diff options
author | Xiangrui Meng <meng@databricks.com> | 2015-02-18 10:09:56 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-02-18 10:09:56 -0800 |
commit | 85e9d091d5d785d412e91038c2490131e64f5634 (patch) | |
tree | 79d956ee9eb4859e32e0dfc46531a346389cb581 /examples/src/main/java | |
parent | 5aecdcf1f23a826f6236096001de1dd811dbc443 (diff) | |
download | spark-85e9d091d5d785d412e91038c2490131e64f5634.tar.gz spark-85e9d091d5d785d412e91038c2490131e64f5634.tar.bz2 spark-85e9d091d5d785d412e91038c2490131e64f5634.zip |
[SPARK-5519][MLLIB] add user guide with example code for fp-growth
The API is still not very Java-friendly because `Array[Item]` in `freqItemsets` is recognized as `Object` in Java. We might want to define a case class to wrap the return pair to make it Java friendly.
Author: Xiangrui Meng <meng@databricks.com>
Closes #4661 from mengxr/SPARK-5519 and squashes the following commits:
58ccc25 [Xiangrui Meng] add user guide with example code for fp-growth
Diffstat (limited to 'examples/src/main/java')
-rw-r--r-- | examples/src/main/java/org/apache/spark/examples/mllib/JavaFPGrowthExample.java | 63 |
1 files changed, 63 insertions, 0 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaFPGrowthExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaFPGrowthExample.java new file mode 100644 index 0000000000..0db572d760 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaFPGrowthExample.java @@ -0,0 +1,63 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples.mllib; + +import java.util.ArrayList; +import java.util.Arrays; + +import scala.Tuple2; + +import com.google.common.collect.Lists; + +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.mllib.fpm.FPGrowth; +import org.apache.spark.mllib.fpm.FPGrowthModel; + +/** + * Java example for mining frequent itemsets using FP-growth. + */ +public class JavaFPGrowthExample { + + public static void main(String[] args) { + SparkConf sparkConf = new SparkConf().setAppName("JavaFPGrowthExample"); + JavaSparkContext sc = new JavaSparkContext(sparkConf); + + + // TODO: Read a user-specified input file. + @SuppressWarnings("unchecked") + JavaRDD<ArrayList<String>> transactions = sc.parallelize(Lists.newArrayList( + Lists.newArrayList("r z h k p".split(" ")), + Lists.newArrayList("z y x w v u t s".split(" ")), + Lists.newArrayList("s x o n r".split(" ")), + Lists.newArrayList("x z y m t s q e".split(" ")), + Lists.newArrayList("z".split(" ")), + Lists.newArrayList("x z y r q t p".split(" "))), 2); + + FPGrowth fpg = new FPGrowth() + .setMinSupport(0.3); + FPGrowthModel<String> model = fpg.run(transactions); + + for (Tuple2<Object, Long> s: model.javaFreqItemsets().collect()) { + System.out.println(Arrays.toString((Object[]) s._1()) + ", " + s._2()); + } + + sc.stop(); + } +} |