Github user sethah commented on the pull request:
https://github.com/apache/spark/pull/12419#issuecomment-210622479
I don't believe this will break the API. You can get away without even
changing the MLlib API by adding a private constructor or a private call to the
fit method that passes in a retained variance parameter. Also, it looks like it
would be good to update the `computePrincipalComponentsAndExplainedVariance`
method to alternately work with an retained variance parameter. Otherwise,
you'd have to pass it a value for `k` equal to the full number of principal
components and then trim it manually. Thoughts?
---
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]
