FIX OOB predictions produce NaN for never-left-out samples in forest/bagging#33879
Open
dhruv7477 wants to merge 4 commits into
Open
FIX OOB predictions produce NaN for never-left-out samples in forest/bagging#33879dhruv7477 wants to merge 4 commits into
dhruv7477 wants to merge 4 commits into
Conversation
…bagging estimators Samples that are never in the out-of-bag set (which can happen with small n_estimators) now correctly produce NaN in oob_decision_function_ and oob_prediction_, rather than 0.0 as before. The oob_score_ is now computed only over samples that actually have OOB predictions, excluding never-left-out samples from the score computation. Fixes: scikit-learn#21490 Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
Signed-off-by: Dhruv Sharma <[email protected]>
Contributor
Author
|
Hi @jeremiedbb can you please look into this ? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #21490.
Samples never in any OOB set now correctly produce NaN in oob_decision_function_ and oob_prediction_ (not 0.0). oob_score_ is now computed only over samples with valid OOB predictions.
Changes: _forest.py _set_oob_score_and_attributes (both classifier and regressor), _bagging.py BaggingClassifier and BaggingRegressor _set_oob_score, new tests in test_forest.py and test_bagging.py, changelog fragment.
Full test suite: 1160 passed, 0 failed. Pre-commit: all pass.
AI assistance disclosure: developed with Claude (Anthropic). All changes reviewed by contributor."