Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/20829#discussion_r175910846 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala --- @@ -136,34 +172,88 @@ class VectorAssembler @Since("1.4.0") (@Since("1.4.0") override val uid: String) @Since("1.6.0") object VectorAssembler extends DefaultParamsReadable[VectorAssembler] { + private[feature] val SKIP_INVALID: String = "skip" + private[feature] val ERROR_INVALID: String = "error" + private[feature] val KEEP_INVALID: String = "keep" + private[feature] val supportedHandleInvalids: Array[String] = + Array(SKIP_INVALID, ERROR_INVALID, KEEP_INVALID) + + + private[feature] def getLengthsFromFirst(dataset: Dataset[_], --- End diff -- Also, it's unclear what this method does until I read the code. Possibly make the method name more explicit ("getVectorLengthsFromFirstRow"), and definitely document that "columns" must all be of Vector type.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org