use sampleByKey for per user sampling

nemccarthy · Nov 8, 2014 · f38a1b5 · f38a1b5
1 parent 10cbb37
commit f38a1b5
Showing 1 changed file with 1 addition and 2 deletions.
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala
@@ -141,9 +141,8 @@ object MovieLensALS {
 
     println(s"Got $numRatings ratings from $numUsers users on $numMovies movies.")
 
-    //val splits = ratings.randomSplit(Array(0.8, 0.2))
     val fractions = (0 until numUsers.toInt).map(x => (x + 1, 0.8)).toMap
-
+    
     val training = ratings.map { x => (x.user, x) }.sampleByKey(false, fractions).map { x => x._2 }
     val testSplit = ratings.subtract(training)