Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/3626#issuecomment-75608187
@alanctgardner That will be great if you change it to
predictProbabilities; thanks. I agree with what @jatinpreet was saying about
the correctness, and with @srowen 's comment on how to fix it: The value of
```brzPi + brzTheta * testData.toBreeze``` is a log probability, which needs to
be exponentiated before you normalize it here:
[https://github.com/apache/spark/pull/3626/files?diff=split#diff-6d8eff78be2fb624d4a076db334208a4R84]
Could you please rebase off of master and make these couple of updates?
After that, I can make a final pass. 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]
