Github user manishamde commented on a diff in the pull request: https://github.com/apache/spark/pull/2604#discussion_r18252110 --- Diff: examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala --- @@ -170,16 +176,40 @@ object DecisionTreeRunner { val frac = classCounts(c) / numExamples.toDouble println(s"$c\t$frac\t${classCounts(c)}") } - (examples, numClasses) + (examples, classIndexMap, numClasses) } case Regression => - (origExamples, 0) + (origExamples, null, 0) case _ => throw new IllegalArgumentException("Algo ${params.algo} not supported.") } - // Split into training, test. - val splits = examples.randomSplit(Array(1.0 - params.fracTest, params.fracTest)) + // Create training, test sets. + val splits = if (params.testInput != "") { --- End diff -- This utility method should probably be in a common utils class and be used by all algorithm runners.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org