Github user iyerr3 commented on the issue:
https://github.com/apache/incubator-madlib/pull/142
I need more info on the RF docs discrepancy.
- Which example is giving the lower than 100% training accuracy?
- How do the trees look?
- Can we replicate in decision tree since that is easier to debug?
On its own, less than 100% accuracy is not wrong, but if the tree is not as
long as it should be (i.e. prematurely terminating) then a problem has been
introduced here.
---
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.
---
