Repository navigation
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hello I was interested in having metrics ranking for a personnal project. Since the PRs was not too big I figured I could help. Thanks for the works that covers significant sklearn blind spots.
Below is mostly AI generated.
Closes #845. ProbeFeatureSelection can now compare real features against random
probes using absolute correlation, classification/regression F scores, mutual
information, or held-out permutation importance. The existing model-based mode
remains the default. Statistical methods do not require an estimator.
Scoring uses identical folds for real and probe features. Permutation importance
is measured on validation folds after fitting cloned estimators on training folds.
Mutual information treats original predictors as continuous; probe types are
handled explicitly. Public API names and this scope are proposed for discussion.
Validation: 69 focused tests pass on pandas 3.0/sklearn 1.9 and pandas 2.2/sklearn 1.4;
72 selector estimator checks pass on the current stack. Added user-guide examples,
reference comparisons, numerical edge cases, and type/style checks.
Dependency requirements are unchanged. Testing covers the two configurations above, not the full supported-version matrix.