Github user jaceklaskowski commented on a diff in the pull request: https://github.com/apache/spark/pull/13981#discussion_r69703134 --- Diff: mllib/src/test/scala/org/apache/spark/ml/regression/DecisionTreeRegressorSuite.scala --- @@ -96,6 +97,25 @@ class DecisionTreeRegressorSuite assert(variance === expectedVariance, s"Expected variance $expectedVariance but got $variance.") } + + val varianceData: RDD[LabeledPoint] = TreeTests.varianceData(sc) + val varianceDF = TreeTests.setMetadata(varianceData, Map.empty[Int, Int], 0) + dt.setMaxDepth(1) + .setMaxBins(6) + .setSeed(0) + val transformVarDF = dt.fit(varianceDF).transform(varianceDF) + val calculatedVariances = transformVarDF.select(dt.getVarianceCol).collect().map { --- End diff -- Before `collect` so you work with type-safe `Dataset` (not a `DataFrame` which is `Dataset[Row]`)
--- 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