Github user hhbyyh commented on the issue:
https://github.com/apache/spark/pull/18313
@jkbradley Thanks for the suggestion. After the discussion, I found that
actually we can reduce the memory requirement for the tuning process. Check
https://issues.apache.org/jira/browse/SPARK-21535 if you have some time.
And I agree to your suggestion overall,
About 2, if we want to use indices rather that the param combination, we
probably need to save a summary table with the models. perhaps like
https://github.com/apache/spark/pull/16158 ?
---
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]
