Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/8246#issuecomment-139311498
@NathanHowell I just looked this over, and it seems fine. A few questions:
Did you encounter this problem in practice? I would have thought that
choosing splits would take much less time than training itself. Was training
itself fast for you?
Note: There are currently 2 tree implementations, one in spark.mllib (which
you're modifying) and one in spark.ml. I eventually want to remove the
spark.mllib one and wrap the spark.ml one
[https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala].
We can commit this here and then copy it over to spark.ml in another PR.
Thanks!
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
