srowen commented on pull request #28503: URL: https://github.com/apache/spark/pull/28503#issuecomment-628669711
Am I right that currently, this would fail if you fit a multi-class model and then tried to call one of the methods on BinaryLogisticRegressionSummary, like roc()? because the Scala impl on the other side would not be a BinaryLogisticRegressionSummary and would not have that method? If so that's almost not a behavior change, as nothing that this change 'takes away' would have worked. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
