Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/15428#discussion_r82741459 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala --- @@ -73,15 +78,27 @@ final class Bucketizer @Since("1.4.0") (@Since("1.4.0") override val uid: String @Since("1.4.0") def setOutputCol(value: String): this.type = set(outputCol, value) + /** @group setParam */ + @Since("2.1.0") + def setHandleInvalid(value: String): this.type = set(handleInvalid, value) + setDefault(handleInvalid, "error") + @Since("2.0.0") override def transform(dataset: Dataset[_]): DataFrame = { transformSchema(dataset.schema) - val bucketizer = udf { feature: Double => - Bucketizer.binarySearchForBuckets($(splits), feature) + val bucketizer: UserDefinedFunction = udf { (feature: Double, flag: String) => + Bucketizer.binarySearchForBuckets($(splits), feature, flag) + } + val filteredDataset = { --- End diff -- Doesn't this need to try to handle "error"? ``` val filteredDataSet = getHandleInvalid match { case "skip" => dataset.na.drop case "keep" => dataset case "error" => if (...dataset contains NaN...) { throw new IllegalArgumentException(...) } else { dataset } } ```
--- 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