-
-
Notifications
You must be signed in to change notification settings - Fork 26k
[MRG] DEP deprecate "mae" criterion in GadientBoosting estimators #18326
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks @madhuracj, looks good. We'll also need a whatsnew entry.
Not sure why the docs aren't building...
@NicolasHug Thanks for reviewing. Changelog entry added in f9f1a3e. Still the docs aren not building. |
Something related with I think that we do not need to worry (so much) about this. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you @madhuracj for your PR!
LGTM.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Thanks @madhuracj
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks @madhuracj .
To briefly explain the reason, let's add those at the end of each warning / doc message:
- for the regressor: "The correct way of minimizing the absolute error is to use loss='lad' instead."
- for the classifier: "Use criterion='friedman_mse' or 'mse' instead, as trees should use a least-square criterion in Gradient Boosting."
Done in e04af1c. |
In the warnings as well please ;) |
Sorry, I missed that part. Hopefully, 7d63e66 fulfils that. |
Thanks @madhuracj |
…oostingRegressor
Reference Issues/PRs
Fixed #18263
What does this implement/fix? Explain your changes.
Deprecate criterion='mae' in GradientBoostingClassifier and GradientBoostingRegressor
Any other comments?