Use collect

freeman-lab · freeman-lab · commit a4a316b2a383 · 2014-10-28T22:13:06.000-07:00
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala
@@ -83,7 +83,7 @@ class StreamingKMeansModel(
       (p1._1 += p2._1, p1._2 + p2._2)
     }
     val pointStats: Array[(Int, (BV[Double], Long))] =
-      closest.reduceByKey{mergeContribs}.collectAsMap().toArray
+      closest.reduceByKey(mergeContribs).collect()
 
     // implement update rule
     for (newP <- pointStats) {

Original file line number	Diff line number	Diff line change
`@@ -83,7 +83,7 @@ class StreamingKMeansModel(`
`83`	`83`	`(p1._1 += p2._1, p1._2 + p2._2)`
`84`	`84`	`}`
`85`	`85`	`val pointStats: Array[(Int, (BV[Double], Long))] =`
`86`		`- closest.reduceByKey{mergeContribs}.collectAsMap().toArray`
	`86`	`+ closest.reduceByKey(mergeContribs).collect()`
`87`	`87`
`88`	`88`	`// implement update rule`
`89`	`89`	`for (newP <- pointStats) {`