-
Notifications
You must be signed in to change notification settings - Fork 552
[MRG] Add support for Multimetric BayesSearchCV #1030
[MRG] Add support for Multimetric BayesSearchCV #1030
Conversation
Co-authored-by: Tim Head <betatim@gmail.com>
…alidation._fit_and_score * Update searchcv.py Further improvements for kernc previous commits. iid totally removed to prevent troubles with sklearn utils prettyprinting. prettyprinting looks for params when print to repl. Sklearn 0.24 has changed return value after cv, so i changed dict destructuring(a litttle bit dirty) * Update searchcv.py * Revert unrelated changes * PEP8 format; add comment * Revert reverting "unrelated changes" This is required to pass tests/test_searchcv.py with scikit-learn 0.24+. Co-authored-by: Kernc <kerncece@gmail.com>
Hello @QuentinSoubeyran! Thanks for updating this PR. We checked the lines you've touched for PEP 8 issues, and found: There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻 Comment last updated at 2021-07-15 17:43:00 UTC |
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 and sorry for the wait. See a few notes below.
Thank you for the review, no worries for the short wait. I integrated most of your suggestions. For the callable |
Please merge this! |
@Abdelgha-4 |
Closed in favor of #1062 which should have a cleaner history |
As discussed in PR #988 and issue #797, this PR implements support for multimetric scoring to
BayesSearchCV
. Therefit
parameter is used to drive the optimization process.Fixes:
Features:
scoring
and callablescoring
returning a dict of scores toBayesSearchCV
refit
to specify the score to use for optimisation. Callablerefit
(accepted byGridSearchCV
) are not supportedBayesSearchCV.multimetric_
attributeI don't have much experience with the code style of scikit-learn/scikit-optimize, feel free to reformat the code as needed.