Github user mengxr commented on the pull request:
https://github.com/apache/spark/pull/6795#issuecomment-122201258
@catap Some high-level comments:
1. The name `SignificantSelector` does not reflect what it really does.
There are many ways to define feature significance. It is hard to guess that
this one means removing constant columns.
2. The example you mentioned doesn't fully support this transformer. If you
don't want zero columns, use bag of words. If there are many values and you
have to use hashing, this transformer doesn't really help reduce the number of
columns.
I don't see how this transformer could help real-world use cases. But if
you have seen reference use cases, please let me know. 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]
