Github user jkbradley commented on the issue:
https://github.com/apache/spark/pull/12823
@BenFradet I'm sorry for dropping the ball on this one. Did you close this
due to inactivity? If you're willing, it would be nice to do this cleanup.
To answer your questions:
> Regarding linear regression, should the tValues, pValues,
coefficientStandardErrors and the different metrics be moved to the training
summary?
Same thing for logistic regression, should the different metrics be moved
to the training summary?
These can go in the summary, not just the training summary, since they can
be calculated from the model. The training summary just has values which are
specific to the training process.
> Also, I noticed some discrepancy regarding the visibility of some fields
in linear regression compared to generalized linear regression:
* numInstances is public in lr and regression private in glr
* degreesOfFreedom is private in lr and public in glr
Making numInstances and degreesOfFreedom public sounds good to me.
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]
