Github user acidghost commented on the pull request:
https://github.com/apache/spark/pull/6761#issuecomment-112449888
Sorry @srowen, I was erroneously subtracting the smallest..
Thank you @squito, my main error was scaling using multiplication instead
of addition in the log space as already pointed out by @srowen.
Something else I was missing is that NaiveBayes has some tendency to
"overestimate" its confidence. Is this a characteristic of generative
algorithms?
Thanks @srowen for the patience and time you're giving.
Do you have any clue on how to unit test this?
---
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]
