Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/2607#issuecomment-58066951
@manishamde
Multi-class classification: Good point; I agree. I think this
implementation can support binary, but we can do another to support multiclass.
(For multiclass, I think the .OC error-correcting versions might be the best
options.)
Weighted weak hypotheses: I am OK if this initial PR does not include
weights, but then weights should be prioritized for the next update.
For the WeightedEnsemble, that generalization could be part of this PR or a
follow-up.
Once this is ready, I'll be happy to help with testing (e.g., to set
checkpointing intervals and general performance).
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]
