Github user srowen commented on the issue:
https://github.com/apache/spark/pull/12896
Yes that sounds like the direction this is heading. In a way, "drop" and
"nan" aren't really different cold start strategies. Both return an implicit or
explicit "I don't know; ask something else". One of these wouldn't have a
counterpart in an API that offers point predictions.
"drop" and "nan" have distinct use in the context of evaluation, and it
sounds like we'd even get rid of "nan" except for potential backwards
compatibility. But, maybe that's just fine.
---
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]
