Github user LIDIAgroup commented on the pull request:
https://github.com/apache/spark/pull/216#issuecomment-38944614
I've made some big changes:
1. Big refactor in the architecture of the discretizer. Now I think it's
more coherent with other packages in MLlib.
2. I've changed the `MapAccumulator` for an `ArrayAccumulator`, which
removes the quadratic complexity and improves the overall efficiency of the
algorithm.
3. I've followed @mengxr suggestions and moved `InfoTheory` to the
`discretization` package.
---
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.
---
