imatiach-msft commented on issue #23818: [SPARK-19591][ML][PYSPARK][FOLLOWUP] Add sample weights to decision trees URL: https://github.com/apache/spark/pull/23818#issuecomment-464973632 GBTClassifier and GBTRegressor don't support weight column yet. There is a separate JIRA for random forest: https://issues.apache.org/jira/browse/SPARK-9478 and another one for GBTs: https://issues.apache.org/jira/browse/SPARK-9612 In GBTClassifier/Reg we currently don't pass weights: https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala#L204 Unfortunately GBTClassifier/Reg uses the same params as DecisionTreeClassifier/Reg, so this is kind of a bug now - since we expose this param but it doesn't actually do anything. Thanks for finding this! We should try to fix this soon at the scala layer but maybe in python for now we shouldn't expose it?
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
