| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.ml.fpm — PySpark 3.3.4 documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../../" 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/language_data.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 async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</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="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../user_guide/index.html">User Guide</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../reference/index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../migration_guide/index.html">Migration Guide</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <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 "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">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="nn">pyspark</span> <span class="kn">import</span> <span class="n">keyword_only</span><span class="p">,</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.util</span> <span class="kn">import</span> <span class="n">JavaMLWritable</span><span class="p">,</span> <span class="n">JavaMLReadable</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</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="nn">pyspark.ml.param.shared</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="nn">py4j.java_gateway</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">"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="k">class</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">"""</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"> """</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">"itemsCol"</span><span class="p">,</span> <span class="s2">"items column name"</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">"minSupport"</span><span class="p">,</span> |
| <span class="s2">"Minimal support level of the frequent pattern. [0.0, 1.0]. "</span> |
| <span class="o">+</span> <span class="s2">"Any pattern that appears more than (minSupport * size-of-the-dataset) "</span> |
| <span class="o">+</span> <span class="s2">"times will be output in the frequent itemsets."</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">"numPartitions"</span><span class="p">,</span> |
| <span class="s2">"Number of partitions (at least 1) used by parallel FP-growth. "</span> |
| <span class="o">+</span> <span class="s2">"By default the param is not set, "</span> |
| <span class="o">+</span> <span class="s2">"and partition number of the input dataset is used."</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">"minConfidence"</span><span class="p">,</span> |
| <span class="s2">"Minimal confidence for generating Association Rule. [0.0, 1.0]. "</span> |
| <span class="o">+</span> <span class="s2">"minConfidence will not affect the mining for frequent itemsets, "</span> |
| <span class="o">+</span> <span class="s2">"but will affect the association rules generation."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_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">"items"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s2">"prediction"</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">getItemsCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of itemsCol or its default value.</span> |
| <span class="sd"> """</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="nf">getMinSupport</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of minSupport or its default value.</span> |
| <span class="sd"> """</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="nf">getNumPartitions</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of :py:attr:`numPartitions` or its default value.</span> |
| <span class="sd"> """</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="nf">getMinConfidence</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of minConfidence or its default value.</span> |
| <span class="sd"> """</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="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">"FPGrowthModel"</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Model fitted by FPGrowth.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| <span class="sd"> """</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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</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">-></span> <span class="s2">"FPGrowthModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`itemsCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</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">-></span> <span class="s2">"FPGrowthModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`minConfidence`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</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"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <span class="nd">@property</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.2.0"</span><span class="p">)</span> |
| <span class="k">def</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">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</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"> """</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">"freqItemsets"</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.2.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">associationRules</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> 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"> """</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">"associationRules"</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="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">"FPGrowth"</span><span class="p">]</span> |
| <span class="p">):</span> |
| <span class="w"> </span><span class="sa">r</span><span class="sd">"""</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 '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"> >>> from pyspark.sql.functions import split</span> |
| <span class="sd"> >>> data = (spark.read</span> |
| <span class="sd"> ... .text("data/mllib/sample_fpgrowth.txt")</span> |
| <span class="sd"> ... .select(split("value", "\s+").alias("items")))</span> |
| <span class="sd"> >>> 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"> >>> fp = FPGrowth(minSupport=0.2, minConfidence=0.7)</span> |
| <span class="sd"> >>> fpm = fp.fit(data)</span> |
| <span class="sd"> >>> fpm.setPredictionCol("newPrediction")</span> |
| <span class="sd"> FPGrowthModel...</span> |
| <span class="sd"> >>> fpm.freqItemsets.sort("items").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"> ...</span> |
| <span class="sd"> >>> fpm.associationRules.sort("antecedent", "consequent").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"> ...</span> |
| <span class="sd"> >>> new_data = spark.createDataFrame([(["t", "s"], )], ["items"])</span> |
| <span class="sd"> >>> sorted(fpm.transform(new_data).first().newPrediction)</span> |
| <span class="sd"> ['x', 'y', 'z']</span> |
| <span class="sd"> >>> model_path = temp_path + "/fpm_model"</span> |
| <span class="sd"> >>> fpm.save(model_path)</span> |
| <span class="sd"> >>> model2 = FPGrowthModel.load(model_path)</span> |
| <span class="sd"> >>> fpm.transform(data).take(1) == model2.transform(data).take(1)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="n">_input_kwargs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> |
| |
| <span class="nd">@keyword_only</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">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">"items"</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">"prediction"</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">"""</span> |
| <span class="sd"> __init__(self, \\*, minSupport=0.3, minConfidence=0.8, itemsCol="items", \</span> |
| <span class="sd"> predictionCol="prediction", numPartitions=None)</span> |
| <span class="sd"> """</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">"org.apache.spark.ml.fpm.FPGrowth"</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">"2.2.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">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">"items"</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">"prediction"</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">-></span> <span class="s2">"FPGrowth"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, minSupport=0.3, minConfidence=0.8, itemsCol="items", \</span> |
| <span class="sd"> predictionCol="prediction", numPartitions=None)</span> |
| <span class="sd"> """</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="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">-></span> <span class="s2">"FPGrowth"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`itemsCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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="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">-></span> <span class="s2">"FPGrowth"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`minSupport`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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="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">-></span> <span class="s2">"FPGrowth"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`numPartitions`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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="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">-></span> <span class="s2">"FPGrowth"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`minConfidence`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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="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">-></span> <span class="s2">"FPGrowth"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">:</span> <span class="s2">"JavaObject"</span><span class="p">)</span> <span class="o">-></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="nc">PrefixSpan</span><span class="p">(</span><span class="n">JavaParams</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 J. Pei, et al., PrefixSpan: Mining Sequential Patterns</span> |
| <span class="sd"> Efficiently by Prefix-Projected Pattern Growth</span> |
| <span class="sd"> (see `here <https://doi.org/10.1109/ICDE.2001.914830">`_).</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"> <https://en.wikipedia.org/wiki/Sequential_Pattern_Mining>`_</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.ml.fpm import PrefixSpan</span> |
| <span class="sd"> >>> from pyspark.sql import Row</span> |
| <span class="sd"> >>> 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"> >>> prefixSpan = PrefixSpan()</span> |
| <span class="sd"> >>> prefixSpan.getMaxLocalProjDBSize()</span> |
| <span class="sd"> 32000000</span> |
| <span class="sd"> >>> prefixSpan.getSequenceCol()</span> |
| <span class="sd"> 'sequence'</span> |
| <span class="sd"> >>> prefixSpan.setMinSupport(0.5)</span> |
| <span class="sd"> PrefixSpan...</span> |
| <span class="sd"> >>> prefixSpan.setMaxPatternLength(5)</span> |
| <span class="sd"> PrefixSpan...</span> |
| <span class="sd"> >>> prefixSpan.findFrequentSequentialPatterns(df).sort("sequence").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"> """</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">"minSupport"</span><span class="p">,</span> |
| <span class="s2">"The minimal support level of the "</span> |
| <span class="o">+</span> <span class="s2">"sequential pattern. Sequential pattern that appears more than "</span> |
| <span class="o">+</span> <span class="s2">"(minSupport * size-of-the-dataset) times will be output. Must be >= 0."</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">"maxPatternLength"</span><span class="p">,</span> |
| <span class="s2">"The maximal length of the sequential pattern. Must be > 0."</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">"maxLocalProjDBSize"</span><span class="p">,</span> |
| <span class="s2">"The maximum number of items (including delimiters used in the "</span> |
| <span class="o">+</span> <span class="s2">"internal storage format) allowed in a projected database before "</span> |
| <span class="o">+</span> <span class="s2">"local processing. If a projected database exceeds this size, "</span> |
| <span class="o">+</span> <span class="s2">"another iteration of distributed prefix growth is run. "</span> |
| <span class="o">+</span> <span class="s2">"Must be > 0."</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">"sequenceCol"</span><span class="p">,</span> |
| <span class="s2">"The name of the sequence column in "</span> |
| <span class="o">+</span> <span class="s2">"dataset, rows with nulls in this column are ignored."</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="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">"sequence"</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, minSupport=0.1, maxPatternLength=10, maxLocalProjDBSize=32000000, \</span> |
| <span class="sd"> sequenceCol="sequence")</span> |
| <span class="sd"> """</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">"org.apache.spark.ml.fpm.PrefixSpan"</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">"sequence"</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">"2.4.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">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">"sequence"</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"PrefixSpan"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, minSupport=0.1, maxPatternLength=10, maxLocalProjDBSize=32000000, \</span> |
| <span class="sd"> sequenceCol="sequence")</span> |
| <span class="sd"> """</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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</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">-></span> <span class="s2">"PrefixSpan"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`minSupport`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMinSupport</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of minSupport or its default value.</span> |
| <span class="sd"> """</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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</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">-></span> <span class="s2">"PrefixSpan"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`maxPatternLength`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMaxPatternLength</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of maxPatternLength or its default value.</span> |
| <span class="sd"> """</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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</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">-></span> <span class="s2">"PrefixSpan"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`maxLocalProjDBSize`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getMaxLocalProjDBSize</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of maxLocalProjDBSize or its default value.</span> |
| <span class="sd"> """</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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</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">-></span> <span class="s2">"PrefixSpan"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`sequenceCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">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">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getSequenceCol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Gets the value of sequenceCol or its default value.</span> |
| <span class="sd"> """</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="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">-></span> <span class="n">DataFrame</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 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"> """</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transfer_params_to_java</span><span class="p">()</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="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">"__main__"</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">pyspark.ml.fpm</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">ml</span><span class="o">.</span><span class="n">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">"local[2]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"ml.fpm tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span> <span class="o">=</span> <span class="n">sc</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"spark"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span> |
| <span class="kn">import</span> <span class="nn">tempfile</span> |
| |
| <span class="n">temp_path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"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="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">rmtree</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
