Github user mengxr commented on the pull request:
https://github.com/apache/spark/pull/6466#issuecomment-106586234
@sryza I think keeping all categories by default is a bad practice. It
throws in an extra column that carries no extra info and causes numerical
problems. I checked several tutorials online and it seems that only sklearn
keeps all by default.
1. http://www.ats.ucla.edu/stat/mult_pkg/faq/general/dummy.htm
2. http://en.wikiversity.org/wiki/Dummy_variable_(statistics)
3. http://dss.princeton.edu/online_help/analysis/dummy_variables.htm
---
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]
