Github user imatiach-msft commented on a diff in the pull request: https://github.com/apache/spark/pull/17084#discussion_r123925177 --- Diff: mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala --- @@ -77,12 +87,16 @@ class BinaryClassificationEvaluator @Since("1.4.0") (@Since("1.4.0") override va SchemaUtils.checkNumericType(schema, $(labelCol)) // TODO: When dataset metadata has been implemented, check rawPredictionCol vector length = 2. - val scoreAndLabels = - dataset.select(col($(rawPredictionCol)), col($(labelCol)).cast(DoubleType)).rdd.map { - case Row(rawPrediction: Vector, label: Double) => (rawPrediction(1), label) - case Row(rawPrediction: Double, label: Double) => (rawPrediction, label) + val scoreAndLabelsWithWeights = + dataset.select(col($(rawPredictionCol)), col($(labelCol)).cast(DoubleType), + if (!isDefined(weightCol) || $(weightCol).isEmpty) lit(1.0) else col($(weightCol))) --- End diff -- added check for numeric type and did cast to Double, similar to labelCol
--- 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