From 52dba89261ee6dddafff5c746322980567252843 Mon Sep 17 00:00:00 2001
From: Matei Zaharia <matei@eecs.berkeley.edu>
Date: Wed, 31 Jul 2013 23:08:12 -0700
Subject: [PATCH] Turn on caching in KMeans.main
---
mllib/src/main/scala/spark/mllib/clustering/KMeans.scala | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mllib/src/main/scala/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/spark/mllib/clustering/KMeans.scala
index a2ed42d7a5..b402c71ed2 100644
--- a/mllib/src/main/scala/spark/mllib/clustering/KMeans.scala
+++ b/mllib/src/main/scala/spark/mllib/clustering/KMeans.scala
@@ -322,7 +322,7 @@ object KMeans {
val (master, inputFile, k, iters) = (args(0), args(1), args(2).toInt, args(3).toInt)
val runs = if (args.length >= 5) args(4).toInt else 1
val sc = new SparkContext(master, "KMeans")
- val data = sc.textFile(inputFile).map(line => line.split(' ').map(_.toDouble))
+ val data = sc.textFile(inputFile).map(line => line.split(' ').map(_.toDouble)).cache()
val model = KMeans.train(data, k, iters, runs)
val cost = model.computeCost(data)
println("Cluster centers:")
--
GitLab