Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/2378#discussion_r17574578 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala --- @@ -60,18 +60,18 @@ class PythonMLLibAPI extends Serializable { def loadLabeledPoints( jsc: JavaSparkContext, path: String, - minPartitions: Int): JavaRDD[Array[Byte]] = - MLUtils.loadLabeledPoints(jsc.sc, path, minPartitions).map(SerDe.serializeLabeledPoint) + minPartitions: Int): JavaRDD[LabeledPoint] = + MLUtils.loadLabeledPoints(jsc.sc, path, minPartitions) private def trainRegressionModel( trainFunc: (RDD[LabeledPoint], Vector) => GeneralizedLinearModel, - dataBytesJRDD: JavaRDD[Array[Byte]], + dataJRDD: JavaRDD[Any], initialWeightsBA: Array[Byte]): java.util.LinkedList[java.lang.Object] = { - val data = dataBytesJRDD.rdd.map(SerDe.deserializeLabeledPoint) - val initialWeights = SerDe.deserializeDoubleVector(initialWeightsBA) + val data = dataJRDD.rdd.map(_.asInstanceOf[LabeledPoint]) --- End diff -- maybe we can try `dataJRDD.rdd.asInstanceOf[RDD[LabeledPoint]]` instead of `map`
--- 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