralizedLinearRegressionModel...</span>
<span class="sd"> &gt;&gt;&gt; model.getMaxIter()</span>
<span class="sd"> 25</span>
<span class="sd"> &gt;&gt;&gt; model.getAggregationDepth()</span>
<span class="sd"> 2</span>
<span class="sd"> &gt;&gt;&gt; transformed = model.transform(df)</span>
<span class="sd"> &gt;&gt;&gt; abs(transformed.head().prediction - 1.5) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; abs(transformed.head().p - 1.5) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.coefficients</span>
<span class="sd"> DenseVector([1.5..., -1.0...])</span>
<span class="sd"> &gt;&gt;&gt; model.numFeatures</span>
<span class="sd"> 2</span>
<span class="sd"> &gt;&gt;&gt; abs(model.intercept - 1.5) &lt; 0.001</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; glr_path = temp_path + &quot;/glr&quot;</span>
<span class="sd"> &gt;&gt;&gt; glr.save(glr_path)</span>
<span class="sd"> &gt;&gt;&gt; glr2 = GeneralizedLinearRegression.load(glr_path)</span>
<span class="sd"> &gt;&gt;&gt; glr.getFamily() == glr2.getFamily()</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/glr_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = GeneralizedLinearRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model.intercept == model2.intercept</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.coefficients[0] == model2.coefficients[0]</span>
<span class="sd"> True</span>
<span class="sd"> &gt;&gt;&gt; model.transform(df).take(1) == model2.transform(df).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">family</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;gaussian&quot;</span><span class="p">,</span>
<span class="n">link</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">25</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">solver</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;irls&quot;</span><span class="p">,</span>
<span class="n">linkPredictionCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">variancePower</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">linkPower</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">offsetCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, labelCol=&quot;label&quot;, featuresCol=&quot;features&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> family=&quot;gaussian&quot;, link=None, fitIntercept=True, maxIter=25, tol=1e-6, \</span>
<span class="sd"> regParam=0.0, weightCol=None, solver=&quot;irls&quot;, linkPredictionCol=None, \</span>
<span class="sd"> variancePower=0.0, linkPower=None, offsetCol=None, aggregationDepth=2)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">GeneralizedLinearRegression</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s2">&quot;org.apache.spark.ml.regression.GeneralizedLinearRegression&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span>
<span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="GeneralizedLinearRegression.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">family</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;gaussian&quot;</span><span class="p">,</span>
<span class="n">link</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">25</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">weightCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">solver</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;irls&quot;</span><span class="p">,</span>
<span class="n">linkPredictionCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">variancePower</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">linkPower</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">offsetCol</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">aggregationDepth</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, labelCol=&quot;label&quot;, featuresCol=&quot;features&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> family=&quot;gaussian&quot;, link=None, fitIntercept=True, maxIter=25, tol=1e-6, \</span>
<span class="sd"> regParam=0.0, weightCol=None, solver=&quot;irls&quot;, linkPredictionCol=None, \</span>
<span class="sd"> variancePower=0.0, linkPower=None, offsetCol=None, aggregationDepth=2)</span>
<span class="sd"> Sets params for generalized linear regression.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">GeneralizedLinearRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="GeneralizedLinearRegression.setFamily"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setFamily">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFamily</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`family`.</span>
<span class="sd"> &quot;&quot;&quot;</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">family</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setLinkPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setLinkPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setLinkPredictionCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`linkPredictionCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">linkPredictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setLink"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setLink">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setLink</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`link`.</span>
<span class="sd"> &quot;&quot;&quot;</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">link</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setVariancePower"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setVariancePower">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.2.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setVariancePower</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`variancePower`.</span>
<span class="sd"> &quot;&quot;&quot;</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">variancePower</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setLinkPower"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setLinkPower">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.2.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setLinkPower</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`linkPower`.</span>
<span class="sd"> &quot;&quot;&quot;</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">linkPower</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setOffsetCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setOffsetCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.3.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setOffsetCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`offsetCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">offsetCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setMaxIter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setMaxIter">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxIter</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxIter`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxIter</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setRegParam"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setRegParam">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setRegParam</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`regParam`.</span>
<span class="sd"> &quot;&quot;&quot;</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">regParam</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setTol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setTol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setTol</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`tol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">tol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setFitIntercept"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setFitIntercept">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFitIntercept</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`fitIntercept`.</span>
<span class="sd"> &quot;&quot;&quot;</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">fitIntercept</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setWeightCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setWeightCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setWeightCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`weightCol`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">weightCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setSolver"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setSolver">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setSolver</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`solver`.</span>
<span class="sd"> &quot;&quot;&quot;</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">solver</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegression.setAggregationDepth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegression.html#pyspark.ml.regression.GeneralizedLinearRegression.setAggregationDepth">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setAggregationDepth</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegression&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`aggregationDepth`.</span>
<span class="sd"> &quot;&quot;&quot;</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">aggregationDepth</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="GeneralizedLinearRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegressionModel.html#pyspark.ml.regression.GeneralizedLinearRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">GeneralizedLinearRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">[</span><span class="n">Vector</span><span class="p">],</span>
<span class="n">_GeneralizedLinearRegressionParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;GeneralizedLinearRegressionModel&quot;</span><span class="p">],</span>
<span class="n">HasTrainingSummary</span><span class="p">[</span><span class="s2">&quot;GeneralizedLinearRegressionTrainingSummary&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`GeneralizedLinearRegression`.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="GeneralizedLinearRegressionModel.setLinkPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegressionModel.html#pyspark.ml.regression.GeneralizedLinearRegressionModel.setLinkPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setLinkPredictionCol</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegressionModel&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`linkPredictionCol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">linkPredictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">coefficients</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model coefficients.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;coefficients&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">intercept</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;intercept&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<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="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegressionTrainingSummary&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets summary (residuals, deviance, p-values) of model on</span>
<span class="sd"> training set. An exception is thrown if</span>
<span class="sd"> `trainingSummary is None`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hasSummary</span><span class="p">:</span>
<span class="k">return</span> <span class="n">GeneralizedLinearRegressionTrainingSummary</span><span class="p">(</span>
<span class="nb">super</span><span class="p">(</span><span class="n">GeneralizedLinearRegressionModel</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">summary</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
<span class="s2">&quot;No training summary available for this </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span>
<span class="p">)</span>
<div class="viewcode-block" id="GeneralizedLinearRegressionModel.evaluate"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegressionModel.html#pyspark.ml.regression.GeneralizedLinearRegressionModel.evaluate">[docs]</a> <span class="k">def</span> <span class="nf">evaluate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;GeneralizedLinearRegressionSummary&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Evaluates the model on a test dataset.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> Test dataset to evaluate model on, where dataset is an</span>
<span class="sd"> instance of :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">&quot;dataset must be a DataFrame but got </span><span class="si">%s</span><span class="s2">.&quot;</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">dataset</span><span class="p">))</span>
<span class="n">java_glr_summary</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;evaluate&quot;</span><span class="p">,</span> <span class="n">dataset</span><span class="p">)</span>
<span class="k">return</span> <span class="n">GeneralizedLinearRegressionSummary</span><span class="p">(</span><span class="n">java_glr_summary</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="GeneralizedLinearRegressionSummary"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegressionSummary.html#pyspark.ml.regression.GeneralizedLinearRegressionSummary">[docs]</a><span class="k">class</span> <span class="nc">GeneralizedLinearRegressionSummary</span><span class="p">(</span><span class="n">JavaWrapper</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Generalized linear regression results evaluated on a dataset.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predictions</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">DataFrame</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Predictions output by the model&#39;s `transform` method.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predictions&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Field in :py:attr:`predictions` which gives the predicted value of each instance.</span>
<span class="sd"> This is set to a new column name if the original model&#39;s `predictionCol` is not set.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;predictionCol&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.2.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">numInstances</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Number of instances in DataFrame predictions.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;numInstances&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">rank</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The numeric rank of the fitted linear model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;rank&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">degreesOfFreedom</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Degrees of freedom.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;degreesOfFreedom&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">residualDegreeOfFreedom</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The residual degrees of freedom.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;residualDegreeOfFreedom&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">residualDegreeOfFreedomNull</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The residual degrees of freedom for the null model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;residualDegreeOfFreedomNull&quot;</span><span class="p">)</span>
<div class="viewcode-block" id="GeneralizedLinearRegressionSummary.residuals"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegressionSummary.html#pyspark.ml.regression.GeneralizedLinearRegressionSummary.residuals">[docs]</a> <span class="k">def</span> <span class="nf">residuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">residualsType</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;deviance&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">DataFrame</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get the residuals of the fitted model by type.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> residualsType : str, optional</span>
<span class="sd"> The type of residuals which should be returned.</span>
<span class="sd"> Supported options: deviance (default), pearson, working, and response.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;residuals&quot;</span><span class="p">,</span> <span class="n">residualsType</span><span class="p">)</span></div>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">nullDeviance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The deviance for the null model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;nullDeviance&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">deviance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The deviance for the fitted model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;deviance&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">dispersion</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The dispersion of the fitted model.</span>
<span class="sd"> It is taken as 1.0 for the &quot;binomial&quot; and &quot;poisson&quot; families, and otherwise</span>
<span class="sd"> estimated by the residual Pearson&#39;s Chi-Squared statistic (which is defined as</span>
<span class="sd"> sum of the squares of the Pearson residuals) divided by the residual degrees of freedom.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;dispersion&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">aic</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Akaike&#39;s &quot;An Information Criterion&quot;(AIC) for the fitted model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;aic&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="GeneralizedLinearRegressionTrainingSummary"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.GeneralizedLinearRegressionTrainingSummary.html#pyspark.ml.regression.GeneralizedLinearRegressionTrainingSummary">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">GeneralizedLinearRegressionTrainingSummary</span><span class="p">(</span><span class="n">GeneralizedLinearRegressionSummary</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Generalized linear regression training results.</span>
<span class="sd"> .. versionadded:: 2.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">numIterations</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Number of training iterations.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;numIterations&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">solver</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The numeric solver used for training.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;solver&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">coefficientStandardErrors</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Standard error of estimated coefficients and intercept.</span>
<span class="sd"> If :py:attr:`GeneralizedLinearRegression.fitIntercept` is set to True,</span>
<span class="sd"> then the last element returned corresponds to the intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;coefficientStandardErrors&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">tValues</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> T-statistic of estimated coefficients and intercept.</span>
<span class="sd"> If :py:attr:`GeneralizedLinearRegression.fitIntercept` is set to True,</span>
<span class="sd"> then the last element returned corresponds to the intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;tValues&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">pValues</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Two-sided p-value of estimated coefficients and intercept.</span>
<span class="sd"> If :py:attr:`GeneralizedLinearRegression.fitIntercept` is set to True,</span>
<span class="sd"> then the last element returned corresponds to the intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;pValues&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;toString&quot;</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">_FactorizationMachinesParams</span><span class="p">(</span>
<span class="n">_PredictorParams</span><span class="p">,</span>
<span class="n">HasMaxIter</span><span class="p">,</span>
<span class="n">HasStepSize</span><span class="p">,</span>
<span class="n">HasTol</span><span class="p">,</span>
<span class="n">HasSolver</span><span class="p">,</span>
<span class="n">HasSeed</span><span class="p">,</span>
<span class="n">HasFitIntercept</span><span class="p">,</span>
<span class="n">HasRegParam</span><span class="p">,</span>
<span class="n">HasWeightCol</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`FMRegressor`, :py:class:`FMRegressionModel`, :py:class:`FMClassifier`</span>
<span class="sd"> and :py:class:`FMClassifierModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">factorSize</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;factorSize&quot;</span><span class="p">,</span>
<span class="s2">&quot;Dimensionality of the factor vectors, &quot;</span>
<span class="o">+</span> <span class="s2">&quot;which are used to get pairwise interactions between variables&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">fitLinear</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;fitLinear&quot;</span><span class="p">,</span>
<span class="s2">&quot;whether to fit linear term (aka 1-way term)&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toBoolean</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">miniBatchFraction</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;miniBatchFraction&quot;</span><span class="p">,</span>
<span class="s2">&quot;fraction of the input data &quot;</span>
<span class="o">+</span> <span class="s2">&quot;set that should be used for one iteration of gradient descent&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">initStd</span><span class="p">:</span> <span class="n">Param</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;initStd&quot;</span><span class="p">,</span>
<span class="s2">&quot;standard deviation of initial coefficients&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">solver</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span>
<span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span>
<span class="s2">&quot;solver&quot;</span><span class="p">,</span>
<span class="s2">&quot;The solver algorithm for optimization. Supported &quot;</span> <span class="o">+</span> <span class="s2">&quot;options: gd, adamW. (Default adamW)&quot;</span><span class="p">,</span>
<span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_FactorizationMachinesParams</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="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">factorSize</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">fitLinear</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">regParam</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">miniBatchFraction</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">initStd</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span>
<span class="n">stepSize</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">tol</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span>
<span class="n">solver</span><span class="o">=</span><span class="s2">&quot;adamW&quot;</span><span class="p">,</span>
<span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getFactorSize</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of factorSize or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">factorSize</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getFitLinear</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of fitLinear or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fitLinear</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getMiniBatchFraction</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of miniBatchFraction or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</span><span class="p">)</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">getInitStd</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the value of initStd or its default value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">initStd</span><span class="p">)</span>
<div class="viewcode-block" id="FMRegressor"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">FMRegressor</span><span class="p">(</span>
<span class="n">_JavaRegressor</span><span class="p">[</span><span class="s2">&quot;FMRegressionModel&quot;</span><span class="p">],</span>
<span class="n">_FactorizationMachinesParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;FMRegressor&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Factorization Machines learning algorithm for regression.</span>
<span class="sd"> solver Supports:</span>
<span class="sd"> * gd (normal mini-batch gradient descent)</span>
<span class="sd"> * adamW (default)</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.regression import FMRegressor</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (2.0, Vectors.dense(2.0)),</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt;</span>
<span class="sd"> &gt;&gt;&gt; fm = FMRegressor(factorSize=2)</span>
<span class="sd"> &gt;&gt;&gt; fm.setSeed(16)</span>
<span class="sd"> FMRegressor...</span>
<span class="sd"> &gt;&gt;&gt; model = fm.fit(df)</span>
<span class="sd"> &gt;&gt;&gt; model.getMaxIter()</span>
<span class="sd"> 100</span>
<span class="sd"> &gt;&gt;&gt; test0 = spark.createDataFrame([</span>
<span class="sd"> ... (Vectors.dense(-2.0),),</span>
<span class="sd"> ... (Vectors.dense(0.5),),</span>
<span class="sd"> ... (Vectors.dense(1.0),),</span>
<span class="sd"> ... (Vectors.dense(4.0),)], [&quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).show(10, False)</span>
<span class="sd"> +--------+-------------------+</span>
<span class="sd"> |features|prediction |</span>
<span class="sd"> +--------+-------------------+</span>
<span class="sd"> |[-2.0] |-1.9989237712341565|</span>
<span class="sd"> |[0.5] |0.4956682219523814 |</span>
<span class="sd"> |[1.0] |0.994586620589689 |</span>
<span class="sd"> |[4.0] |3.9880970124135344 |</span>
<span class="sd"> +--------+-------------------+</span>
<span class="sd"> ...</span>
<span class="sd"> &gt;&gt;&gt; model.intercept</span>
<span class="sd"> -0.0032501766849261557</span>
<span class="sd"> &gt;&gt;&gt; model.linear</span>
<span class="sd"> DenseVector([0.9978])</span>
<span class="sd"> &gt;&gt;&gt; model.factors</span>
<span class="sd"> DenseMatrix(1, 2, [0.0173, 0.0021], 1)</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/fm_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = FMRegressionModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2.intercept</span>
<span class="sd"> -0.0032501766849261557</span>
<span class="sd"> &gt;&gt;&gt; model2.linear</span>
<span class="sd"> DenseVector([0.9978])</span>
<span class="sd"> &gt;&gt;&gt; model2.factors</span>
<span class="sd"> DenseMatrix(1, 2, [0.0173, 0.0021], 1)</span>
<span class="sd"> &gt;&gt;&gt; model.transform(test0).take(1) == model2.transform(test0).take(1)</span>
<span class="sd"> True</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
<span class="nd">@keyword_only</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">factorSize</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">8</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">fitLinear</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">initStd</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
<span class="n">stepSize</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">solver</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;adamW&quot;</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> __init__(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> factorSize=8, fitIntercept=True, fitLinear=True, regParam=0.0, \</span>
<span class="sd"> miniBatchFraction=1.0, initStd=0.01, maxIter=100, stepSize=1.0, \</span>
<span class="sd"> tol=1e-6, solver=&quot;adamW&quot;, seed=None)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">FMRegressor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span><span class="s2">&quot;org.apache.spark.ml.regression.FMRegressor&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="FMRegressor.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setParams">[docs]</a> <span class="nd">@keyword_only</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">featuresCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;features&quot;</span><span class="p">,</span>
<span class="n">labelCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;label&quot;</span><span class="p">,</span>
<span class="n">predictionCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;prediction&quot;</span><span class="p">,</span>
<span class="n">factorSize</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">8</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">fitLinear</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
<span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">initStd</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">,</span>
<span class="n">maxIter</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
<span class="n">stepSize</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
<span class="n">tol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-6</span><span class="p">,</span>
<span class="n">solver</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;adamW&quot;</span><span class="p">,</span>
<span class="n">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, featuresCol=&quot;features&quot;, labelCol=&quot;label&quot;, predictionCol=&quot;prediction&quot;, \</span>
<span class="sd"> factorSize=8, fitIntercept=True, fitLinear=True, regParam=0.0, \</span>
<span class="sd"> miniBatchFraction=1.0, initStd=0.01, maxIter=100, stepSize=1.0, \</span>
<span class="sd"> tol=1e-6, solver=&quot;adamW&quot;, seed=None)</span>
<span class="sd"> Sets Params for FMRegressor.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">&quot;JavaObject&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressionModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">FMRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="FMRegressor.setFactorSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setFactorSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFactorSize</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`factorSize`.</span>
<span class="sd"> &quot;&quot;&quot;</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">factorSize</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setFitLinear"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setFitLinear">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFitLinear</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`fitLinear`.</span>
<span class="sd"> &quot;&quot;&quot;</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">fitLinear</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setMiniBatchFraction"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setMiniBatchFraction">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMiniBatchFraction</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`miniBatchFraction`.</span>
<span class="sd"> &quot;&quot;&quot;</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">miniBatchFraction</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setInitStd"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setInitStd">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setInitStd</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`initStd`.</span>
<span class="sd"> &quot;&quot;&quot;</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">initStd</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setMaxIter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setMaxIter">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setMaxIter</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`maxIter`.</span>
<span class="sd"> &quot;&quot;&quot;</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">maxIter</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setStepSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setStepSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setStepSize</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`stepSize`.</span>
<span class="sd"> &quot;&quot;&quot;</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">stepSize</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setTol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setTol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setTol</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`tol`.</span>
<span class="sd"> &quot;&quot;&quot;</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">tol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setSolver"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setSolver">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setSolver</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="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`solver`.</span>
<span class="sd"> &quot;&quot;&quot;</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">solver</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setSeed"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setSeed">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setSeed</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="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`seed`.</span>
<span class="sd"> &quot;&quot;&quot;</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">seed</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setFitIntercept"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setFitIntercept">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setFitIntercept</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="nb">bool</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`fitIntercept`.</span>
<span class="sd"> &quot;&quot;&quot;</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">fitIntercept</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FMRegressor.setRegParam"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressor.html#pyspark.ml.regression.FMRegressor.setRegParam">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setRegParam</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="nb">float</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;FMRegressor&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sets the value of :py:attr:`regParam`.</span>
<span class="sd"> &quot;&quot;&quot;</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">regParam</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="FMRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.regression.FMRegressionModel.html#pyspark.ml.regression.FMRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">FMRegressionModel</span><span class="p">(</span>
<span class="n">_JavaRegressionModel</span><span class="p">,</span>
<span class="n">_FactorizationMachinesParams</span><span class="p">,</span>
<span class="n">JavaMLWritable</span><span class="p">,</span>
<span class="n">JavaMLReadable</span><span class="p">[</span><span class="s2">&quot;FMRegressionModel&quot;</span><span class="p">],</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by :class:`FMRegressor`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">intercept</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model intercept.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;intercept&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">linear</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Vector</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model linear term.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;linear&quot;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">factors</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Matrix</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model factor term.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">&quot;factors&quot;</span><span class="p">)</span></div>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">doctest</span>
<span class="kn">import</span> <span class="nn">pyspark.ml.regression</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">ml</span><span class="o">.</span><span class="n">regression</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">&quot;local[2]&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">&quot;ml.regression tests&quot;</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">&quot;sc&quot;</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">&quot;spark&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span>
<span class="kn">import</span> <span class="nn">tempfile</span>
<span class="n">temp_path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span>
<span class="n">globs</span><span class="p">[</span><span class="s2">&quot;temp_path&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">temp_path</span>
<span class="k">try</span><span class="p">:</span>
<span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span>
<span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span>
<span class="k">finally</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">rmtree</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</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>