From 85e9d091d5d785d412e91038c2490131e64f5634 Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Wed, 18 Feb 2015 10:09:56 -0800
Subject: [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
---
 .../spark/examples/mllib/JavaFPGrowthExample.java  | 63 ++++++++++++++++++++++
 .../spark/examples/mllib/FPGrowthExample.scala     | 51 ++++++++++++++++++
 2 files changed, 114 insertions(+)
 create mode 100644 examples/src/main/java/org/apache/spark/examples/mllib/JavaFPGrowthExample.java
 create mode 100644 examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala

(limited to 'examples')

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();
+  }
+}
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala
new file mode 100644
index 0000000000..ae66107d70
--- /dev/null
+++ b/examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala
@@ -0,0 +1,51 @@
+/*
+ * 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 org.apache.spark.mllib.fpm.FPGrowth
+import org.apache.spark.{SparkContext, SparkConf}
+
+/**
+ * Example for mining frequent itemsets using FP-growth.
+ */
+object FPGrowthExample {
+
+  def main(args: Array[String]) {
+    val conf = new SparkConf().setAppName("FPGrowthExample")
+    val sc = new SparkContext(conf)
+
+    // TODO: Read a user-specified input file.
+    val transactions = sc.parallelize(Seq(
+      "r z h k p",
+      "z y x w v u t s",
+      "s x o n r",
+      "x z y m t s q e",
+      "z",
+      "x z y r q t p").map(_.split(" ")), numSlices = 2)
+
+    val fpg = new FPGrowth()
+      .setMinSupport(0.3)
+    val model = fpg.run(transactions)
+
+    model.freqItemsets.collect().foreach { case (itemset, freq) =>
+      println(itemset.mkString("[", ",", "]") + ", " + freq)
+    }
+
+    sc.stop()
+  }
+}
-- 
cgit v1.2.3