Google GitGoogle Git
Sign in
apache/spark-website/d6b80ea13dc34d32110eb4dd0169ed16eca71b86/./site/docs/4.0.4/api/python/_modules/pyspark/ml/fpm.html
blob: 58c36dffbe42fb0f86a8c159e026b562673c21f9 [file]
<!DOCTYPE html>
<html >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>pyspark.ml.fpm &#8212; PySpark 4.0.4 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/fpm';</script>
<script>
DOCUMENTATION_OPTIONS.theme_switcher_json_url = 'https://spark.apache.org/static/versions.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '4.0.4';
</script>
<link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/ml/fpm.html" />
<link rel="search" title="Search" href="../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="None">
<!-- Matomo -->
<script type="text/javascript">
var _paq = window._paq = window._paq || [];
/* tracker methods like "setCustomDimension" should be called before "trackPageView" */
_paq.push(["disableCookies"]);
_paq.push(['trackPageView']);
_paq.push(['enableLinkTracking']);
(function() {
var u="https://analytics.apache.org/";
_paq.push(['setTrackerUrl', u+'matomo.php']);
_paq.push(['setSiteId', '40']);
var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
})();
</script>
<!-- End Matomo Code -->
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<a class="skip-link" href="#main-content">Skip to main content</a>
<input type="checkbox"
class="sidebar-toggle"
name="__primary"
id="__primary"/>
<label class="overlay overlay-primary" for="__primary"></label>
<input type="checkbox"
class="sidebar-toggle"
name="__secondary"
id="__secondary"/>
<label class="overlay overlay-secondary" for="__secondary"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<nav class="bd-header navbar navbar-expand-lg bd-navbar">
<div class="bd-header__inner bd-page-width">
<label class="sidebar-toggle primary-toggle" for="__primary">
<span class="fa-solid fa-bars"></span>
</label>
<div class="navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../../index.html">
<img src="https://spark.apache.org/images/spark-logo.png" class="logo__image only-light" alt="Logo image"/>
<script>document.write(`<img src="https://spark.apache.org/images/spark-logo-rev.svg" class="logo__image only-dark" alt="Logo image"/>`);</script>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item"><nav class="navbar-nav">
<p class="sidebar-header-items__title"
role="heading"
aria-level="1"
aria-label="Site Navigation">
Site Navigation
</p>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../index.html">
Overview
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../getting_started/index.html">
Getting Started
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../tutorial/index.html">
Tutorials
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../user_guide/index.html">
User Guide
</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>
<div class="nav-item dropdown">
<button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false">
More
</button>
<div class="dropdown-menu">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../migration_guide/index.html">
Migration Guides
</a>
</li>
</div>
</div>
</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">
<script>
document.write(`
<div class="version-switcher__container dropdown">
<button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown">
4.0.4 <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div class="version-switcher__menu dropdown-menu list-group-flush py-0">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div>
`);
</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="../../../tutorial/index.html">
Tutorials
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../user_guide/index.html">
User Guide
</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>
<div class="nav-item dropdown">
<button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false">
More
</button>
<div class="dropdown-menu">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../migration_guide/index.html">
Migration Guides
</a>
</li>
</div>
</div>
</ul>
</nav></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<script>
document.write(`
<div class="version-switcher__container dropdown">
<button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown">
4.0.4 <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div class="version-switcher__menu dropdown-menu list-group-flush py-0">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div>
`);
</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.fpm</li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article" role="main">
<h1>Source code for pyspark.ml.fpm</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="w"> </span><span class="nn">sys</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </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">Optional</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark</span><span class="w"> </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="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </span><span class="kn">import</span> <span class="n">DataFrame</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.ml.util</span><span class="w"> </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">try_remote_attribute_relation</span><span class="p">,</span>
<span class="n">invoke_helper_relation</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.ml.wrapper</span><span class="w"> </span><span class="kn">import</span> <span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">JavaModel</span><span class="p">,</span> <span class="n">JavaParams</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.ml.param.shared</span><span class="w"> </span><span class="kn">import</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">Param</span><span class="p">,</span> <span class="n">TypeConverters</span><span class="p">,</span> <span class="n">Params</span>
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">py4j.java_gateway</span><span class="w"> </span><span class="kn">import</span> <span class="n">JavaObject</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;FPGrowth&quot;</span><span class="p">,</span> <span class="s2">&quot;FPGrowthModel&quot;</span><span class="p">,</span> <span class="s2">&quot;PrefixSpan&quot;</span><span class="p">]</span>
<span class="k">class</span><span class="w"> </span><span class="nc">_FPGrowthParams</span><span class="p">(</span><span class="n">HasPredictionCol</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Params for :py:class:`FPGrowth` and :py:class:`FPGrowthModel`.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">itemsCol</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;itemsCol&quot;</span><span class="p">,</span> <span class="s2">&quot;items 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="n">minSupport</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;minSupport&quot;</span><span class="p">,</span>
<span class="s2">&quot;Minimal support level of the frequent pattern. [0.0, 1.0]. &quot;</span>
<span class="o">+</span> <span class="s2">&quot;Any pattern that appears more than (minSupport * size-of-the-dataset) &quot;</span>
<span class="o">+</span> <span class="s2">&quot;times will be output in the frequent itemsets.&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">numPartitions</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;numPartitions&quot;</span><span class="p">,</span>
<span class="s2">&quot;Number of partitions (at least 1) used by parallel FP-growth. &quot;</span>
<span class="o">+</span> <span class="s2">&quot;By default the param is not set, &quot;</span>
<span class="o">+</span> <span class="s2">&quot;and partition number of the input dataset is used.&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">minConfidence</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;minConfidence&quot;</span><span class="p">,</span>
<span class="s2">&quot;Minimal confidence for generating Association Rule. [0.0, 1.0]. &quot;</span>
<span class="o">+</span> <span class="s2">&quot;minConfidence will not affect the mining for frequent itemsets, &quot;</span>
<span class="o">+</span> <span class="s2">&quot;but will affect the association rules generation.&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="w"> </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">_FPGrowthParams</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">minSupport</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">minConfidence</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">itemsCol</span><span class="o">=</span><span class="s2">&quot;items&quot;</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">&quot;prediction&quot;</span>
<span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">getItemsCol</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 itemsCol 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">itemsCol</span><span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">getMinSupport</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 minSupport 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">minSupport</span><span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">getNumPartitions</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 :py:attr:`numPartitions` 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">numPartitions</span><span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">getMinConfidence</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 minConfidence 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">minConfidence</span><span class="p">)</span>
<div class="viewcode-block" id="FPGrowthModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowthModel.html#pyspark.ml.fpm.FPGrowthModel">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">FPGrowthModel</span><span class="p">(</span><span class="n">JavaModel</span><span class="p">,</span> <span class="n">_FPGrowthParams</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;FPGrowthModel&quot;</span><span class="p">]):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by FPGrowth.</span>
<span class="sd"> .. versionadded:: 2.2.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="FPGrowthModel.setItemsCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowthModel.html#pyspark.ml.fpm.FPGrowthModel.setItemsCol">[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="w"> </span><span class="nf">setItemsCol</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;FPGrowthModel&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:`itemsCol`.</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">itemsCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowthModel.setMinConfidence"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowthModel.html#pyspark.ml.fpm.FPGrowthModel.setMinConfidence">[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="w"> </span><span class="nf">setMinConfidence</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;FPGrowthModel&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:`minConfidence`.</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">minConfidence</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowthModel.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowthModel.html#pyspark.ml.fpm.FPGrowthModel.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="w"> </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;FPGrowthModel&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>
<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="nd">@try_remote_attribute_relation</span>
<span class="k">def</span><span class="w"> </span><span class="nf">freqItemsets</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 with two columns:</span>
<span class="sd"> * `items` - Itemset of the same type as the input column.</span>
<span class="sd"> * `freq` - Frequency of the itemset (`LongType`).</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;freqItemsets&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="nd">@try_remote_attribute_relation</span>
<span class="k">def</span><span class="w"> </span><span class="nf">associationRules</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 with four columns:</span>
<span class="sd"> * `antecedent` - Array of the same type as the input column.</span>
<span class="sd"> * `consequent` - Array of the same type as the input column.</span>
<span class="sd"> * `confidence` - Confidence for the rule (`DoubleType`).</span>
<span class="sd"> * `lift` - Lift for the rule (`DoubleType`).</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;associationRules&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowth"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">FPGrowth</span><span class="p">(</span>
<span class="n">JavaEstimator</span><span class="p">[</span><span class="n">FPGrowthModel</span><span class="p">],</span> <span class="n">_FPGrowthParams</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;FPGrowth&quot;</span><span class="p">]</span>
<span class="p">):</span>
<span class="w"> </span><span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A parallel FP-growth algorithm to mine frequent itemsets.</span>
<span class="sd"> .. versionadded:: 2.2.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> The algorithm is described in</span>
<span class="sd"> Li et al., PFP: Parallel FP-Growth for Query Recommendation [1]_.</span>
<span class="sd"> PFP distributes computation in such a way that each worker executes an</span>
<span class="sd"> independent group of mining tasks. The FP-Growth algorithm is described in</span>
<span class="sd"> Han et al., Mining frequent patterns without candidate generation [2]_</span>
<span class="sd"> NULL values in the feature column are ignored during `fit()`.</span>
<span class="sd"> Internally `transform` `collects` and `broadcasts` association rules.</span>
<span class="sd"> .. [1] Haoyuan Li, Yi Wang, Dong Zhang, Ming Zhang, and Edward Y. Chang. 2008.</span>
<span class="sd"> Pfp: parallel fp-growth for query recommendation.</span>
<span class="sd"> In Proceedings of the 2008 ACM conference on Recommender systems (RecSys &#39;08).</span>
<span class="sd"> Association for Computing Machinery, New York, NY, USA, 107-114.</span>
<span class="sd"> DOI: https://doi.org/10.1145/1454008.1454027</span>
<span class="sd"> .. [2] Jiawei Han, Jian Pei, and Yiwen Yin. 2000.</span>
<span class="sd"> Mining frequent patterns without candidate generation.</span>
<span class="sd"> SIGMOD Rec. 29, 2 (June 2000), 1-12.</span>
<span class="sd"> DOI: https://doi.org/10.1145/335191.335372</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.sql.functions import split</span>
<span class="sd"> &gt;&gt;&gt; data = (spark.read</span>
<span class="sd"> ... .text(&quot;data/mllib/sample_fpgrowth.txt&quot;)</span>
<span class="sd"> ... .select(split(&quot;value&quot;, &quot;\s+&quot;).alias(&quot;items&quot;)))</span>
<span class="sd"> &gt;&gt;&gt; data.show(truncate=False)</span>
<span class="sd"> +------------------------+</span>
<span class="sd"> |items |</span>
<span class="sd"> +------------------------+</span>
<span class="sd"> |[r, z, h, k, p] |</span>
<span class="sd"> |[z, y, x, w, v, u, t, s]|</span>
<span class="sd"> |[s, x, o, n, r] |</span>
<span class="sd"> |[x, z, y, m, t, s, q, e]|</span>
<span class="sd"> |[z] |</span>
<span class="sd"> |[x, z, y, r, q, t, p] |</span>
<span class="sd"> +------------------------+</span>
<span class="sd"> ...</span>
<span class="sd"> &gt;&gt;&gt; fp = FPGrowth(minSupport=0.2, minConfidence=0.7)</span>
<span class="sd"> &gt;&gt;&gt; fpm = fp.fit(data)</span>
<span class="sd"> &gt;&gt;&gt; fpm.setPredictionCol(&quot;newPrediction&quot;)</span>
<span class="sd"> FPGrowthModel...</span>
<span class="sd"> &gt;&gt;&gt; fpm.freqItemsets.sort(&quot;items&quot;).show(5)</span>
<span class="sd"> +---------+----+</span>
<span class="sd"> | items|freq|</span>
<span class="sd"> +---------+----+</span>
<span class="sd"> | [p]| 2|</span>
<span class="sd"> | [p, r]| 2|</span>
<span class="sd"> |[p, r, z]| 2|</span>
<span class="sd"> | [p, z]| 2|</span>
<span class="sd"> | [q]| 2|</span>
<span class="sd"> +---------+----+</span>
<span class="sd"> only showing top 5 rows</span>
<span class="sd"> &gt;&gt;&gt; fpm.associationRules.sort(&quot;antecedent&quot;, &quot;consequent&quot;).show(5)</span>
<span class="sd"> +----------+----------+----------+----+------------------+</span>
<span class="sd"> |antecedent|consequent|confidence|lift| support|</span>
<span class="sd"> +----------+----------+----------+----+------------------+</span>
<span class="sd"> | [p]| [r]| 1.0| 2.0|0.3333333333333333|</span>
<span class="sd"> | [p]| [z]| 1.0| 1.2|0.3333333333333333|</span>
<span class="sd"> | [p, r]| [z]| 1.0| 1.2|0.3333333333333333|</span>
<span class="sd"> | [p, z]| [r]| 1.0| 2.0|0.3333333333333333|</span>
<span class="sd"> | [q]| [t]| 1.0| 2.0|0.3333333333333333|</span>
<span class="sd"> +----------+----------+----------+----+------------------+</span>
<span class="sd"> only showing top 5 rows</span>
<span class="sd"> &gt;&gt;&gt; new_data = spark.createDataFrame([([&quot;t&quot;, &quot;s&quot;], )], [&quot;items&quot;])</span>
<span class="sd"> &gt;&gt;&gt; sorted(fpm.transform(new_data).first().newPrediction)</span>
<span class="sd"> [&#39;x&#39;, &#39;y&#39;, &#39;z&#39;]</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/fpm_model&quot;</span>
<span class="sd"> &gt;&gt;&gt; fpm.save(model_path)</span>
<span class="sd"> &gt;&gt;&gt; model2 = FPGrowthModel.load(model_path)</span>
<span class="sd"> &gt;&gt;&gt; fpm.transform(data).take(1) == model2.transform(data).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="w"> </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">minSupport</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.3</span><span class="p">,</span>
<span class="n">minConfidence</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.8</span><span class="p">,</span>
<span class="n">itemsCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;items&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">numPartitions</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, \\*, minSupport=0.3, minConfidence=0.8, itemsCol=&quot;items&quot;, \</span>
<span class="sd"> predictionCol=&quot;prediction&quot;, numPartitions=None)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">FPGrowth</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.fpm.FPGrowth&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="FPGrowth.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth.setParams">[docs]</a> <span class="nd">@keyword_only</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="w"> </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">minSupport</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.3</span><span class="p">,</span>
<span class="n">minConfidence</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.8</span><span class="p">,</span>
<span class="n">itemsCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;items&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">numPartitions</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;FPGrowth&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, minSupport=0.3, minConfidence=0.8, itemsCol=&quot;items&quot;, \</span>
<span class="sd"> predictionCol=&quot;prediction&quot;, numPartitions=None)</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>
<div class="viewcode-block" id="FPGrowth.setItemsCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth.setItemsCol">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">setItemsCol</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;FPGrowth&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:`itemsCol`.</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">itemsCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowth.setMinSupport"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth.setMinSupport">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">setMinSupport</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;FPGrowth&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:`minSupport`.</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">minSupport</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowth.setNumPartitions"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth.setNumPartitions">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">setNumPartitions</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;FPGrowth&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:`numPartitions`.</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">numPartitions</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowth.setMinConfidence"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth.setMinConfidence">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">setMinConfidence</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;FPGrowth&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:`minConfidence`.</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">minConfidence</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="FPGrowth.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.FPGrowth.html#pyspark.ml.fpm.FPGrowth.setPredictionCol">[docs]</a> <span class="k">def</span><span class="w"> </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;FPGrowth&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>
<span class="k">def</span><span class="w"> </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="n">FPGrowthModel</span><span class="p">:</span>
<span class="k">return</span> <span class="n">FPGrowthModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">PrefixSpan</span><span class="p">(</span><span class="n">JavaParams</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A parallel PrefixSpan algorithm to mine frequent sequential patterns.</span>
<span class="sd"> The PrefixSpan algorithm is described in J. Pei, et al., PrefixSpan: Mining Sequential Patterns</span>
<span class="sd"> Efficiently by Prefix-Projected Pattern Growth</span>
<span class="sd"> (see `here &lt;https://doi.org/10.1109/ICDE.2001.914830&gt;`_).</span>
<span class="sd"> This class is not yet an Estimator/Transformer, use :py:func:`findFrequentSequentialPatterns`</span>
<span class="sd"> method to run the PrefixSpan algorithm.</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> See `Sequential Pattern Mining (Wikipedia) \</span>
<span class="sd"> &lt;https://en.wikipedia.org/wiki/Sequential_Pattern_Mining&gt;`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.fpm import PrefixSpan</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.sql import Row</span>
<span class="sd"> &gt;&gt;&gt; df = sc.parallelize([Row(sequence=[[1, 2], [3]]),</span>
<span class="sd"> ... Row(sequence=[[1], [3, 2], [1, 2]]),</span>
<span class="sd"> ... Row(sequence=[[1, 2], [5]]),</span>
<span class="sd"> ... Row(sequence=[[6]])]).toDF()</span>
<span class="sd"> &gt;&gt;&gt; prefixSpan = PrefixSpan()</span>
<span class="sd"> &gt;&gt;&gt; prefixSpan.getMaxLocalProjDBSize()</span>
<span class="sd"> 32000000</span>
<span class="sd"> &gt;&gt;&gt; prefixSpan.getSequenceCol()</span>
<span class="sd"> &#39;sequence&#39;</span>
<span class="sd"> &gt;&gt;&gt; prefixSpan.setMinSupport(0.5)</span>
<span class="sd"> PrefixSpan...</span>
<span class="sd"> &gt;&gt;&gt; prefixSpan.setMaxPatternLength(5)</span>
<span class="sd"> PrefixSpan...</span>
<span class="sd"> &gt;&gt;&gt; prefixSpan.findFrequentSequentialPatterns(df).sort(&quot;sequence&quot;).show(truncate=False)</span>
<span class="sd"> +----------+----+</span>
<span class="sd"> |sequence |freq|</span>
<span class="sd"> +----------+----+</span>
<span class="sd"> |[[1]] |3 |</span>
<span class="sd"> |[[1], [3]]|2 |</span>
<span class="sd"> |[[2]] |3 |</span>
<span class="sd"> |[[2, 1]] |3 |</span>
<span class="sd"> |[[3]] |2 |</span>
<span class="sd"> +----------+----+</span>
<span class="sd"> ...</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="n">minSupport</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;minSupport&quot;</span><span class="p">,</span>
<span class="s2">&quot;The minimal support level of the &quot;</span>
<span class="o">+</span> <span class="s2">&quot;sequential pattern. Sequential pattern that appears more than &quot;</span>
<span class="o">+</span> <span class="s2">&quot;(minSupport * size-of-the-dataset) times will be output. Must be &gt;= 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">toFloat</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">maxPatternLength</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;maxPatternLength&quot;</span><span class="p">,</span>
<span class="s2">&quot;The maximal length of the sequential pattern. Must be &gt; 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">toInt</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">maxLocalProjDBSize</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;maxLocalProjDBSize&quot;</span><span class="p">,</span>
<span class="s2">&quot;The maximum number of items (including delimiters used in the &quot;</span>
<span class="o">+</span> <span class="s2">&quot;internal storage format) allowed in a projected database before &quot;</span>
<span class="o">+</span> <span class="s2">&quot;local processing. If a projected database exceeds this size, &quot;</span>
<span class="o">+</span> <span class="s2">&quot;another iteration of distributed prefix growth is run. &quot;</span>
<span class="o">+</span> <span class="s2">&quot;Must be &gt; 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">toInt</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">sequenceCol</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;sequenceCol&quot;</span><span class="p">,</span>
<span class="s2">&quot;The name of the sequence column in &quot;</span>
<span class="o">+</span> <span class="s2">&quot;dataset, rows with nulls in this column are ignored.&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="nd">@keyword_only</span>
<span class="k">def</span><span class="w"> </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">minSupport</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">maxPatternLength</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">maxLocalProjDBSize</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32000000</span><span class="p">,</span>
<span class="n">sequenceCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;sequence&quot;</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, \\*, minSupport=0.1, maxPatternLength=10, maxLocalProjDBSize=32000000, \</span>
<span class="sd"> sequenceCol=&quot;sequence&quot;)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">PrefixSpan</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.fpm.PrefixSpan&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="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span>
<span class="n">minSupport</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">maxPatternLength</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxLocalProjDBSize</span><span class="o">=</span><span class="mi">32000000</span><span class="p">,</span> <span class="n">sequenceCol</span><span class="o">=</span><span class="s2">&quot;sequence&quot;</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="PrefixSpan.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.setParams">[docs]</a> <span class="nd">@keyword_only</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="w"> </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">minSupport</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">maxPatternLength</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">maxLocalProjDBSize</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32000000</span><span class="p">,</span>
<span class="n">sequenceCol</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;sequence&quot;</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;PrefixSpan&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> setParams(self, \\*, minSupport=0.1, maxPatternLength=10, maxLocalProjDBSize=32000000, \</span>
<span class="sd"> sequenceCol=&quot;sequence&quot;)</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>
<div class="viewcode-block" id="PrefixSpan.setMinSupport"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.setMinSupport">[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="w"> </span><span class="nf">setMinSupport</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;PrefixSpan&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:`minSupport`.</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">minSupport</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.getMinSupport"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.getMinSupport">[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="w"> </span><span class="nf">getMinSupport</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 minSupport 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">minSupport</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.setMaxPatternLength"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.setMaxPatternLength">[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="w"> </span><span class="nf">setMaxPatternLength</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;PrefixSpan&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:`maxPatternLength`.</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">maxPatternLength</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.getMaxPatternLength"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.getMaxPatternLength">[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="w"> </span><span class="nf">getMaxPatternLength</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 maxPatternLength 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">maxPatternLength</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.setMaxLocalProjDBSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.setMaxLocalProjDBSize">[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="w"> </span><span class="nf">setMaxLocalProjDBSize</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;PrefixSpan&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:`maxLocalProjDBSize`.</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">maxLocalProjDBSize</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.getMaxLocalProjDBSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.getMaxLocalProjDBSize">[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="w"> </span><span class="nf">getMaxLocalProjDBSize</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 maxLocalProjDBSize 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">maxLocalProjDBSize</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.setSequenceCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.setSequenceCol">[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="w"> </span><span class="nf">setSequenceCol</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;PrefixSpan&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:`sequenceCol`.</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">sequenceCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.getSequenceCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.getSequenceCol">[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="w"> </span><span class="nf">getSequenceCol</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 sequenceCol 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">sequenceCol</span><span class="p">)</span></div>
<div class="viewcode-block" id="PrefixSpan.findFrequentSequentialPatterns"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.fpm.PrefixSpan.html#pyspark.ml.fpm.PrefixSpan.findFrequentSequentialPatterns">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">findFrequentSequentialPatterns</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="n">DataFrame</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Finds the complete set of frequent sequential patterns in the input sequences of itemsets.</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> A dataframe containing a sequence column which is</span>
<span class="sd"> `ArrayType(ArrayType(T))` type, T is the item type for the input dataset.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> A `DataFrame` that contains columns of sequence and corresponding frequency.</span>
<span class="sd"> The schema of it will be:</span>
<span class="sd"> - `sequence: ArrayType(ArrayType(T))` (T is the item type)</span>
<span class="sd"> - `freq: Long`</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">is_remote</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">is_remote</span><span class="p">():</span>
<span class="k">return</span> <span class="n">invoke_helper_relation</span><span class="p">(</span>
<span class="s2">&quot;prefixSpanFindFrequentSequentialPatterns&quot;</span><span class="p">,</span>
<span class="n">dataset</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">getMinSupport</span><span class="p">(),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">getMaxPatternLength</span><span class="p">(),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">getMaxLocalProjDBSize</span><span class="p">(),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">getSequenceCol</span><span class="p">(),</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_transfer_params_to_java</span><span class="p">()</span>
<span class="n">jdf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span><span class="o">.</span><span class="n">findFrequentSequentialPatterns</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">jdf</span><span class="p">,</span> <span class="n">dataset</span><span class="o">.</span><span class="n">sparkSession</span><span class="p">)</span></div></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="w"> </span><span class="nn">doctest</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">pyspark.ml.fpm</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </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">fpm</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.fpm 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="w"> </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="w"> </span><span class="nn">shutil</span><span class="w"> </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 @ 2026 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>