| |
| <!DOCTYPE html> |
| <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]--> |
| <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]--> |
| <!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> |
| <title>Frequent Pattern Mining - Spark 3.3.0 Documentation</title> |
| |
| |
| |
| |
| <link rel="stylesheet" href="css/bootstrap.min.css"> |
| <style> |
| body { |
| padding-top: 60px; |
| padding-bottom: 40px; |
| } |
| </style> |
| <meta name="viewport" content="width=device-width"> |
| <link rel="stylesheet" href="css/main.css"> |
| |
| <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script> |
| |
| <link rel="stylesheet" href="css/pygments-default.css"> |
| <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/docsearch.js@2/dist/cdn/docsearch.min.css" /> |
| <link rel="stylesheet" href="css/docsearch.css"> |
| |
| <!-- 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> |
| <!--[if lt IE 7]> |
| <p class="chromeframe">You are using an outdated browser. <a href="https://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p> |
| <![endif]--> |
| |
| <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html --> |
| |
| <nav class="navbar fixed-top navbar-expand-md navbar-light bg-light" id="topbar"> |
| <div class="container"> |
| <div class="navbar-header"> |
| <div class="navbar-brand"><a href="index.html"> |
| <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">3.3.0</span> |
| </div> |
| </div> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" |
| data-target="#navbarCollapse" aria-controls="navbarCollapse" |
| aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| <div class="collapse navbar-collapse" id="navbarCollapse"> |
| <ul class="navbar-nav"> |
| <!--TODO(andyk): Add class="active" attribute to li some how.--> |
| <li class="nav-item"><a href="index.html" class="nav-link">Overview</a></li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarQuickStart" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Programming Guides</a> |
| <div class="dropdown-menu" aria-labelledby="navbarQuickStart"> |
| <a class="dropdown-item" href="quick-start.html">Quick Start</a> |
| <a class="dropdown-item" href="rdd-programming-guide.html">RDDs, Accumulators, Broadcasts Vars</a> |
| <a class="dropdown-item" href="sql-programming-guide.html">SQL, DataFrames, and Datasets</a> |
| <a class="dropdown-item" href="structured-streaming-programming-guide.html">Structured Streaming</a> |
| <a class="dropdown-item" href="streaming-programming-guide.html">Spark Streaming (DStreams)</a> |
| <a class="dropdown-item" href="ml-guide.html">MLlib (Machine Learning)</a> |
| <a class="dropdown-item" href="graphx-programming-guide.html">GraphX (Graph Processing)</a> |
| <a class="dropdown-item" href="sparkr.html">SparkR (R on Spark)</a> |
| <a class="dropdown-item" href="api/python/getting_started/index.html">PySpark (Python on Spark)</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarAPIDocs" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">API Docs</a> |
| <div class="dropdown-menu" aria-labelledby="navbarAPIDocs"> |
| <a class="dropdown-item" href="api/scala/org/apache/spark/index.html">Scala</a> |
| <a class="dropdown-item" href="api/java/index.html">Java</a> |
| <a class="dropdown-item" href="api/python/index.html">Python</a> |
| <a class="dropdown-item" href="api/R/index.html">R</a> |
| <a class="dropdown-item" href="api/sql/index.html">SQL, Built-in Functions</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarDeploying" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Deploying</a> |
| <div class="dropdown-menu" aria-labelledby="navbarDeploying"> |
| <a class="dropdown-item" href="cluster-overview.html">Overview</a> |
| <a class="dropdown-item" href="submitting-applications.html">Submitting Applications</a> |
| <div class="dropdown-divider"></div> |
| <a class="dropdown-item" href="spark-standalone.html">Spark Standalone</a> |
| <a class="dropdown-item" href="running-on-mesos.html">Mesos</a> |
| <a class="dropdown-item" href="running-on-yarn.html">YARN</a> |
| <a class="dropdown-item" href="running-on-kubernetes.html">Kubernetes</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarMore" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a> |
| <div class="dropdown-menu" aria-labelledby="navbarMore"> |
| <a class="dropdown-item" href="configuration.html">Configuration</a> |
| <a class="dropdown-item" href="monitoring.html">Monitoring</a> |
| <a class="dropdown-item" href="tuning.html">Tuning Guide</a> |
| <a class="dropdown-item" href="job-scheduling.html">Job Scheduling</a> |
| <a class="dropdown-item" href="security.html">Security</a> |
| <a class="dropdown-item" href="hardware-provisioning.html">Hardware Provisioning</a> |
| <a class="dropdown-item" href="migration-guide.html">Migration Guide</a> |
| <div class="dropdown-divider"></div> |
| <a class="dropdown-item" href="building-spark.html">Building Spark</a> |
| <a class="dropdown-item" href="https://spark.apache.org/contributing.html">Contributing to Spark</a> |
| <a class="dropdown-item" href="https://spark.apache.org/third-party-projects.html">Third Party Projects</a> |
| </div> |
| </li> |
| |
| <li class="nav-item"> |
| <input type="text" id="docsearch-input" placeholder="Search the docs…"> |
| </li> |
| </ul> |
| <!--<span class="navbar-text navbar-right"><span class="version-text">v3.3.0</span></span>--> |
| </div> |
| </div> |
| </nav> |
| |
| <div class="container-wrapper"> |
| |
| |
| |
| <div class="left-menu-wrapper"> |
| <div class="left-menu"> |
| <h3><a href="ml-guide.html">MLlib: Main Guide</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="ml-statistics.html"> |
| |
| Basic statistics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-datasource.html"> |
| |
| Data sources |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-pipeline.html"> |
| |
| Pipelines |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-features.html"> |
| |
| Extracting, transforming and selecting features |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-classification-regression.html"> |
| |
| Classification and Regression |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-clustering.html"> |
| |
| Clustering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-collaborative-filtering.html"> |
| |
| Collaborative filtering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-frequent-pattern-mining.html"> |
| |
| Frequent Pattern Mining |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-tuning.html"> |
| |
| Model selection and tuning |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-advanced.html"> |
| |
| Advanced topics |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| <h3><a href="mllib-guide.html">MLlib: RDD-based API Guide</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="mllib-data-types.html"> |
| |
| Data types |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-statistics.html"> |
| |
| Basic statistics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-classification-regression.html"> |
| |
| Classification and regression |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-collaborative-filtering.html"> |
| |
| Collaborative filtering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-clustering.html"> |
| |
| Clustering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-dimensionality-reduction.html"> |
| |
| Dimensionality reduction |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-feature-extraction.html"> |
| |
| Feature extraction and transformation |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-frequent-pattern-mining.html"> |
| |
| Frequent pattern mining |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-evaluation-metrics.html"> |
| |
| Evaluation metrics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-pmml-model-export.html"> |
| |
| PMML model export |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-optimization.html"> |
| |
| Optimization (developer) |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| </div> |
| </div> |
| |
| <input id="nav-trigger" class="nav-trigger" checked type="checkbox"> |
| <label for="nav-trigger"></label> |
| <div class="content-with-sidebar mr-3" id="content"> |
| |
| <h1 class="title">Frequent Pattern Mining</h1> |
| |
| |
| <p>Mining frequent items, itemsets, subsequences, or other substructures is usually among the |
| first steps to analyze a large-scale dataset, which has been an active research topic in |
| data mining for years. |
| We refer users to Wikipedia’s <a href="http://en.wikipedia.org/wiki/Association_rule_learning">association rule learning</a> |
| for more information.</p> |
| |
| <p><strong>Table of Contents</strong></p> |
| |
| <ul id="markdown-toc"> |
| <li><a href="#fp-growth" id="markdown-toc-fp-growth">FP-Growth</a></li> |
| <li><a href="#prefixspan" id="markdown-toc-prefixspan">PrefixSpan</a></li> |
| </ul> |
| |
| <h2 id="fp-growth">FP-Growth</h2> |
| |
| <p>The FP-growth algorithm is described in the paper |
| <a href="https://doi.org/10.1145/335191.335372">Han et al., Mining frequent patterns without candidate generation</a>, |
| where “FP” stands for frequent pattern. |
| Given a dataset of transactions, the first step of FP-growth is to calculate item frequencies and identify frequent items. |
| Different from <a href="http://en.wikipedia.org/wiki/Apriori_algorithm">Apriori-like</a> algorithms designed for the same purpose, |
| the second step of FP-growth uses a suffix tree (FP-tree) structure to encode transactions without generating candidate sets |
| explicitly, which are usually expensive to generate. |
| After the second step, the frequent itemsets can be extracted from the FP-tree. |
| In <code class="language-plaintext highlighter-rouge">spark.mllib</code>, we implemented a parallel version of FP-growth called PFP, |
| as described in <a href="https://doi.org/10.1145/1454008.1454027">Li et al., PFP: Parallel FP-growth for query recommendation</a>. |
| PFP distributes the work of growing FP-trees based on the suffixes of transactions, |
| and hence is more scalable than a single-machine implementation. |
| We refer users to the papers for more details.</p> |
| |
| <p>FP-growth operates on <em>itemsets</em>. An itemset is an unordered collection of unique items. Spark does not have a <em>set</em> type, so itemsets are represented as arrays.</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">spark.ml</code>’s FP-growth implementation takes the following (hyper-)parameters:</p> |
| |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">minSupport</code>: the minimum support for an itemset to be identified as frequent. |
| For example, if an item appears 3 out of 5 transactions, it has a support of 3/5=0.6.</li> |
| <li><code class="language-plaintext highlighter-rouge">minConfidence</code>: minimum confidence for generating Association Rule. Confidence is an indication of how often an |
| association rule has been found to be true. For example, if in the transactions itemset <code class="language-plaintext highlighter-rouge">X</code> appears 4 times, <code class="language-plaintext highlighter-rouge">X</code> |
| and <code class="language-plaintext highlighter-rouge">Y</code> co-occur only 2 times, the confidence for the rule <code class="language-plaintext highlighter-rouge">X => Y</code> is then 2/4 = 0.5. The parameter will not |
| affect the mining for frequent itemsets, but specify the minimum confidence for generating association rules |
| from frequent itemsets.</li> |
| <li><code class="language-plaintext highlighter-rouge">numPartitions</code>: the number of partitions used to distribute the work. By default the param is not set, and |
| number of partitions of the input dataset is used.</li> |
| </ul> |
| |
| <p>The <code class="language-plaintext highlighter-rouge">FPGrowthModel</code> provides:</p> |
| |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">freqItemsets</code>: frequent itemsets in the format of a DataFrame with the following columns: |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">items: array</code>: A given itemset.</li> |
| <li><code class="language-plaintext highlighter-rouge">freq: long</code>: A count of how many times this itemset was seen, given the configured model parameters.</li> |
| </ul> |
| </li> |
| <li><code class="language-plaintext highlighter-rouge">associationRules</code>: association rules generated with confidence above <code class="language-plaintext highlighter-rouge">minConfidence</code>, in the format of a DataFrame with the following columns: |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">antecedent: array</code>: The itemset that is the hypothesis of the association rule.</li> |
| <li><code class="language-plaintext highlighter-rouge">consequent: array</code>: An itemset that always contains a single element representing the conclusion of the association rule.</li> |
| <li><code class="language-plaintext highlighter-rouge">confidence: double</code>: Refer to <code class="language-plaintext highlighter-rouge">minConfidence</code> above for a definition of <code class="language-plaintext highlighter-rouge">confidence</code>.</li> |
| <li><code class="language-plaintext highlighter-rouge">lift: double</code>: A measure of how well the antecedent predicts the consequent, calculated as <code class="language-plaintext highlighter-rouge">support(antecedent U consequent) / (support(antecedent) x support(consequent))</code></li> |
| <li><code class="language-plaintext highlighter-rouge">support: double</code>: Refer to <code class="language-plaintext highlighter-rouge">minSupport</code> above for a definition of <code class="language-plaintext highlighter-rouge">support</code>.</li> |
| </ul> |
| </li> |
| <li><code class="language-plaintext highlighter-rouge">transform</code>: For each transaction in <code class="language-plaintext highlighter-rouge">itemsCol</code>, the <code class="language-plaintext highlighter-rouge">transform</code> method will compare its items against the antecedents |
| of each association rule. If the record contains all the antecedents of a specific association rule, the rule |
| will be considered as applicable and its consequents will be added to the prediction result. The transform |
| method will summarize the consequents from all the applicable rules as prediction. The prediction column has |
| the same data type as <code class="language-plaintext highlighter-rouge">itemsCol</code> and does not contain existing items in the <code class="language-plaintext highlighter-rouge">itemsCol</code>.</li> |
| </ul> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/fpm/FPGrowth.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.ml.fpm.FPGrowth</span> |
| |
| <span class="k">val</span> <span class="nv">dataset</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">createDataset</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span> |
| <span class="s">"1 2 5"</span><span class="o">,</span> |
| <span class="s">"1 2 3 5"</span><span class="o">,</span> |
| <span class="s">"1 2"</span><span class="o">)</span> |
| <span class="o">).</span><span class="py">map</span><span class="o">(</span><span class="n">t</span> <span class="k">=></span> <span class="nv">t</span><span class="o">.</span><span class="py">split</span><span class="o">(</span><span class="s">" "</span><span class="o">)).</span><span class="py">toDF</span><span class="o">(</span><span class="s">"items"</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="nv">fpgrowth</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">FPGrowth</span><span class="o">().</span><span class="py">setItemsCol</span><span class="o">(</span><span class="s">"items"</span><span class="o">).</span><span class="py">setMinSupport</span><span class="o">(</span><span class="mf">0.5</span><span class="o">).</span><span class="py">setMinConfidence</span><span class="o">(</span><span class="mf">0.6</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">fpgrowth</span><span class="o">.</span><span class="py">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// Display frequent itemsets.</span> |
| <span class="nv">model</span><span class="o">.</span><span class="py">freqItemsets</span><span class="o">.</span><span class="py">show</span><span class="o">()</span> |
| |
| <span class="c1">// Display generated association rules.</span> |
| <span class="nv">model</span><span class="o">.</span><span class="py">associationRules</span><span class="o">.</span><span class="py">show</span><span class="o">()</span> |
| |
| <span class="c1">// transform examines the input items against all the association rules and summarize the</span> |
| <span class="c1">// consequents as prediction</span> |
| <span class="nv">model</span><span class="o">.</span><span class="py">transform</span><span class="o">(</span><span class="n">dataset</span><span class="o">).</span><span class="py">show</span><span class="o">()</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/FPGrowthExample.scala" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="java"> |
| <p>Refer to the <a href="api/java/org/apache/spark/ml/fpm/FPGrowth.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">java.util.Arrays</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">java.util.List</span><span class="o">;</span> |
| |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.fpm.FPGrowth</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.fpm.FPGrowthModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Dataset</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Row</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.RowFactory</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.SparkSession</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.*</span><span class="o">;</span> |
| |
| <span class="nc">List</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="s">"1 2 5"</span><span class="o">.</span><span class="na">split</span><span class="o">(</span><span class="s">" "</span><span class="o">))),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="s">"1 2 3 5"</span><span class="o">.</span><span class="na">split</span><span class="o">(</span><span class="s">" "</span><span class="o">))),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="s">"1 2"</span><span class="o">.</span><span class="na">split</span><span class="o">(</span><span class="s">" "</span><span class="o">)))</span> |
| <span class="o">);</span> |
| <span class="nc">StructType</span> <span class="n">schema</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">StructType</span><span class="o">(</span><span class="k">new</span> <span class="nc">StructField</span><span class="o">[]{</span> <span class="k">new</span> <span class="nc">StructField</span><span class="o">(</span> |
| <span class="s">"items"</span><span class="o">,</span> <span class="k">new</span> <span class="nc">ArrayType</span><span class="o">(</span><span class="nc">DataTypes</span><span class="o">.</span><span class="na">StringType</span><span class="o">,</span> <span class="kc">true</span><span class="o">),</span> <span class="kc">false</span><span class="o">,</span> <span class="nc">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">())</span> |
| <span class="o">});</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">itemsDF</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">data</span><span class="o">,</span> <span class="n">schema</span><span class="o">);</span> |
| |
| <span class="nc">FPGrowthModel</span> <span class="n">model</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">FPGrowth</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setItemsCol</span><span class="o">(</span><span class="s">"items"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMinSupport</span><span class="o">(</span><span class="mf">0.5</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMinConfidence</span><span class="o">(</span><span class="mf">0.6</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">itemsDF</span><span class="o">);</span> |
| |
| <span class="c1">// Display frequent itemsets.</span> |
| <span class="n">model</span><span class="o">.</span><span class="na">freqItemsets</span><span class="o">().</span><span class="na">show</span><span class="o">();</span> |
| |
| <span class="c1">// Display generated association rules.</span> |
| <span class="n">model</span><span class="o">.</span><span class="na">associationRules</span><span class="o">().</span><span class="na">show</span><span class="o">();</span> |
| |
| <span class="c1">// transform examines the input items against all the association rules and summarize the</span> |
| <span class="c1">// consequents as prediction</span> |
| <span class="n">model</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">itemsDF</span><span class="o">).</span><span class="na">show</span><span class="o">();</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaFPGrowthExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.fpm.FPGrowth.html">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.fpm</span> <span class="kn">import</span> <span class="n">FPGrowth</span> |
| |
| <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="p">.</span><span class="n">createDataFrame</span><span class="p">([</span> |
| <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">5</span><span class="p">]),</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">5</span><span class="p">]),</span> |
| <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">])</span> |
| <span class="p">],</span> <span class="p">[</span><span class="s">"id"</span><span class="p">,</span> <span class="s">"items"</span><span class="p">])</span> |
| |
| <span class="n">fpGrowth</span> <span class="o">=</span> <span class="n">FPGrowth</span><span class="p">(</span><span class="n">itemsCol</span><span class="o">=</span><span class="s">"items"</span><span class="p">,</span> <span class="n">minSupport</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">minConfidence</span><span class="o">=</span><span class="mf">0.6</span><span class="p">)</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">fpGrowth</span><span class="p">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">)</span> |
| |
| <span class="c1"># Display frequent itemsets. |
| </span><span class="n">model</span><span class="p">.</span><span class="n">freqItemsets</span><span class="p">.</span><span class="n">show</span><span class="p">()</span> |
| |
| <span class="c1"># Display generated association rules. |
| </span><span class="n">model</span><span class="p">.</span><span class="n">associationRules</span><span class="p">.</span><span class="n">show</span><span class="p">()</span> |
| |
| <span class="c1"># transform examines the input items against all the association rules and summarize the |
| # consequents as prediction |
| </span><span class="n">model</span><span class="p">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">).</span><span class="n">show</span><span class="p">()</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/fpgrowth_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/spark.fpGrowth.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="c1"># Load training data</span><span class="w"> |
| |
| </span><span class="n">df</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">selectExpr</span><span class="p">(</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data.frame</span><span class="p">(</span><span class="n">rawItems</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="nf">c</span><span class="p">(</span><span class="w"> |
| </span><span class="s2">"1,2,5"</span><span class="p">,</span><span class="w"> </span><span class="s2">"1,2,3,5"</span><span class="p">,</span><span class="w"> </span><span class="s2">"1,2"</span><span class="w"> |
| </span><span class="p">))),</span><span class="w"> </span><span class="s2">"split(rawItems, ',') AS items"</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="n">fpm</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.fpGrowth</span><span class="p">(</span><span class="n">df</span><span class="p">,</span><span class="w"> </span><span class="n">itemsCol</span><span class="o">=</span><span class="s2">"items"</span><span class="p">,</span><span class="w"> </span><span class="n">minSupport</span><span class="o">=</span><span class="m">0.5</span><span class="p">,</span><span class="w"> </span><span class="n">minConfidence</span><span class="o">=</span><span class="m">0.6</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Extracting frequent itemsets</span><span class="w"> |
| |
| </span><span class="n">spark.freqItemsets</span><span class="p">(</span><span class="n">fpm</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Extracting association rules</span><span class="w"> |
| |
| </span><span class="n">spark.associationRules</span><span class="p">(</span><span class="n">fpm</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Predict uses association rules to and combines possible consequents</span><span class="w"> |
| |
| </span><span class="n">predict</span><span class="p">(</span><span class="n">fpm</span><span class="p">,</span><span class="w"> </span><span class="n">df</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/fpm.R" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| <h2 id="prefixspan">PrefixSpan</h2> |
| |
| <p>PrefixSpan is a sequential pattern mining algorithm described in |
| <a href="https://doi.org/10.1109%2FTKDE.2004.77">Pei et al., Mining Sequential Patterns by Pattern-Growth: The |
| PrefixSpan Approach</a>. We refer |
| the reader to the referenced paper for formalizing the sequential |
| pattern mining problem.</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">spark.ml</code>’s PrefixSpan implementation takes the following parameters:</p> |
| |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">minSupport</code>: the minimum support required to be considered a frequent |
| sequential pattern.</li> |
| <li><code class="language-plaintext highlighter-rouge">maxPatternLength</code>: the maximum length of a frequent sequential |
| pattern. Any frequent pattern exceeding this length will not be |
| included in the results.</li> |
| <li><code class="language-plaintext highlighter-rouge">maxLocalProjDBSize</code>: the maximum number of items allowed in a |
| prefix-projected database before local iterative processing of the |
| projected database begins. This parameter should be tuned with respect |
| to the size of your executors.</li> |
| <li><code class="language-plaintext highlighter-rouge">sequenceCol</code>: the name of the sequence column in dataset (default “sequence”), rows with |
| nulls in this column are ignored.</li> |
| </ul> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/fpm/PrefixSpan.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.ml.fpm.PrefixSpan</span> |
| |
| <span class="k">val</span> <span class="nv">smallTestData</span> <span class="k">=</span> <span class="nc">Seq</span><span class="o">(</span> |
| <span class="nc">Seq</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">2</span><span class="o">),</span> <span class="nc">Seq</span><span class="o">(</span><span class="mi">3</span><span class="o">)),</span> |
| <span class="nc">Seq</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span><span class="mi">1</span><span class="o">),</span> <span class="nc">Seq</span><span class="o">(</span><span class="mi">3</span><span class="o">,</span> <span class="mi">2</span><span class="o">),</span> <span class="nc">Seq</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">2</span><span class="o">)),</span> |
| <span class="nc">Seq</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">2</span><span class="o">),</span> <span class="nc">Seq</span><span class="o">(</span><span class="mi">5</span><span class="o">)),</span> |
| <span class="nc">Seq</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span><span class="mi">6</span><span class="o">)))</span> |
| |
| <span class="k">val</span> <span class="nv">df</span> <span class="k">=</span> <span class="nv">smallTestData</span><span class="o">.</span><span class="py">toDF</span><span class="o">(</span><span class="s">"sequence"</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">result</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">PrefixSpan</span><span class="o">()</span> |
| <span class="o">.</span><span class="py">setMinSupport</span><span class="o">(</span><span class="mf">0.5</span><span class="o">)</span> |
| <span class="o">.</span><span class="py">setMaxPatternLength</span><span class="o">(</span><span class="mi">5</span><span class="o">)</span> |
| <span class="o">.</span><span class="py">setMaxLocalProjDBSize</span><span class="o">(</span><span class="mi">32000000</span><span class="o">)</span> |
| <span class="o">.</span><span class="py">findFrequentSequentialPatterns</span><span class="o">(</span><span class="n">df</span><span class="o">)</span> |
| <span class="o">.</span><span class="py">show</span><span class="o">()</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/PrefixSpanExample.scala" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="java"> |
| <p>Refer to the <a href="api/java/org/apache/spark/ml/fpm/PrefixSpan.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">java.util.Arrays</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">java.util.List</span><span class="o">;</span> |
| |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.fpm.PrefixSpan</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Dataset</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Row</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.RowFactory</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.SparkSession</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.*</span><span class="o">;</span> |
| |
| <span class="nc">List</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">2</span><span class="o">),</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">3</span><span class="o">))),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">1</span><span class="o">),</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">3</span><span class="o">,</span> <span class="mi">2</span><span class="o">),</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span><span class="mi">2</span><span class="o">))),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">2</span><span class="o">),</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">5</span><span class="o">))),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="mi">6</span><span class="o">)))</span> |
| <span class="o">);</span> |
| <span class="nc">StructType</span> <span class="n">schema</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">StructType</span><span class="o">(</span><span class="k">new</span> <span class="nc">StructField</span><span class="o">[]{</span> <span class="k">new</span> <span class="nc">StructField</span><span class="o">(</span> |
| <span class="s">"sequence"</span><span class="o">,</span> <span class="k">new</span> <span class="nc">ArrayType</span><span class="o">(</span><span class="k">new</span> <span class="nc">ArrayType</span><span class="o">(</span><span class="nc">DataTypes</span><span class="o">.</span><span class="na">IntegerType</span><span class="o">,</span> <span class="kc">true</span><span class="o">),</span> <span class="kc">true</span><span class="o">),</span> |
| <span class="kc">false</span><span class="o">,</span> <span class="nc">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">())</span> |
| <span class="o">});</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">sequenceDF</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">data</span><span class="o">,</span> <span class="n">schema</span><span class="o">);</span> |
| |
| <span class="nc">PrefixSpan</span> <span class="n">prefixSpan</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">PrefixSpan</span><span class="o">().</span><span class="na">setMinSupport</span><span class="o">(</span><span class="mf">0.5</span><span class="o">).</span><span class="na">setMaxPatternLength</span><span class="o">(</span><span class="mi">5</span><span class="o">);</span> |
| |
| <span class="c1">// Finding frequent sequential patterns</span> |
| <span class="n">prefixSpan</span><span class="o">.</span><span class="na">findFrequentSequentialPatterns</span><span class="o">(</span><span class="n">sequenceDF</span><span class="o">).</span><span class="na">show</span><span class="o">();</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaPrefixSpanExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.fpm.PrefixSpan">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.fpm</span> <span class="kn">import</span> <span class="n">PrefixSpan</span> |
| |
| <span class="n">df</span> <span class="o">=</span> <span class="n">sc</span><span class="p">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Row</span><span class="p">(</span><span class="n">sequence</span><span class="o">=</span><span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span> <span class="p">[</span><span class="mi">3</span><span class="p">]]),</span> |
| <span class="n">Row</span><span class="p">(</span><span class="n">sequence</span><span class="o">=</span><span class="p">[[</span><span class="mi">1</span><span class="p">],</span> <span class="p">[</span><span class="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">]]),</span> |
| <span class="n">Row</span><span class="p">(</span><span class="n">sequence</span><span class="o">=</span><span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span> <span class="p">[</span><span class="mi">5</span><span class="p">]]),</span> |
| <span class="n">Row</span><span class="p">(</span><span class="n">sequence</span><span class="o">=</span><span class="p">[[</span><span class="mi">6</span><span class="p">]])]).</span><span class="n">toDF</span><span class="p">()</span> |
| |
| <span class="n">prefixSpan</span> <span class="o">=</span> <span class="n">PrefixSpan</span><span class="p">(</span><span class="n">minSupport</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">maxPatternLength</span><span class="o">=</span><span class="mi">5</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="c1"># Find frequent sequential patterns. |
| </span><span class="n">prefixSpan</span><span class="p">.</span><span class="n">findFrequentSequentialPatterns</span><span class="p">(</span><span class="n">df</span><span class="p">).</span><span class="n">show</span><span class="p">()</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/prefixspan_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/spark.prefixSpan.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="c1"># Load training data</span><span class="w"> |
| |
| </span><span class="n">df</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">createDataFrame</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="m">1L</span><span class="p">,</span><span class="w"> </span><span class="m">2L</span><span class="p">),</span><span class="w"> </span><span class="nf">list</span><span class="p">(</span><span class="m">3L</span><span class="p">))),</span><span class="w"> |
| </span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="m">1L</span><span class="p">),</span><span class="w"> </span><span class="nf">list</span><span class="p">(</span><span class="m">3L</span><span class="p">,</span><span class="w"> </span><span class="m">2L</span><span class="p">),</span><span class="w"> </span><span class="nf">list</span><span class="p">(</span><span class="m">1L</span><span class="p">,</span><span class="w"> </span><span class="m">2L</span><span class="p">))),</span><span class="w"> |
| </span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="m">1L</span><span class="p">,</span><span class="w"> </span><span class="m">2L</span><span class="p">),</span><span class="w"> </span><span class="nf">list</span><span class="p">(</span><span class="m">5L</span><span class="p">))),</span><span class="w"> |
| </span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="m">6L</span><span class="p">)))),</span><span class="w"> |
| </span><span class="n">schema</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="nf">c</span><span class="p">(</span><span class="s2">"sequence"</span><span class="p">))</span><span class="w"> |
| |
| </span><span class="c1"># Finding frequent sequential patterns</span><span class="w"> |
| </span><span class="n">frequency</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.findFrequentSequentialPatterns</span><span class="p">(</span><span class="n">df</span><span class="p">,</span><span class="w"> </span><span class="n">minSupport</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">0.5</span><span class="p">,</span><span class="w"> </span><span class="n">maxPatternLength</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">5L</span><span class="p">,</span><span class="w"> |
| </span><span class="n">maxLocalProjDBSize</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">32000000L</span><span class="p">)</span><span class="w"> |
| </span><span class="n">showDF</span><span class="p">(</span><span class="n">frequency</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/prefixSpan.R" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| |
| <!-- /container --> |
| </div> |
| |
| <script src="js/vendor/jquery-3.5.1.min.js"></script> |
| <script src="js/vendor/bootstrap.bundle.min.js"></script> |
| <script src="js/vendor/anchor.min.js"></script> |
| <script src="js/main.js"></script> |
| <script type="text/javascript" src="https://cdn.jsdelivr.net/npm/docsearch.js@2/dist/cdn/docsearch.min.js"></script> |
| <script type="text/javascript"> |
| // DocSearch is entirely free and automated. DocSearch is built in two parts: |
| // 1. a crawler which we run on our own infrastructure every 24 hours. It follows every link |
| // in your website and extract content from every page it traverses. It then pushes this |
| // content to an Algolia index. |
| // 2. a JavaScript snippet to be inserted in your website that will bind this Algolia index |
| // to your search input and display its results in a dropdown UI. If you want to find more |
| // details on how works DocSearch, check the docs of DocSearch. |
| docsearch({ |
| apiKey: 'd62f962a82bc9abb53471cb7b89da35e', |
| appId: 'RAI69RXRSK', |
| indexName: 'apache_spark', |
| inputSelector: '#docsearch-input', |
| enhancedSearchInput: true, |
| algoliaOptions: { |
| 'facetFilters': ["version:3.3.0"] |
| }, |
| debug: false // Set debug to true if you want to inspect the dropdown |
| }); |
| |
| </script> |
| |
| <!-- MathJax Section --> |
| <script type="text/x-mathjax-config"> |
| MathJax.Hub.Config({ |
| TeX: { equationNumbers: { autoNumber: "AMS" } } |
| }); |
| </script> |
| <script> |
| // Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS. |
| // We could use "//cdn.mathjax...", but that won't support "file://". |
| (function(d, script) { |
| script = d.createElement('script'); |
| script.type = 'text/javascript'; |
| script.async = true; |
| script.onload = function(){ |
| MathJax.Hub.Config({ |
| tex2jax: { |
| inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ], |
| displayMath: [ ["$$","$$"], ["\\[", "\\]"] ], |
| processEscapes: true, |
| skipTags: ['script', 'noscript', 'style', 'textarea', 'pre'] |
| } |
| }); |
| }; |
| script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') + |
| 'cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js' + |
| '?config=TeX-AMS-MML_HTMLorMML'; |
| d.getElementsByTagName('head')[0].appendChild(script); |
| }(document)); |
| </script> |
| </body> |
| </html> |
