Github user WeichenXu123 commented on a diff in the pull request: https://github.com/apache/spark/pull/20686#discussion_r173995919 --- Diff: mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala --- @@ -299,18 +310,17 @@ class StringIndexerSuite .setInputCol("label") .setOutputCol("labelIndex") - val expected = Seq(Set((0, 0.0), (1, 0.0), (2, 2.0), (3, 1.0), (4, 1.0), (5, 0.0)), - Set((0, 2.0), (1, 2.0), (2, 0.0), (3, 1.0), (4, 1.0), (5, 2.0)), - Set((0, 1.0), (1, 1.0), (2, 0.0), (3, 2.0), (4, 2.0), (5, 1.0)), - Set((0, 1.0), (1, 1.0), (2, 2.0), (3, 0.0), (4, 0.0), (5, 1.0))) + val expected = Seq(Seq((0, 0.0), (1, 0.0), (2, 2.0), (3, 1.0), (4, 1.0), (5, 0.0)), --- End diff -- I'd make a little argument that if without shuffling, dataframe transformation will keep row ordering. :)
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org