From 0cfd2cebde0b7fac3779eda80d6e42223f8a3d9f Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Thu, 19 Feb 2015 18:06:16 -0800 Subject: [SPARK-5900][MLLIB] make PIC and FPGrowth Java-friendly In the previous version, PIC stores clustering assignments as an `RDD[(Long, Int)]`. This is mapped to `RDD>` in Java and hence Java users have to cast types manually. We should either create a new method called `javaAssignments` that returns `JavaRDD[(java.lang.Long, java.lang.Int)]` or wrap the result pair in a class. I chose the latter approach in this PR. Now assignments are stored as an `RDD[Assignment]`, where `Assignment` is a class with `id` and `cluster`. Similarly, in FPGrowth, the frequent itemsets are stored as an `RDD[(Array[Item], Long)]`, which is mapped to `RDD>`. Though we provide a "Java-friendly" method `javaFreqItemsets` that returns `JavaRDD[(Array[Item], java.lang.Long)]`. It doesn't really work because `Array[Item]` is mapped to `Object` in Java. So in this PR I created a class `FreqItemset` to wrap the results. It has `items` and `freq`, as well as a `javaItems` method that returns `List` in Java. I'm not certain that the names I chose are proper: `Assignment`/`id`/`cluster` and `FreqItemset`/`items`/`freq`. Please let me know if there are better suggestions. CC: jkbradley Author: Xiangrui Meng Closes #4695 from mengxr/SPARK-5900 and squashes the following commits: 865b5ca [Xiangrui Meng] make Assignment serializable cffa96e [Xiangrui Meng] fix test 9c0e590 [Xiangrui Meng] remove unused Tuple2 1b9db3d [Xiangrui Meng] make PIC and FPGrowth Java-friendly --- .../scala/org/apache/spark/examples/mllib/FPGrowthExample.scala | 4 ++-- .../spark/examples/mllib/PowerIterationClusteringExample.scala | 8 ++------ 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'examples/src/main/scala') 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 index ae66107d70..aaae275ec5 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala @@ -42,8 +42,8 @@ object FPGrowthExample { .setMinSupport(0.3) val model = fpg.run(transactions) - model.freqItemsets.collect().foreach { case (itemset, freq) => - println(itemset.mkString("[", ",", "]") + ", " + freq) + model.freqItemsets.collect().foreach { itemset => + println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq) } sc.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala index b2373adba1..91c9772744 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala @@ -44,8 +44,7 @@ import org.apache.spark.{SparkConf, SparkContext} * * Here is a sample run and output: * - * ./bin/run-example mllib.PowerIterationClusteringExample - * -k 3 --n 30 --maxIterations 15 + * ./bin/run-example mllib.PowerIterationClusteringExample -k 3 --n 30 --maxIterations 15 * * Cluster assignments: 1 -> [0,1,2,3,4],2 -> [5,6,7,8,9,10,11,12,13,14], * 0 -> [15,16,17,18,19,20,21,22,23,24,25,26,27,28,29] @@ -103,7 +102,7 @@ object PowerIterationClusteringExample { .setMaxIterations(params.maxIterations) .run(circlesRdd) - val clusters = model.assignments.collect.groupBy(_._2).mapValues(_.map(_._1)) + val clusters = model.assignments.collect().groupBy(_.cluster).mapValues(_.map(_.id)) val assignments = clusters.toList.sortBy { case (k, v) => v.length} val assignmentsStr = assignments .map { case (k, v) => @@ -153,8 +152,5 @@ object PowerIterationClusteringExample { val expCoeff = -1.0 / 2.0 * math.pow(sigma, 2.0) val ssquares = (p1._1 - p2._1) * (p1._1 - p2._1) + (p1._2 - p2._2) * (p1._2 - p2._2) coeff * math.exp(expCoeff * ssquares) - // math.exp((p1._1 - p2._1) * (p1._1 - p2._1) + (p1._2 - p2._2) * (p1._2 - p2._2)) } - - } -- cgit v1.2.3