Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/17819#discussion_r143722947 --- Diff: mllib/src/test/scala/org/apache/spark/ml/feature/BucketizerSuite.scala --- @@ -187,6 +188,196 @@ class BucketizerSuite extends SparkFunSuite with MLlibTestSparkContext with Defa } } } + + test("multiple columns: Bucket continuous features, without -inf,inf") { + // Check a set of valid feature values. + val splits = Array(Array(-0.5, 0.0, 0.5), Array(-0.1, 0.3, 0.5)) + val validData1 = Array(-0.5, -0.3, 0.0, 0.2) + val validData2 = Array(0.5, 0.3, 0.0, -0.1) + val expectedBuckets1 = Array(0.0, 0.0, 1.0, 1.0) + val expectedBuckets2 = Array(1.0, 1.0, 0.0, 0.0) + + val data = (0 until validData1.length).map { idx => + (validData1(idx), validData2(idx), expectedBuckets1(idx), expectedBuckets2(idx)) + } + val dataFrame: DataFrame = data.toSeq.toDF("feature1", "feature2", "expected1", "expected2") --- End diff -- `toSeq` not required here?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org