| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>pyspark.mllib.fpm — PySpark 4.1.0-preview2 documentation</title> |
| |
| |
| |
| <script data-cfasync="false"> |
| document.documentElement.dataset.mode = localStorage.getItem("mode") || ""; |
| document.documentElement.dataset.theme = localStorage.getItem("theme") || "light"; |
| </script> |
| |
| <!-- Loaded before other Sphinx assets --> |
| <link href="../../../_static/styles/theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../../../_static/styles/bootstrap.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| |
| |
| <link href="../../../_static/vendor/fontawesome/6.1.2/css/all.min.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-solid-900.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-brands-400.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-regular-400.woff2" /> |
| |
| <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <!-- Pre-loaded scripts that we'll load fully later --> |
| <link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52" /> |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52" /> |
| |
| <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/clipboard.min.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script>DOCUMENTATION_OPTIONS.pagename = '_modules/pyspark/mllib/fpm';</script> |
| <script> |
| DOCUMENTATION_OPTIONS.theme_switcher_json_url = 'https://spark.apache.org/static/versions.json'; |
| DOCUMENTATION_OPTIONS.theme_switcher_version_match = '4.1.0-preview2'; |
| </script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/mllib/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"> |
| 4.1.0-preview2 <!-- 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"> |
| 4.1.0-preview2 <!-- 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.mllib.fpm</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <h1>Source code for pyspark.mllib.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 "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="kn">import</span><span class="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">Generic</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">NamedTuple</span><span class="p">,</span> <span class="n">TypeVar</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">since</span><span class="p">,</span> <span class="n">SparkContext</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.common</span><span class="w"> </span><span class="kn">import</span> <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">callMLlibFunc</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.util</span><span class="w"> </span><span class="kn">import</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">,</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.core.rdd</span><span class="w"> </span><span class="kn">import</span> <span class="n">RDD</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"FPGrowth"</span><span class="p">,</span> <span class="s2">"FPGrowthModel"</span><span class="p">,</span> <span class="s2">"PrefixSpan"</span><span class="p">,</span> <span class="s2">"PrefixSpanModel"</span><span class="p">]</span> |
| |
| <span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"T"</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="FPGrowthModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowthModel.html#pyspark.mllib.fpm.FPGrowthModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">FPGrowthModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">[</span><span class="s2">"FPGrowthModel"</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A FP-Growth model for mining frequent itemsets</span> |
| <span class="sd"> using the Parallel FP-Growth algorithm.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> data = [["a", "b", "c"], ["a", "b", "d", "e"], ["a", "c", "e"], ["a", "c", "f"]]</span> |
| <span class="sd"> >>> rdd = sc.parallelize(data, 2)</span> |
| <span class="sd"> >>> model = FPGrowth.train(rdd, 0.6, 2)</span> |
| <span class="sd"> >>> sorted(model.freqItemsets().collect())</span> |
| <span class="sd"> [FreqItemset(items=['a'], freq=4), FreqItemset(items=['c'], freq=3), ...</span> |
| <span class="sd"> >>> model_path = temp_path + "/fpm"</span> |
| <span class="sd"> >>> model.save(sc, model_path)</span> |
| <span class="sd"> >>> sameModel = FPGrowthModel.load(sc, model_path)</span> |
| <span class="sd"> >>> sorted(model.freqItemsets().collect()) == sorted(sameModel.freqItemsets().collect())</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="FPGrowthModel.freqItemsets"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowthModel.html#pyspark.mllib.fpm.FPGrowthModel.freqItemsets">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">freqItemsets</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"FPGrowth.FreqItemset"</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the frequent itemsets of this model.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"getFreqItemsets"</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="p">(</span><span class="n">FPGrowth</span><span class="o">.</span><span class="n">FreqItemset</span><span class="p">(</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">])))</span></div> |
| |
| <div class="viewcode-block" id="FPGrowthModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowthModel.html#pyspark.mllib.fpm.FPGrowthModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"FPGrowthModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Load a model from the given path.</span> |
| <span class="sd"> """</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">wrapper</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">api</span><span class="o">.</span><span class="n">python</span><span class="o">.</span><span class="n">FPGrowthModelWrapper</span><span class="p">(</span><span class="n">model</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">FPGrowthModel</span><span class="p">(</span><span class="n">wrapper</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="FPGrowth"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowth.html#pyspark.mllib.fpm.FPGrowth">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">FPGrowth</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A Parallel FP-growth algorithm to mine frequent itemsets.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="FPGrowth.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowth.html#pyspark.mllib.fpm.FPGrowth.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">]],</span> <span class="n">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">numPartitions</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"FPGrowthModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Computes an FP-Growth model that contains frequent itemsets.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The input data set, each element contains a transaction.</span> |
| <span class="sd"> minSupport : float, optional</span> |
| <span class="sd"> The minimal support level.</span> |
| <span class="sd"> (default: 0.3)</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> The number of partitions used by parallel FP-growth. A value</span> |
| <span class="sd"> of -1 will use the same number as input data.</span> |
| <span class="sd"> (default: -1)</span> |
| <span class="sd"> """</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"trainFPGrowthModel"</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">minSupport</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">numPartitions</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">FPGrowthModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div> |
| |
| <span class="k">class</span><span class="w"> </span><span class="nc">FreqItemset</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Represents an (items, freq) tuple.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">items</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Any</span><span class="p">]</span> |
| <span class="n">freq</span><span class="p">:</span> <span class="nb">int</span></div> |
| |
| |
| <div class="viewcode-block" id="PrefixSpanModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpanModel.html#pyspark.mllib.fpm.PrefixSpanModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">PrefixSpanModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">Generic</span><span class="p">[</span><span class="n">T</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Model fitted by PrefixSpan</span> |
| |
| <span class="sd"> .. versionadded:: 1.6.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... [["a", "b"], ["c"]],</span> |
| <span class="sd"> ... [["a"], ["c", "b"], ["a", "b"]],</span> |
| <span class="sd"> ... [["a", "b"], ["e"]],</span> |
| <span class="sd"> ... [["f"]]]</span> |
| <span class="sd"> >>> rdd = sc.parallelize(data, 2)</span> |
| <span class="sd"> >>> model = PrefixSpan.train(rdd)</span> |
| <span class="sd"> >>> sorted(model.freqSequences().collect())</span> |
| <span class="sd"> [FreqSequence(sequence=[['a']], freq=3), FreqSequence(sequence=[['a'], ['a']], freq=1), ...</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="PrefixSpanModel.freqSequences"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpanModel.html#pyspark.mllib.fpm.PrefixSpanModel.freqSequences">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.6.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">freqSequences</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"PrefixSpan.FreqSequence"</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""Gets frequent sequences"""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"getFreqSequences"</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">PrefixSpan</span><span class="o">.</span><span class="n">FreqSequence</span><span class="p">(</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="PrefixSpan"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpan.html#pyspark.mllib.fpm.PrefixSpan">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">PrefixSpan</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A parallel PrefixSpan algorithm to mine frequent sequential patterns.</span> |
| <span class="sd"> The PrefixSpan algorithm is described in Jian Pei et al (2001) [1]_</span> |
| |
| <span class="sd"> .. versionadded:: 1.6.0</span> |
| |
| <span class="sd"> .. [1] Jian Pei et al.,</span> |
| <span class="sd"> "PrefixSpan,: mining sequential patterns efficiently by prefix-projected pattern growth,"</span> |
| <span class="sd"> Proceedings 17th International Conference on Data Engineering, Heidelberg,</span> |
| <span class="sd"> Germany, 2001, pp. 215-224,</span> |
| <span class="sd"> doi: https://doi.org/10.1109/ICDE.2001.914830</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="PrefixSpan.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpan.html#pyspark.mllib.fpm.PrefixSpan.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> |
| <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">]]],</span> |
| <span class="n">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="p">)</span> <span class="o">-></span> <span class="n">PrefixSpanModel</span><span class="p">[</span><span class="n">T</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Finds the complete set of frequent sequential patterns in the</span> |
| <span class="sd"> input sequences of itemsets.</span> |
| |
| <span class="sd"> .. versionadded:: 1.6.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The input data set, each element contains a sequence of</span> |
| <span class="sd"> itemsets.</span> |
| <span class="sd"> minSupport : float, optional</span> |
| <span class="sd"> The minimal support level of the sequential pattern, any</span> |
| <span class="sd"> pattern that appears more than (minSupport *</span> |
| <span class="sd"> size-of-the-dataset) times will be output.</span> |
| <span class="sd"> (default: 0.1)</span> |
| <span class="sd"> maxPatternLength : int, optional</span> |
| <span class="sd"> The maximal length of the sequential pattern, any pattern</span> |
| <span class="sd"> that appears less than maxPatternLength will be output.</span> |
| <span class="sd"> (default: 10)</span> |
| <span class="sd"> maxLocalProjDBSize : int, optional</span> |
| <span class="sd"> The maximum number of items (including delimiters used in the</span> |
| <span class="sd"> internal storage format) allowed in a projected database before</span> |
| <span class="sd"> local processing. If a projected database exceeds this size,</span> |
| <span class="sd"> another iteration of distributed prefix growth is run.</span> |
| <span class="sd"> (default: 32000000)</span> |
| <span class="sd"> """</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainPrefixSpanModel"</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">minSupport</span><span class="p">,</span> <span class="n">maxPatternLength</span><span class="p">,</span> <span class="n">maxLocalProjDBSize</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">PrefixSpanModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div> |
| |
| <span class="k">class</span><span class="w"> </span><span class="nc">FreqSequence</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Represents a (sequence, freq) tuple.</span> |
| |
| <span class="sd"> .. versionadded:: 1.6.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">sequence</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">Any</span><span class="p">]]</span> |
| <span class="n">freq</span><span class="p">:</span> <span class="nb">int</span></div> |
| |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">doctest</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="kn">import</span><span class="w"> </span><span class="nn">pyspark.mllib.fpm</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">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="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"mllib.fpm tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span> |
| <span class="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">"temp_path"</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> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </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 @ 2025 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> |
