Github user yanboliang commented on the issue:
https://github.com/apache/spark/pull/15324
I'm against to merge ```theta``` and ```sigma``` together, it should be two
individual variables of model. To the question that whether GaussianNB should
be part of the ```NaiveBayes``` estimator, I'm ambivalent between these two
opinions but I'm more prefer to add another variable ```sigma``` to the model.
When it's a gaussian NB model, both ```theta``` and ```sigma``` are effective;
otherwise, only ```theta``` is valid. We keep private constructor for all
models, so add another variable is not a big issue. I'm open to hear others'
thoughts. cc @jkbradley
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
