Github user goodsoldiersvejk commented on the pull request:
https://github.com/apache/spark/pull/12895#issuecomment-222559584
Hi,
Marginally related to this, it would be good to improve the Spark mllib
documentation to provide context for using the information gain parameter
appropriately (if I'm not mistaken the information gain is simply the mutual
information which is bounded between zero and the minimum of the entropy of
each of two given random variables). It would also be useful to abstract out
the mutual information or information gain; I ended up abusing spark decision
trees to do some work with large-scale mutual information statistics because of
the ready presence of labelling and distributed computation.
---
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]
