Github user yanboliang commented on a diff in the pull request: https://github.com/apache/spark/pull/12066#discussion_r61580506 --- Diff: mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala --- @@ -37,8 +37,38 @@ private[spark] trait ClassifierParams schema: StructType, fitting: Boolean, featuresDataType: DataType): StructType = { - val parentSchema = super.validateAndTransformSchema(schema, fitting, featuresDataType) - SchemaUtils.appendColumn(parentSchema, $(rawPredictionCol), new VectorUDT) + // TODO: Support casting Array[Double] and Array[Float] to Vector when FeaturesType = Vector + SchemaUtils.checkColumnType(schema, $(featuresCol), featuresDataType) + if (fitting) { + SchemaUtils.checkNumericType(schema, $(labelCol)) + } + val newSchema = SchemaUtils.appendColumn(schema, $(predictionCol), DoubleType, + nullable = false, generatePredictionMetadata(schema)) + SchemaUtils.appendColumn(newSchema, $(rawPredictionCol), new VectorUDT) + } + + protected def generatePredictionMetadata(schema: StructType): Metadata = { + // The label column for base binary classifier of OneVsRest will not be retained during --- End diff -- Yes. The annotation is to clarify if the current ```Classifier``` is act as the base binary classifier of OneVsRest estimator(rather than the OneVsRest itself), its label column will not be retained and we should check whether it exists.
--- 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