scikit-learn/scikit-learn

23 Pull requests merged by 14 people

• Merged #14708 [MRG] Fixing Scikit learn build on pypy Aug 21, 2019
• Merged #13911 [MRG] Native support for missing values in GBDTs Aug 21, 2019
• Merged #14694 MAINT:Fix assert raises in `sklearn/feature_extraction/tests/` Aug 21, 2019
• Merged #14697 MAINT:Fix assert raises in `sklearn/feature_selection/tests/` Aug 21, 2019
• Merged #14699 MAINT:Fix assert raises in `sklearn/manifold/tests/` Aug 21, 2019
• Merged #14701 [MRG] BUG: Passes sample_weight to roc_auc_curve Aug 21, 2019
• Merged #14680 [MRG] Use tag requires_positive_X for NMF + ComplementNB Aug 20, 2019
• Merged #12887 [MRG] Adds Minimal Cost-Complexity Pruning to Decision Trees Aug 20, 2019
• Merged #14651 Added sktime to related projects Aug 20, 2019
• Merged #14689 [MRG] MAINT Fixes azure pipeline on OSX Aug 20, 2019
• Merged #14684 DOC fix typos in manifold learning user guide Aug 20, 2019
• Merged #14686 [MRG] MAINT/CI pin sphinx version until release of jinja2 Aug 20, 2019
• Merged #14678 [MRG] Use return_X_y=True with load_boston where appropriate Aug 20, 2019
• Merged #14477 DOC add missing attributes to Bagging, AdaBoost algorithms #14312 Aug 19, 2019
• Merged #11221 [MRG] DOC: add binder links to examples Aug 19, 2019
• Merged #14679 MAINT Remove the use of assert_raises* in decomposition Aug 18, 2019
• Merged #14676 MNT: datasets tests Aug 18, 2019
• Merged #14670 MAINT:Fix assert raises in `sklearn/compose/tests/` Aug 17, 2019
• Merged #14674 MNT:Remove the use of assert_raises and assert_raises_regex Aug 17, 2019
• Merged #14666 Fix LassoLars copy_X comment format Aug 16, 2019
• Merged #9288 [MRG] add seeds when n_jobs=1 and use seed as random_state Aug 16, 2019
• Merged #14660 clarify that sklearn.metric.pairwise doesn't provide callables for pairwise_kernel Aug 15, 2019
• Merged #14512 [MRG] DOC document default values for Lars Aug 15, 2019

15 Pull requests proposed by 14 people

• Proposed #14663 [MRG] cache get_params to improve clone performance Aug 15, 2019
• Proposed #14675 [MRG] Fix Tutorial example code lacking context #13566 Aug 17, 2019
• Proposed #14677 ENH: adds support for list of list for multilabel_indicator target types Aug 17, 2019
• Proposed #14681 [NOMRG] Try docs with numpydoc#221 Aug 18, 2019
• Proposed #14682 Add bootstrap sample size limit to forest ensembles Aug 18, 2019
• Proposed #14683 [WIP] Added 2 common tests for sparse matrix densification. Aug 19, 2019
• Proposed #14691 MAINT filter deprecation warnings triggered by all_estimators Aug 20, 2019
• Proposed #14696 [WIP] Support sample weights in HGBT Aug 20, 2019
• Proposed #14698 [MRG] Adds Correlation Based Feature Selection Aug 20, 2019
• Proposed #14702 estimator check for not calling __array_function__ Aug 20, 2019
• Proposed #14704 [MRG] FIX reimplement StratifiedKFold to avoid variation in test size Aug 21, 2019
• Proposed #14705 [WIP] Enforce positiveness in tests using enforce_estimator_tags_X Aug 21, 2019
• Proposed #14706 [MRG] key_precomputed Aug 21, 2019
• Proposed #14707 MAINT:Fix assert raises in `sklearn/metrics/cluster/tests/` Aug 21, 2019
• Proposed #14710 FIX encode target for scoring when using early stopping in HistGradientBoostinClassifier Aug 21, 2019

13 Issues closed by 10 people

• Closed #14608 Multinomial Hessian-vector product returns input times alpha (binary one is not affected) Aug 21, 2019
• Closed #14693 GridSearchCV with Pipeline without Predictor Aug 20, 2019
• Closed #6557 add post-pruning for decision trees Aug 20, 2019
• Closed #14688 Example in documentation sklearn.metrics.pairwise.haversine_distances should have radians conversion. Aug 20, 2019
• Closed #14413 `test_sag_regressor_computed_correctly` fails sometimes on py35_ubuntu_atlas_32bit Aug 18, 2019
• Closed #13578 Azure CI error Aug 17, 2019
• Closed #4348 cross_validation.StratifieldKFold random_state argument is not working Aug 17, 2019
• Closed #14669 sklearn._built_utils missing resulting in build from source errors . Aug 16, 2019
• Closed #14667 Create a Stub Scaler Aug 16, 2019
• Closed #9784 KMeans gives slightly different result for n_jobs=1 vs. n_jobs > 1 Aug 16, 2019
• Closed #10890 `_pairwise_callable` function doesn't work with pairwise metrics functions from sklearn itself Aug 15, 2019
• Closed #14661 RandomizedSearchCV does not work in a Pipeline when evaluating alternative classifiers Aug 15, 2019
• Closed #6191 preprocessing.label_binarize for 2 classes gives single vector Aug 15, 2019

16 Issues created by 9 people

• Opened #14714 Improve example on StratifiedKFold in user guide Aug 21, 2019
• Opened #14713 Simplify spectral clustering solver logic Aug 21, 2019
• Opened #14712 More generic estimator checks Aug 21, 2019
• Opened #14711 `sklearn/tree/*` refactoring Aug 21, 2019
• Opened #14709 HistGradientBoostingClassifier does not work with string target when early stopping turned on Aug 21, 2019
• Opened #14703 Reorganize examples into different subsections Aug 21, 2019
• Opened #14700 "English" stop-word list. Aug 20, 2019
• Opened #14695 Run doctest on VarianceThreshold Aug 20, 2019
• Opened #14692 should utils.resample accept sample_weight? Aug 20, 2019
• Opened #14690 Pandas error when using ColumnTransformer Aug 20, 2019
• Opened #14687 Classifiers may not work with arrays defining __array_function__ Aug 19, 2019
• Opened #14673 StratifiedKFold makes fold-sizes very unequal Aug 16, 2019
• Opened #14672 RidgeClassifierCV bug when using scoring Aug 16, 2019
• Opened #14671 BUG: sklearn/utils/multiclass.type_of_target inconsistent for similar inputs Aug 16, 2019
• Opened #14665 Document when to use single backticks Aug 15, 2019
• Opened #14664 Add more dtype details to docstring standard doc Aug 15, 2019

73 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.

• 33 new comments Open #11047 [MRG] FEA: Stacking estimator for classification and regression Aug 22, 2019
• 29 new comments Open #14300 Minimal Generalized linear models implementation (L2 + lbfgs) Aug 18, 2019
• 29 new comments Open #14475 [MRG] EHN add support for scalar, slice and mask in safe_indexing axis=0 Aug 22, 2019
• 25 new comments Open #14593 [MRG] Adds _MultimetricScorer for Optimized Scoring Aug 22, 2019
• 20 new comments Open #14381 [MRG] ENH Disassemble check estimator Aug 22, 2019
• 12 new comments Open #13603 [WIP] Add n_features_in_ attribute to BaseEstimator Aug 21, 2019
• 12 new comments Open #14611 Separate documentation for contributing and developing estimators in to different files #14582 Aug 21, 2019
• 11 new comments Open #14306 Multicore scalability of the Histogram-based GBDT Aug 16, 2019
• 11 new comments Open #14649 Remove the use of assert_raises and assert_raises_regex from the tests Aug 20, 2019
• 11 new comments Open #14653 ENH: refactored utils/validation._check_sample_weights() and added stronger sample_weights checks for all estimators Aug 21, 2019
• 9 new comments Open #10482 [MRG+1] Generalize the use of precomputed sparse distance matrices, for estimators which use nearest neighbors Aug 17, 2019
• 9 new comments Open #14602 [WIP] text vectorizers should raise warnings when user params will be unused Aug 18, 2019
• 9 new comments Open #14646 [MRG] Adds Plotting API to Partial Dependence Aug 19, 2019
• 8 new comments Open #12852 [MRG] Adds KNNImputer Aug 22, 2019
• 7 new comments Open #14603 MLPClassifier is behaving abnormally in both training and inference in Kubernetes deployment Aug 20, 2019
• 7 new comments Open #14644 Mixin order fix for tags Aug 21, 2019
• 6 new comments Open #12893 [MRG] Unary encoder -- continued Aug 21, 2019
• 5 new comments Open #13246 [WIP] Common test for equivalence between sparse and dense matrices. Aug 21, 2019
• 5 new comments Open #14324 Fixes #14311: Adding check_constant_features function to test that estimators work … Aug 22, 2019
• 4 new comments Open #14036 [QST] Updating indices creation for split Aug 21, 2019
• 4 new comments Open #14641 kernel_approximation.Nystroem does not support precomputed kernel Aug 22, 2019
• 3 new comments Open #14563 OrdinalEncoder with string categories should force user to specify the order Aug 16, 2019
• 3 new comments Open #7910 [MRG+1] Support Vector Data Description Aug 22, 2019
• 3 new comments Open #10711 [MRG] Enhancement: Add MAPE as an evaluation metric Aug 20, 2019
• 3 new comments Open #11635 [MRG] Allow nan/inf in feature selection Aug 20, 2019
• 3 new comments Open #12319 [MRG] add lobpcg svd_solver to PCA and TruncatedSVD Aug 20, 2019
• 3 new comments Open #13096 [MRG] FIX #13056 - FastICA whitening problem Aug 18, 2019
• 3 new comments Open #14241 MRG add n_features_out_ attribute Aug 21, 2019
• 3 new comments Open #14315 feature names - NamedArray Aug 16, 2019
• 3 new comments Open #14450 Fixes #13609: Fixing y_score initialization so that it is not initialized as a column … Aug 22, 2019
• 2 new comments Open #4667 RidgeCV should provide best_score_ Aug 16, 2019
• 2 new comments Open #14338 IterativeImputer not converging (at all) Aug 16, 2019
• 2 new comments Open #14566 LassoLarsIC information criteria incorrectly calculated Aug 20, 2019
• 2 new comments Open #14216 Remove the use of assert_raises and assert_raises_regex from the tests Aug 21, 2019
• 2 new comments Open #14648 adding multilabel capability to voting classifier and bagging classifier Aug 22, 2019
• 2 new comments Open #7333 [MRG] Allow sample weights and other fit_params for RFE Aug 22, 2019
• 2 new comments Open #14516 [MRG] Turn on early stopping in histogram GBDT by default Aug 21, 2019
• 2 new comments Open #14591 don't overwrite precompute=True in lassocv Aug 21, 2019
• 2 new comments Open #14643 Created Pitfalls section and included SelectKBest Aug 15, 2019
• 2 new comments Open #14647 Amg arpack workaround fix Aug 21, 2019
• 1 new comment Open #14650 KDTree / BallTree seg fault Aug 15, 2019
• 1 new comment Open #9603 least_angle.py in lars_path - shapes not aligned on properly formatted data with specific alpha Aug 16, 2019
• 1 new comment Open #9453 PLS* should not transform on y Aug 16, 2019
• 1 new comment Open #14485 ImportError: dlopen: cannot load any more object with static TLS with torch built with gcc 5.5 Aug 17, 2019
• 1 new comment Open #14347 Use return_X_y=True when applicable in examples Aug 18, 2019
• 1 new comment Open #14568 n_jobs=-1, "timeout or by a memory leak.", UserWarning Aug 18, 2019
• 1 new comment Open #14094 Suggestion: Fill with feature mean instead of 0 for VarianceThreshold.inverse_transform Aug 20, 2019
• 1 new comment Open #2807 Add support for SVDD (one-class SVM) Aug 21, 2019
• 1 new comment Open #4406 Out of bag probability estimates for Random Forests Aug 21, 2019
• 1 new comment Open #8642 Implement `nbytes` or `__sizeof__` (or equivalent) for estimators Aug 21, 2019
• 1 new comment Open #14044 Estimator tag overwriting and update in _get_tags Aug 22, 2019
• 1 new comment Open #9555 [WIP] Implement Gower similarity coeficient Aug 22, 2019
• 1 new comment Open #10875 [MRG+1] Enable using 2SD scaling in StandardScaler Aug 21, 2019
• 1 new comment Open #11070 [MRG] FIX sklearn.cluster.spectral_clustering fails with `np.matrix` input (#10993) Aug 20, 2019
• 1 new comment Open #11725 [MRG] Adding min_tpr parameter to roc_auc_score Aug 18, 2019
• 1 new comment Open #12479 [MRG] Add calibration loss metric in classification Aug 20, 2019
• 1 new comment Open #13470 RFE/RFECV step enhancements Aug 20, 2019
• 1 new comment Open #13896 [MRG] implement least absolute deviation loss in GBDTs Aug 21, 2019
• 1 new comment Open #14048 Extended get_feature_names() for ColumnTransformer to include 'passthrough' Aug 18, 2019
• 1 new comment Open #14560 [MRG] Binned regression cv Aug 22, 2019
• 1 new comment Open #14654 [Fix] Classifier chain multiclass predict_proba and decision_function Aug 19, 2019
• 0 new comments Open #10733 API for returning datasets as DataFrames Aug 17, 2019
• 0 new comments Open #11816 Validate MD5 checksum of downloaded ARFF in fetch_openml Aug 20, 2019
• 0 new comments Open #12730 Add paired test for cross-validation Aug 20, 2019
• 0 new comments Open #10360 Verbose VotingClassifier Aug 20, 2019
• 0 new comments Open #10905 permutation_test_score has no user guide Aug 20, 2019
• 0 new comments Open #10903 CalibratedClassifierCV with mode = 'isotonic' has predict_proba return infinite probabilities Aug 20, 2019
• 0 new comments Open #12297 `prefit` option missing for voting? Aug 21, 2019
• 0 new comments Open #11772 Inconsistent documentation for C parameter in SVM estimators Aug 21, 2019
• 0 new comments Open #7156 update documentation to reflect fit, transform, and predict parameter… Aug 16, 2019
• 0 new comments Open #14417 ENH Adds roc weighted scorers to SCORERS Aug 15, 2019
• 0 new comments Open #14466 Fixes estimator tags entry in glossary seems outdated #14083 Aug 17, 2019
• 0 new comments Open #14622 Remove redundant max iter Aug 15, 2019