examples/mllib/JavaSimpleFPGrowth.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.examples.mllib;
0019
0020 // $example on$
0021 import java.util.Arrays;
0022 import java.util.List;
0023
0024 import org.apache.spark.api.java.JavaRDD;
0025 import org.apache.spark.api.java.JavaSparkContext;
0026 import org.apache.spark.mllib.fpm.AssociationRules;
0027 import org.apache.spark.mllib.fpm.FPGrowth;
0028 import org.apache.spark.mllib.fpm.FPGrowthModel;
0029 // $example off$
0030
0031 import org.apache.spark.SparkConf;
0032
0033 public class JavaSimpleFPGrowth {
0034
0035   public static void main(String[] args) {
0036     SparkConf conf = new SparkConf().setAppName("FP-growth Example");
0037     JavaSparkContext sc = new JavaSparkContext(conf);
0038
0039     // $example on$
0040     JavaRDD<String> data = sc.textFile("data/mllib/sample_fpgrowth.txt");
0041
0042     JavaRDD<List<String>> transactions = data.map(line -> Arrays.asList(line.split(" ")));
0043
0044     FPGrowth fpg = new FPGrowth()
0045       .setMinSupport(0.2)
0046       .setNumPartitions(10);
0047     FPGrowthModel<String> model = fpg.run(transactions);
0048
0049     for (FPGrowth.FreqItemset<String> itemset: model.freqItemsets().toJavaRDD().collect()) {
0050       System.out.println("[" + itemset.javaItems() + "], " + itemset.freq());
0051     }
0052
0053     double minConfidence = 0.8;
0054     for (AssociationRules.Rule<String> rule
0055       : model.generateAssociationRules(minConfidence).toJavaRDD().collect()) {
0056       System.out.println(
0057         rule.javaAntecedent() + " => " + rule.javaConsequent() + ", " + rule.confidence());
0058     }
0059     // $example off$
0060
0061     sc.stop();
0062   }
0063 }