CBribiescas edited a comment on pull request #32813: URL: https://github.com/apache/spark/pull/32813#issuecomment-857390387
To elaborate on the merge condition part, can I propose the following. Expose a `pruning_strategy` (both scala/pyspark) behavior which is as follows: - `None` - No pruning to be done - `class` - The behavior that exists where pruning will happen if the prediction is the same - `probability` - Which will prune if the probabilities match only (Not sure how likely) Default setting being either `none` or `probability`. Of course, adding unit tests and documentation for the above. Prior to implementing, does this sound good? Also, the formatting was prescribed by the Scala style check described here: https://spark.apache.org/contributing.html Should I remove it or leave? -- 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]
