Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/21081#discussion_r182925491 --- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala --- @@ -144,8 +168,23 @@ class KMeansModel private[ml] ( // TODO: Replace the temp fix when we have proper evaluators defined for clustering. @Since("2.0.0") def computeCost(dataset: Dataset[_]): Double = { - SchemaUtils.checkColumnType(dataset.schema, $(featuresCol), new VectorUDT) - val data: RDD[OldVector] = dataset.select(col($(featuresCol))).rdd.map { + val typeCandidates = List( new VectorUDT, --- End diff -- You can reuse validateAndTransformSchema here.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org