23 Pull requests merged by 13 people

• DOC Rework voting classifier example

  #30985 merged May 1, 2025

• ENH check_classification_targets raises a warning when unique classes > 50% of n_samples

  #26335 merged Apr 30, 2025

• MNT Apply ruff/flake8-executable rules (EXE)

  #31063 merged Apr 30, 2025

• ENH add X_val and y_val to HGBT.fit

  #27124 merged Apr 30, 2025

• DOC Fix typos found by codespell

  #31277 merged Apr 30, 2025

• MNT Avoid pre-commit failures

  #31276 merged Apr 30, 2025

• DOC Improve consistency of inverse_transform return name

  #31135 merged Apr 30, 2025

• Enhance ROC Curve Display Tests for Improved Clarity and Maintainability

  #31266 merged Apr 30, 2025

• Investigate test_precomputed_nearest_neighbors_filtering[60] failure on CI

  #31262 merged Apr 30, 2025

• DOC Minor update to CalibratedClassifierCV docstring

  #31275 merged Apr 30, 2025

• MNT git ignore application of ruff PGH rules (#31226)

  #31265 merged Apr 30, 2025

• MNT Avoid nested sequence in weighted_percentile

  #31211 merged Apr 29, 2025

• MNT Fix the formatting of the what's new entries for 1.7

  #31272 merged Apr 29, 2025

• MNT Avoid pre-commit failure

  #31273 merged Apr 29, 2025

• ENH Change the default n_init and eps for MDS

  #31117 merged Apr 29, 2025

• DOC Improve descriptions of roc_curve-related dosctrings

  #31238 merged Apr 28, 2025

• MNT Add ignore_types to assert_docstring_consistency

  #30944 merged Apr 28, 2025

• Use BLAS_Order.ColMajor sklearn/utils/_cython_blas.pyx

  #31263 merged Apr 28, 2025

• MNT Enforce ruff/pygrep-hooks rules (PGH)

  #31226 merged Apr 28, 2025

• ENH Add Array API compatibility to Binarizer

  #31190 merged Apr 28, 2025

• 🔒 🤖 CI Update lock files for array-api CI build(s) 🔒 🤖

  #31260 merged Apr 28, 2025

• 🔒 🤖 CI Update lock files for free-threaded CI build(s) 🔒 🤖

  #31259 merged Apr 28, 2025

• 🔒 🤖 CI Update lock files for main CI build(s) 🔒 🤖

  #31261 merged Apr 28, 2025

12 Pull requests opened by 9 people

• Enable using 2SD scaling in StandardScaler

  #31268 opened Apr 28, 2025

• Fix default value of average in precision_recall_fscore_support

  #31270 opened Apr 29, 2025

• DOC Add link to plot_sparse_cov example (Towards #30621)

  #31278 opened Apr 30, 2025

• Unbiased MDI-like feature importance measure for random forests

  #31279 opened Apr 30, 2025

• DOC: Add link to plot_nnls example

  #31280 opened Apr 30, 2025

• DOC Fix return type for `d2_tweedie_score`

  #31285 opened May 1, 2025

• COSMIT Use `get_namespace_and_device` in `multilabel_confusion_matrix`

  #31287 opened May 1, 2025

• FIX ConvergenceWarning in plot_gpr_on_structured_data (#31164)

  #31289 opened May 1, 2025

• Bump pypa/cibuildwheel from 2.23.2 to 2.23.3 in the actions group

  #31291 opened May 1, 2025

• Fix internal kwargs leakage in scorers (metrics._scorer)

  #31293 opened May 1, 2025

• DOC Remove reference to entropy API

  #31294 opened May 2, 2025

• Use OS-specific cache directories instead of home directory

  #31295 opened May 2, 2025

5 Issues closed by 2 people

• Use more complex data in `test_roc_curve_display.py`

  #31243 closed Apr 30, 2025

• ⚠️ CI failed on Linux_Runs.pylatest_conda_forge_mkl (last failure: Apr 26, 2025) ⚠️

  #31256 closed Apr 30, 2025

• Finding indexes with `np.where(condition)` or `np.asarray(condition).nonzero()`

  #30400 closed Apr 29, 2025

• ⚠️ CI failed on Wheel builder (last failure: Apr 28, 2025) ⚠️

  #31257 closed Apr 28, 2025

• Hangs in LogisticRegression with high intercept_scaling number

  #31248 closed Apr 28, 2025

8 Issues opened by 5 people

• `_safe_indexing` triggers `SettingWithCopyWarning` when used with `slice`

  #31290 opened May 1, 2025

• `make_scorer(needs_sample_weight=True)` wrongly injects `needs_sample_weight` into the scoring function

  #31288 opened May 1, 2025

• Clarification of output array type when metrics accept multiclass/multioutput

  #31286 opened May 1, 2025

• ⚠️ CI failed on Linux_Nightly.pylatest_pip_scipy_dev (last failure: May 02, 2025) ⚠️

  #31284 opened May 1, 2025

• ⚠️ CI failed on Linux_free_threaded.pylatest_free_threaded (last failure: May 02, 2025) ⚠️

  #31283 opened May 1, 2025

• Automatically move `y_true` to the same device and namespace as `y_pred` for metrics

  #31274 opened Apr 30, 2025

• ⚠️ CI failed on Wheel builder (last failure: May 02, 2025) ⚠️

  #31269 opened Apr 29, 2025

• Change the default data directory

  #31267 opened Apr 28, 2025

61 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• adding adaptive learning rate for minibatch k-means

  #30051 commented on May 1, 2025 • 14 new comments

• ENH add CAP curve

  #28972 commented on Apr 30, 2025 • 14 new comments

• WIP: Display parameters in HTML representation

  #30763 commented on May 2, 2025 • 12 new comments

• ENH: Finalize Yeo-Johnson implementation with scipy.stats in PowerTransformer (#27818)

  #31227 commented on May 1, 2025 • 10 new comments

• DOC Clarify usage of d2_pinball_score with model selection tools

  #31239 commented on Apr 30, 2025 • 9 new comments

• feat: tprocess

  #30482 commented on Apr 30, 2025 • 7 new comments

• DOC Scale data before using k-neighbours regression (fixes #31200)

  #31201 commented on Apr 29, 2025 • 6 new comments

• DOC Merge plot_svm_margin.py and plot_separating_hyperplane.py into plot_svm_hyperplane_margin.py

  #31045 commented on Apr 28, 2025 • 4 new comments

• ENH Add zero division handling to cohen_kappa_score

  #31172 commented on Apr 30, 2025 • 4 new comments

• FEA add temperature scaling to `CalibratedClassifierCV`

  #31068 commented on May 1, 2025 • 3 new comments

• FEAT Support precomputed distance matrix for `PairwiseDistancesReductions`

  #29483 commented on Apr 30, 2025 • 3 new comments

• Array API support for pairwise kernels

  #29822 commented on Apr 28, 2025 • 3 new comments

• ENH Add replace_undefined_by to accuracy_score

  #31187 commented on Apr 29, 2025 • 3 new comments

• DOC update and improve the `sample_weight` entry in the glossary

  #30564 commented on Apr 30, 2025 • 3 new comments

• ENH add narwhals as dependency

  #31127 commented on May 1, 2025 • 2 new comments

• DOC added reference to plot_grid_search_stats.py

  #30965 commented on Apr 28, 2025 • 1 new comment

• FEA Callbacks base infrastructure + progress bars (Alternative to #27663)

  #28760 commented on Apr 28, 2025 • 1 new comment

• DOC add link to cluster_plot_ward_structured_vs_unstructured in _aggl…

  #30861 commented on Apr 28, 2025 • 1 new comment

• DOC Add link to plot_gmm_pdf.py in GaussianMixture examples

  #31230 commented on Apr 28, 2025 • 1 new comment

• Fix #30832 LogisticRegressionCV with underrepresented classes

  #31126 commented on Apr 30, 2025 • 1 new comment

• MNT Clean-up deprecations for 1.7: Remainder column type of ColumnTransformer

  #31167 commented on May 2, 2025 • 1 new comment

• doc: add link to the plot_gmm_covariances example

  #31249 commented on Apr 28, 2025 • 0 new comments

• MNT Make sample_weight checking more consistent in regression metrics

  #30886 commented on Apr 28, 2025 • 0 new comments

• ENH: Faster Eigen Decomposition For Isomap & KernelPCA

  #31247 commented on May 1, 2025 • 0 new comments

• DOC: Add missing link to plot_logistic.py in Logistic Regression documentation

  #30942 commented on Apr 28, 2025 • 0 new comments

• Division by zero in OneVsRest's `predict_proba` (see #31224); bugfix for `test_ovo_decision_function`

  #31228 commented on Apr 29, 2025 • 0 new comments

• DOC Added an example reference for plot_manifold_sphere.py

  #30959 commented on Apr 29, 2025 • 0 new comments

• Add array api support for jaccard score

  #31204 commented on Apr 28, 2025 • 0 new comments

• New `MKL` Module adding Multiple Kernel Learning estimators/transformers

  #31166 commented on May 1, 2025 • 0 new comments

• Fix Add _indic_tokenizer for Indic support

  #31130 commented on Apr 30, 2025 • 0 new comments

• Fix: added pseudo-likelihood normalization option in RBM #23179

  #31099 commented on Apr 30, 2025 • 0 new comments

• FIX _safe_indexing for pyarrow

  #31040 commented on Apr 29, 2025 • 0 new comments

• Enhance ValidationCurveDisplay for categorical parameters

  #31043 commented on Apr 28, 2025 • 0 new comments

• Fix `PandasAdapter` causes crash or misattributed features

  #31079 commented on Apr 28, 2025 • 0 new comments

• DOC Update plots in Categorical Feature Support in GBDT example

  #31062 commented on May 2, 2025 • 0 new comments

• Add Categorical Feature Support to `IterativeImputer`

  #31219 commented on Apr 25, 2025 • 0 new comments

• OneVsRestClassifier when all estimators predict a sample belongs to the other classes

  #31224 commented on Apr 26, 2025 • 0 new comments

• Add sankey style confusion matrix visualization

  #31133 commented on Apr 28, 2025 • 0 new comments

• Faster Eigen Decomposition for Isomap & KernelPCA

  #31246 commented on Apr 28, 2025 • 0 new comments

• RFC Supporting `scipy.sparse.sparray`

  #26418 commented on Apr 28, 2025 • 0 new comments

• Crash in T-SNE

  #28368 commented on Apr 28, 2025 • 0 new comments

• RFC adopt narwhals for dataframe support

  #31049 commented on Apr 29, 2025 • 0 new comments

• Provide examples on how to customize the scikit-learn classes

  #28828 commented on Apr 29, 2025 • 0 new comments

• Add links to examples from the docstrings and user guide

  #30621 commented on Apr 30, 2025 • 0 new comments

• Fix ConvergenceWarning in `plot_gpr_on_structured_data.py` example

  #31164 commented on May 1, 2025 • 0 new comments

• ⚠️ CI failed on Ubuntu_Atlas.ubuntu_atlas (last failure: Feb 19, 2025) ⚠️

  #27846 commented on May 2, 2025 • 0 new comments

• ⚠️ CI failed on Linux.pymin_conda_forge_openblas_min_dependencies (last failure: Jan 19, 2025) ⚠️

  #29909 commented on May 2, 2025 • 0 new comments

• ⚠️ CI failed on Linux_Docker.debian_32bit (last failure: Apr 19, 2025) ⚠️

  #29802 commented on May 2, 2025 • 0 new comments

• FEA Add missing-value support to sparse splitter in RandomForest and ExtraTrees

  #29542 commented on May 2, 2025 • 0 new comments

• Feature request: forcing a Gram matrix to be positive definite

  #8590 commented on May 2, 2025 • 0 new comments

• [MRG+1] Enable using 2SD scaling in StandardScaler

  #10875 commented on Apr 28, 2025 • 0 new comments

• [MRG] Implement calibration loss metrics

  #11096 commented on Apr 30, 2025 • 0 new comments

• [MRG] [ENH] Exposes latent mean and variance for GPCs

  #22227 commented on May 2, 2025 • 0 new comments

• FEA Implementation of "threshold-dependent metric per threshold value" curve

  #25639 commented on May 1, 2025 • 0 new comments

• API Gaussian Process: change default behavior of `sample_y`

  #25789 commented on Apr 30, 2025 • 0 new comments

• MNT Deprecate metrics.pairwise.paired_*_distances and paired_distances public functions

  #27129 commented on Apr 30, 2025 • 0 new comments

• ENH Add Friedman's H-squared

  #28375 commented on Apr 30, 2025 • 0 new comments

• Added sample weight handling to BinMapper under HGBT

  #29641 commented on Apr 25, 2025 • 0 new comments

• ENH add `from_cv_results` in `RocCurveDisplay` (single `RocCurveDisplay`)

  #30399 commented on Apr 30, 2025 • 0 new comments

• MNT Deprecate metrics.pairwise.paired_*_distances and paired_distances public functions

  #30537 commented on Apr 30, 2025 • 0 new comments

• Investigate GaussianMixture array API support

  #30777 commented on Apr 28, 2025 • 0 new comments