Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/3975#issuecomment-71419431 @Lewuathe I'm suggesting the following: 1) loadLibSVMFile should not transform the input data. 2) Users should map the labels to 0, 1, 2, 3, ... a) using ad-hoc transformations, b) or using a `LabelIndexer` (to be added) in the new pipeline API, where metadata will be added to the output column of `LabelIndexer` 3) Algorithms should validate the label values and throw errors if they are out of range
--- 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