Github user imatiach-msft commented on the issue: https://github.com/apache/spark/pull/16441 Thanks, I've updated the PR based on your comment. The only disadvantage to the current code is that I do the probability computation within the classifier, but it seems like it should be moved to the LogLoss.scala class. However, it's not a problem right now because GBTClassifier only uses logistic loss, and other learners would have to be modified in a similar way as well probably.
--- 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