Make optimizers raise an error when provided negative fixed features

[esantorella]

Summary:
Context: See #2602

This PR:

• Adds a check for negative fixed_features keys to input validation for optimizers. This applies to all of the optimizers that take fixed_features.
• Updates docstrings

Differential Revision: D65272024

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D65272024

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 99.98%. Comparing base (66660e3) to head (26b86e0).
Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #2603   +/-   ##
=======================================
  Coverage   99.98%   99.98%           
=======================================
  Files         196      196           
  Lines       17370    17372    +2     
=======================================
+ Hits        17368    17370    +2     
  Misses          2        2           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[Balandat]

I think it's good to get this in for now, but I feel like it shouldn't be to hard to allow this by canonicalizing the indices to index % num_features? Being able to use backward indexing can be quite convenient. Maybe we can make a backlog task for this?

[esantorella]

I think it's good to get this in for now, but I feel like it shouldn't be to hard to allow this by canonicalizing the indices to index % num_features? Being able to use backward indexing can be quite convenient. Maybe we can make a backlog task for this?

That makes sense to me. I didn't want to do it right now since I'd want to check a lot more carefully that that wouldn't break anything (e.g. if there were a place in the code that added a feature as the last column).

[facebook-github-bot]

This pull request has been merged in 9e44749.