27 Pull requests merged by 16 people

• API Rename base_estimator in CalibratedClassifierCV

  #22054 merged May 30, 2022

• MNT Minor refactor of `n_support`

  #23353 merged May 30, 2022

• DOC Rework plot_hashing_vs_dict_vectorizer.py example

  #23266 merged May 30, 2022

• TST Update pytest to 7.0

  #23444 merged May 30, 2022

• MAINT float 32bit support for `DistanceMetric`

  #22764 merged May 30, 2022

• Typo in deprecation of plot_roc_curve function

  #23489 merged May 30, 2022

• DOC Ensures that fbeta_score passes numpydoc validation

  #23486 merged May 30, 2022

• DOC Fix typo in random forest feature importance comparison example.

  #23484 merged May 28, 2022

• DOC Ensures that inplace_swap_column passes numpydoc validation

  #23476 merged May 27, 2022

• DOC Ensures that f_oneway passes numpydoc validation.

  #23468 merged May 26, 2022

• DOC Ensures that sklearn.feature_selection._univariate_selection.chi2 passes numpydoc validation.

  #23467 merged May 26, 2022

• DOC Fixes order in whats new

  #23466 merged May 25, 2022

• MNT Removed `_safe_accumulator_op` for first-pass algorithm in `_assert_all_finite`

  #23446 merged May 25, 2022

• MNT Small refactor of `_bagging.py`

  #23460 merged May 25, 2022

• FIX attribute error is BIRCH

  #23395 merged May 25, 2022

• MAINT Remove commented dissimilarities

  #23457 merged May 25, 2022

• DOC fix typo in OneHotEncoder docstring

  #23455 merged May 25, 2022

• EHN Change default value of `n_init` in `cluster.KMeans` and `cluster.k_means`

  #23038 merged May 25, 2022

• DOC Update testing section url in main README

  #23435 merged May 25, 2022

• DOC Fix distribution information in wine_data.rst

  #23452 merged May 25, 2022

• DOC fix typos

  #23456 merged May 25, 2022

• DOC Point GradientBoosting towards HistGradientBoosting

  #23340 merged May 24, 2022

• ENH Deprecate `class_weight_` in regression/single class models in SVM module

  #22898 merged May 24, 2022

• Add BSD license trove classifier

  #23451 merged May 24, 2022

• CI unpin pip now that pip 22.1.1 has been released

  #23448 merged May 24, 2022

• CI Use lock files for CircleCI doc builds

  #23429 merged May 24, 2022

• DOCS Fix broken link

  #23449 merged May 24, 2022

17 Pull requests opened by 11 people

• TST update test_dist_metrics to use global_random_seed env variable

  #23453 opened May 25, 2022

• MNT Param validation: do not expose internal values in error msg

  #23459 opened May 25, 2022

• ENH Added warning for `ndcg_score` when used w/ negative `y_true` values

  #23461 opened May 25, 2022

• [WIP] MNT Use _validate_params in NMF and MiniBatchNMF

  #23463 opened May 25, 2022

• TST use global_random_seed in sklearn/linear_model/tests/test_base.py

  #23465 opened May 25, 2022

• MNT Improves comment when CI fails a second time

  #23469 opened May 26, 2022

• MNT Deprecate `affinity` in `AgglomerativeClustering`

  #23470 opened May 26, 2022

• FIX Added validation for `TSNE.perplexity` against data

  #23471 opened May 26, 2022

• [MRG] MNT Use _validate_params in HistGradientBoostingClassifier and Regressor

  #23479 opened May 27, 2022

• ENH Uses x[i] to represent features in tree plotting

  #23480 opened May 27, 2022

• TfidfTransformer Use _validate_params in TfidfTransformer

  #23483 opened May 28, 2022

• [WIP] Use _validate_params in PCA

  #23485 opened May 29, 2022

• DOC Add kernel glossary

  #23487 opened May 30, 2022

• TST Add test for quasi equality for `PairwiseDistancesReduction` results

  #23490 opened May 30, 2022

• LinearRegression uses _validate_parameters

  #23491 opened May 30, 2022

• MNT Removes parallel sphinx build by default

  #23492 opened May 30, 2022

• MNT Fixes lgtm config for Cpp

  #23493 opened May 30, 2022

17 Issues closed by 7 people

• Enable pytest to work with >=7.0

  #22396 closed May 30, 2022

• Default constant value in SimpleImputer with heterogeneous data

  #23439 closed May 30, 2022

• Optimizing recall calculation for micro-averaging

  #8126 closed May 30, 2022

• ⚠️ CI failed on Wheel builder ⚠️

  #23482 closed May 29, 2022

• Introduce a mixin to reactor `get_n_splits()` in `model_selection` module

  #7235 closed May 27, 2022

• Problem with export_graphviz and expat

  #6522 closed May 27, 2022

• Precision errors in KernelPCA

  #5970 closed May 27, 2022

• ConfusionMatrixDisplay.from_estimator(normalize='true') returns

  #23478 closed May 27, 2022

• ⚠️ CI failed on Wheel builder ⚠️

  #23454 closed May 27, 2022

• "No module named 'sklearn.preprocessing.data'"

  #23474 closed May 26, 2022

• AttributeError in Birch for StandardScaled values

  #23269 closed May 25, 2022

• Counterintuitive AttributeError in Birch for very large numbers

  #17966 closed May 25, 2022

• Enable pytest to work with >=7.0

  #23458 closed May 25, 2022

• Change KMeans n_init default value to 1.

  #9729 closed May 25, 2022

• Formula to compute BIC in sklearn.mixture.GaussianMixture wrong

  #23443 closed May 25, 2022

• Scan examples to see where HistGradientBoostingRegressor should replace GradientBoostingRegressor

  #23231 closed May 25, 2022

• Deprecate n_support_ and class_weight_ from SVR class

  #14788 closed May 24, 2022

3 Issues opened by 3 people

• ⚠️ CI failed on Wheel builder ⚠️

  #23488 opened May 30, 2022

• Make all estimators use `_validate_params`

  #23462 opened May 25, 2022

• Add neighbors algorithm based on NSW graphs

  #23450 opened May 24, 2022

48 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.

• ENH Cythonize `dump_svmlight_file`

  #23127 commented on May 30, 2022 • 22 new comments

• ENH Cythonize `_assert_all_finite` using stop-on-first strategy

  #23197 commented on May 30, 2022 • 20 new comments

• FIX Enables label_ranking_average_precision_score to support sparse y_true

  #23442 commented on May 24, 2022 • 12 new comments

• MAINT 32bit datasets support for `PairwiseDistancesReduction`

  #22590 commented on May 30, 2022 • 10 new comments

• DOC Improve the mathematical description of Logistic Regression

  #22382 commented on May 30, 2022 • 9 new comments

• ENH propagate `eigen_tol` to all eigen solver

  #23210 commented on May 27, 2022 • 7 new comments

• [MRG] Add min_tpr parameter to roc_auc_score, allow both min_tpr and max_fpr

  #19751 commented on May 30, 2022 • 5 new comments

• FEA add Cholesky based Newton solver to GLMs

  #23314 commented on May 25, 2022 • 5 new comments

• RidgeCV doesn't allow `alpha=0`

  #23074 commented on May 26, 2022 • 4 new comments

• [MRG] fixes #14257 - Group aware Time-based cross validation

  #16236 commented on May 30, 2022 • 4 new comments

• Grouping of infrequent categories in 𝗢𝗻𝗲𝗛𝗼𝘁𝗘𝗻𝗰𝗼𝗱𝗲𝗿

  #23401 commented on May 25, 2022 • 3 new comments

• Ensure that functions's docstrings pass numpydoc validation

  #21350 commented on May 30, 2022 • 3 new comments

• FIX SimpleImputer uses dtype seen in fit for transform

  #22063 commented on May 30, 2022 • 3 new comments

• ENH Add `eigh` solver to `FastICA`

  #22527 commented on May 30, 2022 • 3 new comments

• Use the function check_scalar for parameters validation

  #21927 commented on May 25, 2022 • 2 new comments

• KNeighborsClassifier not accepting a DistanceMetric

  #22348 commented on May 27, 2022 • 2 new comments

• validation check for precomputed gram matrix fails erroneously when using float32 data

  #21997 commented on May 28, 2022 • 2 new comments

• [MRG] Generative Classification

  #2468 commented on May 29, 2022 • 2 new comments

• Fix gram validation: dtype-aware tolerance

  #22059 commented on May 30, 2022 • 2 new comments

• Poor performance of KNeighborsClassifier for sklearn version >=0.24.2

  #23427 commented on May 24, 2022 • 1 new comment

• RandomizedSearchCV: warnings cannot be suppressed

  #12939 commented on May 24, 2022 • 1 new comment

• Include drop='last' to OneHotEncoder

  #23436 commented on May 25, 2022 • 1 new comment

• roc_plot.py example gives different macro-averaged AUC than roc_auc_score

  #13546 commented on May 25, 2022 • 1 new comment

• Library should not be printing to stdout without verbose option

  #6929 commented on May 26, 2022 • 1 new comment

• cache_size > 2000 not recognized in SVM classifiers

  #8012 commented on May 26, 2022 • 1 new comment

• Optimizing assert_all_finite check

  #11681 commented on May 26, 2022 • 1 new comment

• Include cython sources in coverage

  #8163 commented on May 30, 2022 • 1 new comment

• the use of chi2 with the iris dataset is incorrect

  #17286 commented on May 30, 2022 • 1 new comment

• ENH improve _weighted_percentile to provide several interpolation

  #17768 commented on May 30, 2022 • 1 new comment

• ENH add Naive Bayes Metaestimator `ColumnwiseNB` (aka "GeneralNB")

  #22574 commented on May 29, 2022 • 1 new comment

• Include `HDBSCAN` as a sub-module for `sklearn.cluster`

  #22616 commented on May 30, 2022 • 1 new comment

• [FEAT] Zero division nan

  #23183 commented on May 28, 2022 • 1 new comment

• FET add support for manhattan distances in KNN imputer

  #23286 commented on May 30, 2022 • 1 new comment

• MNT add isort to pre-commit hooks

  #23362 commented on May 30, 2022 • 1 new comment

• Inconsistent density estimator sampling APIs

  #10539 commented on May 25, 2022 • 0 new comments

• Feature request: Group aware Time-based cross validation

  #14257 commented on May 27, 2022 • 0 new comments

• fetch_openml difference between pandas and liac-arff parser

  #23381 commented on May 27, 2022 • 0 new comments

• Link to logos in Community section of website

  #23072 commented on May 27, 2022 • 0 new comments

• Add prefit to VotingClassifier

  #7382 commented on May 27, 2022 • 0 new comments

• LogisticRegression freezed when X containing large number

  #7486 commented on May 30, 2022 • 0 new comments

• Infinite loop or never returns for logistic regression in nearly degenerate case

  #7489 commented on May 30, 2022 • 0 new comments

• Scikit-learn office hours Monday May 30, 2022 from 4 pm to 5 pm (UTC) on the scikit-learn discord channel

  #23070 commented on May 30, 2022 • 0 new comments

• ENH Monotonic Contraints for Tree-based models

  #13649 commented on May 30, 2022 • 0 new comments

• [WIP] ENH Add trust-ncg option to LogisticRegression

  #22236 commented on May 24, 2022 • 0 new comments

• [MRG] Update gridsearch example for multimetric scoring.

  #22279 commented on May 26, 2022 • 0 new comments

• ENH Add eigh as a solver in MDS

  #22330 commented on May 30, 2022 • 0 new comments

• ENH Added warning for RidgeCV

  #23031 commented on May 25, 2022 • 0 new comments

• MNT Replaced `np.ndarray` with memview where applicable in `linear_model/_cd_fast.pyx`

  #23147 commented on May 26, 2022 • 0 new comments