Github user NathanHowell commented on the pull request:
https://github.com/apache/spark/pull/8246#issuecomment-139334977
@manishamde yes, same parameters. this dataset is about 100m examples, not
sure offhand on the exact number of features but probably about 5k categorical
features (typically with single digit arity) and 100-200k continuous features.
the binning slowdown can also be avoided by using a one-hot encoding but
it's not convenient. having per feature bin counts would be nice, and it can
(probably?) be ignored for categorical features altogether.
---
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]
