scikit-learn · Issues· 2160 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #34883
[BUG] `compute_class_weight` coerces class labels to int in 1.9, breaking dict lookup for string labels
BugUpdated Sep 17, 2026 - #30223
Add Accumulated local effects (ALE) to inspection
New FeatureModeratemodule:inspectionUpdated Sep 17, 2026 - #34880
SelectFromModel's `prefit` fails unless fit is called when set_output(transform="pandas")
DocumentationNeeds DecisionUpdated Sep 17, 2026 - #34975
BUG confusion_matrix_at_thresholds / roc_auc_score lose precision on plain numpy when y_score is float32 (regression from #34817)
Numerical StabilityUpdated Sep 17, 2026 - #34979
Clarify the random_state description in train_test_split documentation
DocumentationNeeds TriageUpdated Sep 17, 2026 - #34943
Add Information Value (IV) / Weight-of-Evidence binning as metric and feature-selection
New FeatureNeeds TriageUpdated Sep 17, 2026 - #34945
Add Population Stability Index (PSI) as a model/data drift metric
New FeatureNeeds TriageUpdated Sep 17, 2026 - #34946
`xp.isdtype` checks raise on NumPy `StringDType`
BugRFCUpdated Sep 17, 2026 - #34964
I cannot get the scikit-learn development Codespace into the intended development environment.
Updated Sep 17, 2026 - #30354
Enhance "Choosing the Right Estimator" Graphic (scikit-learn algorithm cheat sheet)
DocumentationUpdated Sep 17, 2026 - #30524
A helpful warning when adding sparsity constraints to NMF
DocumentationUpdated Sep 17, 2026 - #34977
⚠️ CI failed on Wheel builder (last failure: Sep 17, 2026) ⚠️
Needs TriageUpdated Sep 17, 2026 - #34383
In encoders, switch to faster string representation than `object` dtype
Updated Sep 17, 2026 - #34651
⚠️ CI failed on Unit tests Linux x86-64 pylatest_free_threaded (last failure: Aug 05, 2026) ⚠️
Needs TriageUpdated Sep 17, 2026 - #33387
⚠️ CI failed on Unit tests Linux x86-64 pylatest_conda_forge_mkl (last failure: Aug 04, 2026) ⚠️
Updated Sep 17, 2026