zhengruifeng commented on issue #25983: [SPARK-29327][MLLIB]Support specifying features via multiple columns URL: https://github.com/apache/spark/pull/25983#issuecomment-548643803 If current algs in MLLIB will not benefit from this design (execpt skip `VectorAssembler`), I do not prefer it. SKLearn is also widely used, it do not support this feature. > There are also lots of algorithms outside the spark core ml lib code that use these classes and so we were thinking this would be convenience method that doesn't add much overhead to the spark core code. Yes, but I think current design in MLLIB do not pose an obstacle to impl third-party libs.
---------------------------------------------------------------- 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] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
