diff options
| author | Matei Zaharia <matei@eecs.berkeley.edu> | 2013-07-31 23:08:12 -0700 |
|---|---|---|
| committer | Matei Zaharia <matei@eecs.berkeley.edu> | 2013-07-31 23:08:12 -0700 |
| commit | 52dba89261ee6dddafff5c746322980567252843 (patch) | |
| tree | 1c0e101b3fe13d407bc7a2457ba293e23566794b /mllib | |
| parent | f607ffb9e1f799d73818f1d37c633007a6b900fb (diff) | |
| download | spark-52dba89261ee6dddafff5c746322980567252843.tar.gz spark-52dba89261ee6dddafff5c746322980567252843.tar.bz2 spark-52dba89261ee6dddafff5c746322980567252843.zip | |
Turn on caching in KMeans.main
Diffstat (limited to 'mllib')
| -rw-r--r-- | mllib/src/main/scala/spark/mllib/clustering/KMeans.scala | 2 |
1 files changed, 1 insertions, 1 deletions
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:") |