Insights: scikit-learn/scikit-learn

27 Pull requests merged by 18 people

• MAINT Update CI dependencies

  #24453 merged Sep 17, 2022

• MAINT Clean deprecation for 1.2: plot functions

  #24445 merged Sep 16, 2022

• DOC Ensures that check_is_fitted passes numpydoc validation

  #24454 merged Sep 16, 2022

• DOC fix labels in legend of plot_logistic

  #24455 merged Sep 16, 2022

• DOC Fix `monotonic_cst` description in HGBT docstrings

  #24396 merged Sep 16, 2022

• DOC ensures sklearn.utils.multiclass.class_distribution passes numpydoc validation

  #24452 merged Sep 16, 2022

• API Rename OneHotEncoder option sparse to sparse_output

  #24412 merged Sep 16, 2022

• DOC Update estimator representation example

  #24439 merged Sep 16, 2022

• EHN Add multilabel classification support for `StackingClassifier`

  #24146 merged Sep 16, 2022

• ENH Adds class_weight to HistGradientBoostingClassifier

  #22014 merged Sep 16, 2022

• DOC Ensures that sparsefuncs.count_nonzero passes numpydoc validation

  #24447 merged Sep 16, 2022

• ENH Remove validation from `__init__` for `SGDOneClassSVM`

  #24433 merged Sep 15, 2022

• MAINT Clean deprecation for 1.2: assert_warns

  #24442 merged Sep 15, 2022

• DOC ensures sklearn.utils.safe_sqr passes numpydoc validation

  #24437 merged Sep 15, 2022

• DOC Rework plot_grid_search_text_feature_extraction.py example

  #23740 merged Sep 15, 2022

• FEA Add support for micro averaging in ovr-roc-auc

  #24338 merged Sep 14, 2022

• DOC Rework `plot_affinity_propagation.py` to make it colorblind friendly

  #24335 merged Sep 13, 2022

• MAINT Clean deprecation for 1.2: losses in gradient boosting

  #24394 merged Sep 13, 2022

• API Deprecate `n_feature_` fitted attribute in PCA

  #24421 merged Sep 13, 2022

• MAINT Clean deprecation for 1.2: NMF

  #24393 merged Sep 12, 2022

• FIX Ensure that GaussianProcessRegressor predict method does not modify input

  #24405 merged Sep 12, 2022

• MAINT Clean deprecation for 1.2: KernelPCA

  #24406 merged Sep 12, 2022

• MAINT Clean deprecation for 1.2: Ransac losses

  #24408 merged Sep 12, 2022

• DOC fix repeated typos in docstrings

  #24416 merged Sep 12, 2022

• Lines 2359 to 2362 needed editing

  #24417 merged Sep 12, 2022

• MNT Update license year to 2022

  #24418 merged Sep 12, 2022

• DOC ensures sklearn.utils.safe_mask passes numpydoc validation

  #24425 merged Sep 12, 2022

12 Pull requests opened by 11 people

• Add questions category and contents in FAQ

  #24420 opened Sep 11, 2022

• ENH csr_row_norms optimization

  #24426 opened Sep 12, 2022

• CI Make pytest err on PytestUnraisableExceptionWarning

  #24438 opened Sep 14, 2022

• SLEP006: ClassifierChain and RegressorChain routing

  #24443 opened Sep 15, 2022

• DOC SLEP019 Governance Update

  #24444 opened Sep 15, 2022

• [CI] Add wheel builds for python 3.11

  #24446 opened Sep 15, 2022

• ENH type_of_target raises ValueError for invalid inputs

  #24448 opened Sep 16, 2022

• Comment uses of deprecated plot functions in past release highlights

  #24456 opened Sep 16, 2022

• [Doc] Fix hyperlink formatting

  #24457 opened Sep 16, 2022

• Fixed AgglomerativeClustering's distance_threshold misleading statement

  #24460 opened Sep 17, 2022

• Doc fix csc median axis 0

  #24461 opened Sep 18, 2022

• DOC ensures sklearn.utils.multiclass.type_of_target passes numpydoc validation.

  #24463 opened Sep 18, 2022

18 Issues closed by 10 people

• Please change Confusion Matrix Heatmap cmap.

  #24458 closed Sep 18, 2022

• Legend confuses lines in the logistic regression example

  #24451 closed Sep 16, 2022

• The loss squared_error is not supported for SGDRegressor

  #24449 closed Sep 16, 2022

• Rename OneHotEncoder option sparse to sparse_output

  #24265 closed Sep 16, 2022

• Add a demo of the HTML repr to "Compact estimator representations" example

  #21289 closed Sep 16, 2022

• StackingClassifier to support multilabel classification

  #17979 closed Sep 16, 2022

• Implement class_weight in HistGradientBoostingClassifier

  #14735 closed Sep 16, 2022

• Remove validation from `__init__` and `set_params`

  #21406 closed Sep 15, 2022

• `cross_val_score` crashes with `StackingRegressor`

  #24430 closed Sep 15, 2022

• Different dataset for different models when using StackingClassifier

  #24434 closed Sep 15, 2022

• `MinMaxScaler.fit_transform()` overflow when input array is `float16`

  #24428 closed Sep 14, 2022

• Wrong illustration for ARD

  #20740 closed Sep 13, 2022

• "StackingClassifier" throws ValueError when cv = "prefit"

  #24429 closed Sep 13, 2022

• Deprecate n_features_ in PCA

  #24387 closed Sep 13, 2022

• Add option to compute permutation_importance on a random subset of rows

  #20245 closed Sep 13, 2022

• Eigenvalue in Kernel PCA

  #4795 closed Sep 12, 2022

• BUG: GaussianProcessRegressor.predict inplace modifies input X, when passed via kernel

  #24340 closed Sep 12, 2022

• Unexpected Normalization

  #2601 closed Sep 11, 2022

5 Issues opened by 5 people

• DOC See Also descriptions do not match for multiple functions/classes

  #24464 opened Sep 18, 2022

• Implement p-value splitting criterion for Decision Trees

  #24462 opened Sep 18, 2022

• StackingRegressor does not allow classifiers as estimators (and vice versa)

  #24432 opened Sep 14, 2022

• Python 3.11 wheels

  #24427 opened Sep 13, 2022

• ⚠️ CI failed on Linux_Nightly.pylatest_pip_scipy_dev ⚠️

  #24424 opened Sep 12, 2022

188 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 Introduces set_output API for pandas output

  #23734 commented on Sep 16, 2022 • 48 new comments

• DOC Rework plot_roc.py example

  #24200 commented on Sep 15, 2022 • 45 new comments

• ENH Monotonic Contraints for Tree-based models

  #13649 commented on Sep 17, 2022 • 22 new comments

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

  #22616 commented on Sep 16, 2022 • 13 new comments

• FIX adapt epsilon value depending of the dtype of the input

  #24354 commented on Sep 14, 2022 • 11 new comments

• FEA Fused sparse-dense support for `PairwiseDistancesReduction`

  #23585 commented on Sep 16, 2022 • 8 new comments

• SLEP006 - Metadata Routing task list

  #22893 commented on Sep 13, 2022 • 4 new comments

• GridSearchCV & RandomizedSearchCV has a ranking issue when test scores are same. #21895

  #21925 commented on Sep 14, 2022 • 4 new comments

• MAINT Clean deprecation for 1.2: get_feature_names

  #24395 commented on Sep 16, 2022 • 4 new comments

• LocalOutlierFactor exposes methods that it shouldn't

  #21876 commented on Sep 15, 2022 • 3 new comments

• Ensure that functions's docstrings pass numpydoc validation

  #21350 commented on Sep 16, 2022 • 3 new comments

• MLPRegressor - Validation score wrongly defined

  #24411 commented on Sep 17, 2022 • 3 new comments

• SLEP006: Metadata routing for bagging

  #24250 commented on Sep 12, 2022 • 3 new comments

• GridSearchCV does not seem to recognize whether estimators from StackingClassifier are fitted or not

  #24409 commented on Sep 12, 2022 • 2 new comments

• Incorrect documentation for `warm_start` behavior on BaseForest-derived classes

  #20435 commented on Sep 13, 2022 • 2 new comments

• Segmentation Fault in KMeans

  #23574 commented on Sep 16, 2022 • 2 new comments

• Added option to use standard idf term for TfidfTransformer and TfidfVectorizer

  #14748 commented on Sep 13, 2022 • 2 new comments

• Adding a reset weights strategy to Adaboost Regressor

  #21010 commented on Sep 14, 2022 • 2 new comments

• ENH Implement get_feature_names_out for FeatureUnion in case of "passthrough"

  #24058 commented on Sep 16, 2022 • 2 new comments

• FIX behaviour of `check_estimator` with `require_positive` tags of a regressor

  #24136 commented on Sep 15, 2022 • 2 new comments

• [WIP] ENH Tree Splitter: 50% performance improvement with radix sort and feature ranks

  #24239 commented on Sep 15, 2022 • 2 new comments

• MNT Do not update docs with deprecated decorator

  #24410 commented on Sep 12, 2022 • 2 new comments

• Navigation on FAQ is not the best

  #23839 commented on Sep 11, 2022 • 1 new comment

• Mixture Entropy Estimation for Gaussian Mixture Models

  #19030 commented on Sep 12, 2022 • 1 new comment

• Make TfidfVectorizer serializable in a reproducible way

  #18669 commented on Sep 12, 2022 • 1 new comment

• Is there an issue with TimeSeriesSplit and the learning_curve?

  #7834 commented on Sep 13, 2022 • 1 new comment

• ValueError buffer source array is read-only when computing manahattan_distances of a CSR matrix inside Parallel

  #7981 commented on Sep 13, 2022 • 1 new comment

• GridSearchCV & RandomizedSearchCV has a ranking issue when test scores are same.

  #21895 commented on Sep 13, 2022 • 1 new comment

• Add class_weight feature to MLPClassifier

  #9113 commented on Sep 16, 2022 • 1 new comment

• `type_of_target` returns `unknown` for valid arrays of dtype `object`

  #24355 commented on Sep 16, 2022 • 1 new comment

• API options for Pandas output

  #20258 commented on Sep 16, 2022 • 1 new comment

• Coordinate with other scientific python projects to use shared tools and policy to upload nightly build wheels

  #24312 commented on Sep 17, 2022 • 1 new comment

• Inconsistency in AUC ROC and AUPR API

  #24381 commented on Sep 17, 2022 • 1 new comment

• FEA add PredictionErrorDisplay

  #18020 commented on Sep 16, 2022 • 1 new comment

• DOC Add example comparing permutation importance and SHAP

  #18139 commented on Sep 16, 2022 • 1 new comment

• Draft implementation of non-parametric quantile methods (RF, Extra Trees and Nearest Neighbors)

  #19754 commented on Sep 12, 2022 • 1 new comment

• ENH add x and y to importance getter rfe

  #21935 commented on Sep 15, 2022 • 1 new comment

• ENH Paired haversine

  #22705 commented on Sep 15, 2022 • 1 new comment

• Using callable in RandomForest oob_score parameter to define the oob scoring strategy.

  #23043 commented on Sep 13, 2022 • 1 new comment

• FEA add Cholesky based Newton solver to GLMs

  #23314 commented on Sep 15, 2022 • 1 new comment

• ENH: Added "walk forward" feature to sklearn.model_selection.TimeSeriesSplit

  #23780 commented on Sep 12, 2022 • 1 new comment

• [MRG] Fix Erroneous Avg. Loss calculation

  #23798 commented on Sep 15, 2022 • 1 new comment

• TST use global_random_seed in sklearn/cluster/tests/test_affinity_propagation.py

  #23838 commented on Sep 12, 2022 • 1 new comment

• [MRG] Add common tests for classifiers reducing to less than two classes via sample weights during fit.

  #24140 commented on Sep 17, 2022 • 1 new comment

• ENH Add dtype preservation to FeatureAgglomeration

  #24346 commented on Sep 11, 2022 • 1 new comment

• PERF `PairwiseDistancesReductions` roadmap

  #22587 commented on Sep 12, 2022 • 0 new comments

• ClassifierChain should only accept multilabel-indicator

  #19853 commented on Sep 13, 2022 • 0 new comments

• LabelEncoder ValueError on unseen labels is too broad.

  #19830 commented on Sep 13, 2022 • 0 new comments

• ElasticNet (and Lasso) for multiple outputs is not described correctly

  #19868 commented on Sep 13, 2022 • 0 new comments

• PLSRegression include percentage of variance in Y explained by each component

  #19896 commented on Sep 13, 2022 • 0 new comments

• Implement Nystroem.inverse_transform

  #19899 commented on Sep 13, 2022 • 0 new comments

• FunctionTransformer does not handle object dtype when check_inverse is True

  #19905 commented on Sep 13, 2022 • 0 new comments

• KBinsDiscretizer doesn't handle NAs

  #19920 commented on Sep 13, 2022 • 0 new comments

• SimpleImputer is very slow with DataFrames

  #19926 commented on Sep 13, 2022 • 0 new comments

• Allow NMF to run on data that is not strictly nonnegative

  #19941 commented on Sep 13, 2022 • 0 new comments

• StandardScaler with_mean=False fits mean_

  #20006 commented on Sep 13, 2022 • 0 new comments

• enable regression step coefs after fit

  #20033 commented on Sep 13, 2022 • 0 new comments

• CategoricalNB : it needs to add proper treatment for unseen values in validation data (validation data has new values than train data )

  #20034 commented on Sep 13, 2022 • 0 new comments

• sklearn.tree.export_dict

  #20051 commented on Sep 13, 2022 • 0 new comments

• Adding user-provided validation data added to randomforest models other than using non selected indices from bootstrapping

  #20064 commented on Sep 13, 2022 • 0 new comments

• Doc should mentioned that support vector will be empty with precomputed kernel

  #20068 commented on Sep 13, 2022 • 0 new comments

• ColumnTransformer give "TypeError: invalid type promotion"

  #20090 commented on Sep 13, 2022 • 0 new comments

• Metrics for prediction intervals

  #20162 commented on Sep 13, 2022 • 0 new comments

• Optional `stop_words_` attribute for CountVectorizer and TfidfVectorizer

  #20178 commented on Sep 13, 2022 • 0 new comments

• AttributError when accessing `coef_` after constructor for `ElasticNet` subclasses

  #20224 commented on Sep 13, 2022 • 0 new comments

• Add the ability for the user to provide specific landmarks points to approximate the Nystroem kernel approximation

  #20232 commented on Sep 13, 2022 • 0 new comments

• Elastic Net Regression with Linear Constraints

  #20226 commented on Sep 13, 2022 • 0 new comments

• Extention of Gaussian Mixture Models to Wrapped and Semiwrapped Gaussian Mixture Models

  #20270 commented on Sep 13, 2022 • 0 new comments

• Precision @ Recall K || Recall @ Precision K

  #20266 commented on Sep 13, 2022 • 0 new comments

• Numerical stability problems in GaussianProcessRegressor on 32 bit Python

  #20337 commented on Sep 13, 2022 • 0 new comments

• Confusion_matrix: drilldown to underlying data.

  #20341 commented on Sep 13, 2022 • 0 new comments

• `model_selection.cross_validate` doesn't pass `groups` argument to estimator

  #20349 commented on Sep 13, 2022 • 0 new comments

• AdaBoost's training error can increase with a larger number of trees

  #20443 commented on Sep 13, 2022 • 0 new comments

• 'Shuffle' in the GroupKFold function and RepeatedGroupKFold function

  #20520 commented on Sep 13, 2022 • 0 new comments

• Score decision tree using only samples that propagate to leaves trained with >N datapoints

  #20537 commented on Sep 13, 2022 • 0 new comments

• RegressorChain support for Pipelines including ColumnTransformer

  #20557 commented on Sep 13, 2022 • 0 new comments

• `tree.export_text`: add `class_names` argument to mirror `plot_tree`

  #20576 commented on Sep 13, 2022 • 0 new comments

• PCA inconsistency with adding/subtracting mean for transform and inverse_transform when n_components=0

  #20591 commented on Sep 13, 2022 • 0 new comments

• Parallelization in LocallyLinearEmbedding

  #20595 commented on Sep 13, 2022 • 0 new comments

• CalibratedClassifierCV does not handle well sample_weight when ensemble=False

  #20610 commented on Sep 13, 2022 • 0 new comments

• Unable to construct trees on 32 bit machine

  #20665 commented on Sep 13, 2022 • 0 new comments

• Threads awaiting for GIL in Forest estimators

  #20666 commented on Sep 13, 2022 • 0 new comments

• Halving*SearchCV selects estimator with nan score as best estimator

  #20678 commented on Sep 13, 2022 • 0 new comments

• HalvingGridSearchCV number of classes

  #20775 commented on Sep 13, 2022 • 0 new comments

• Support for 2d sample weights for MultiOutputEstimators

  #20801 commented on Sep 13, 2022 • 0 new comments

• Adding Oblique Trees (Forest-RC) to the Cythonized Tree Module

  #20819 commented on Sep 13, 2022 • 0 new comments

• Rank about GridSearchCV

  #20852 commented on Sep 13, 2022 • 0 new comments

• Allow users to pass their own grid to partial dependence

  #20890 commented on Sep 13, 2022 • 0 new comments

• Allow `Pipeline` to whether pass or not `y` to some transformer

  #20898 commented on Sep 13, 2022 • 0 new comments

• Add an option to plot the iso-fbeta lines in PrecisionRecallDisplay

  #20917 commented on Sep 13, 2022 • 0 new comments

• get_params method in cross-validation splitters

  #20920 commented on Sep 13, 2022 • 0 new comments

• TransformedTargetClassifier

  #20952 commented on Sep 13, 2022 • 0 new comments

• red/green scatter plots. Colorblindness friendlyness in Documentation

  #5435 commented on Sep 14, 2022 • 0 new comments

• Chain on decision_function or predict_proba in ClassifierChain

  #9247 commented on Sep 14, 2022 • 0 new comments

• deprecate using fit without y in GridSearchCV

  #9088 commented on Sep 14, 2022 • 0 new comments

• Add `fit_params` to `IterativeImputer`'s `fit` method

  #20954 commented on Sep 14, 2022 • 0 new comments

• incompatible HTML representation for RandomizedSearchCV

  #20971 commented on Sep 14, 2022 • 0 new comments

• Explain LocalOutlierFactor's Labelling Behaviour to Users

  #20989 commented on Sep 14, 2022 • 0 new comments

• Feature request: confusion matrix could report confidence intervals

  #21007 commented on Sep 14, 2022 • 0 new comments

• CountVectorizer(lowercase=True,strip_accents='unicode') may produce vocab that contains uppercase chars

  #21207 commented on Sep 14, 2022 • 0 new comments

• Support `dualtree=True` (or other kwargs) in `NearestNeighbors.kneighbors()`

  #21209 commented on Sep 14, 2022 • 0 new comments

• Kernel Density adding .sample() support for linear and exponential kernels

  #21224 commented on Sep 14, 2022 • 0 new comments

• SpectralClustering breaks normalized Laplacian when the row sums are negative

  #21274 commented on Sep 14, 2022 • 0 new comments

• Make it possible to pass an arbitrary probablistic classifier as `method` for CalibratedClassifierCV

  #21280 commented on Sep 14, 2022 • 0 new comments

• HTML representation of estimators: center the diagrams

  #21290 commented on Sep 14, 2022 • 0 new comments

• Another input needed for the parameter `n_features_to_select` in SequentialFeatureSelector

  #21291 commented on Sep 14, 2022 • 0 new comments

• BayesianRidge prediction standard deviation affected by uniform sample weights

  #24313 commented on Sep 14, 2022 • 0 new comments

• LogisticRegression with SAGA using sample_weight does not converge

  #21305 commented on Sep 14, 2022 • 0 new comments

• Performance of the RBF kernel in epsilon-SVR (SVM)

  #21312 commented on Sep 14, 2022 • 0 new comments

• Improve make_scorer for multiclass classification, or add new metrics to "common cases" predefined values

  #21313 commented on Sep 14, 2022 • 0 new comments

• `check_estimator` wrong behavior with `require_positive` tags of a regressor

  #21323 commented on Sep 14, 2022 • 0 new comments

• NDCG score doesn't work with binary relevance and a list of 1 element

  #21335 commented on Sep 14, 2022 • 0 new comments

• SequentialFeatureSelector.fit() groups parameter

  #21356 commented on Sep 14, 2022 • 0 new comments

• Skewed Gaussian Process Regressor

  #21377 commented on Sep 14, 2022 • 0 new comments

• Allow inspect.PartialDependenceDisplay to work with a prediction function

  #21388 commented on Sep 14, 2022 • 0 new comments

• add sklearn.metrics Display class to plot Precision/Recall/F1 for probability thresholds

  #21391 commented on Sep 14, 2022 • 0 new comments

• [Feature Request] Add support for negative coefficient constraints

  #21394 commented on Sep 14, 2022 • 0 new comments

• Beta-divergence example promotes the usage of a non-public API

  #21402 commented on Sep 14, 2022 • 0 new comments

• Using a custom rbf kernel function for sklearn's SVC is way faster than built-in method

  #21410 commented on Sep 14, 2022 • 0 new comments

• Use a stable sorting algorithm when selecting the `max_features` in TfidfVectorizer

  #21446 commented on Sep 14, 2022 • 0 new comments

• Ridge with cholesky solver returns NaN

  #21447 commented on Sep 14, 2022 • 0 new comments

• ColumnTransformers should use get_feature_names_out() when columns attribute is not available

  #21452 commented on Sep 14, 2022 • 0 new comments

• chi2 should support categorical data other than binary or document count

  #21455 commented on Sep 14, 2022 • 0 new comments

• There is no list of regressors that support multioutput regression natively

  #21484 commented on Sep 14, 2022 • 0 new comments

• [DOC] Outdated description of attributes oob_decision_function_ and oob_prediction_ in bagging estimators

  #21490 commented on Sep 14, 2022 • 0 new comments

• RFC Migrate away from numpy.distutils before CPython 3.12 (October 2023)

  #21499 commented on Sep 14, 2022 • 0 new comments

• TST Check correct interactions of `class_weight` and `sample_weight`

  #21504 commented on Sep 14, 2022 • 0 new comments

• permutation_test_score shuffling when a group enforces a specific label

  #21543 commented on Sep 14, 2022 • 0 new comments

• add graph-based clustering

  #21570 commented on Sep 14, 2022 • 0 new comments

• Conflict between key-values and build-in method name in `Bunch`

  #21595 commented on Sep 14, 2022 • 0 new comments

• `_check_feature_names` raises UserWarning when accesing bagged estimators

  #21599 commented on Sep 14, 2022 • 0 new comments

• Default Value for SimpleImputer with all missing values

  #21639 commented on Sep 14, 2022 • 0 new comments

• MeanThreshold, MedianThreshold, and other threshold support in GenericUnivariateSelect

  #21699 commented on Sep 14, 2022 • 0 new comments

• fit_params for Adaboost estimator

  #21706 commented on Sep 14, 2022 • 0 new comments

• Weights for sklearn.model_selection.KFold

  #21719 commented on Sep 14, 2022 • 0 new comments

• Improve documentation of the `impute` module

  #21722 commented on Sep 14, 2022 • 0 new comments

• Missing values break feature selection with pipeline estimator

  #21743 commented on Sep 14, 2022 • 0 new comments

• Enhance semi_supervised.LabelPropagation

  #21783 commented on Sep 14, 2022 • 0 new comments

• sklearn.cluster.OPTICS uses all cores when minkowski's p=2

  #21786 commented on Sep 14, 2022 • 0 new comments

• CountVectorizer out of dictionary features

  #21790 commented on Sep 14, 2022 • 0 new comments

• Sparse NeighborhoodComponentsAnalysis

  #21815 commented on Sep 14, 2022 • 0 new comments

• Add drop_intermediate to precision_recall_curve

  #21825 commented on Sep 14, 2022 • 0 new comments

• MultiOutputClassifier should have `decision_function`

  #21861 commented on Sep 15, 2022 • 0 new comments

• Non-standard "negative_outlier_factor_"

  #21875 commented on Sep 15, 2022 • 0 new comments

• Lasso(alpha) = SGDRegressor(alpha, penalty="l1"), but Ridge(alpha) = SGDRegressor(alpha / len(train_set))

  #21891 commented on Sep 15, 2022 • 0 new comments

• Optionally passing X and y to importance_getter callable in Recursive Feature Elimination

  #21934 commented on Sep 15, 2022 • 0 new comments

• QoL improvement: Add monotonicity constraints specification using dict of feature names in HistGradientBoostingClassifier/Regressor

  #21961 commented on Sep 15, 2022 • 0 new comments

• Allow other initialization strategies for IterativeImputer

  #22770 commented on Sep 16, 2022 • 0 new comments

• KFold splitter falsely claims it supports groups

  #22848 commented on Sep 16, 2022 • 0 new comments

• Improve tests to make them run on variously typed data using the `global_dtype` fixture

  #22881 commented on Sep 16, 2022 • 0 new comments

• Implement Min-Cut clustering

  #23080 commented on Sep 16, 2022 • 0 new comments

• Yeo-Johnson Power Transformer gives Numpy warning

  #23319 commented on Sep 16, 2022 • 0 new comments

• The data type of input data for LinearRegression class will affect the results

  #23376 commented on Sep 16, 2022 • 0 new comments

• t-SNE score for generalized embedding method

  #23715 commented on Sep 16, 2022 • 0 new comments

• Symmetry of `mutual_info_classif` and `mutual_info_regression`.

  #23720 commented on Sep 16, 2022 • 0 new comments

• NearestCentroid not handling properly distance metrics other than Manhattan or Euclidean.

  #23890 commented on Sep 16, 2022 • 0 new comments

• Vector Quantization Example increases rather than decreases memory use

  #23896 commented on Sep 16, 2022 • 0 new comments

• Sparse Bernoulli Naive Bayes

  #23939 commented on Sep 16, 2022 • 0 new comments

• Unsupervised K-Means Clustering Algorithm

  #23967 commented on Sep 16, 2022 • 0 new comments

• Test Failed on CICD Pipeline with varied LinearRegression predictions

  #23970 commented on Sep 16, 2022 • 0 new comments

• check_estimator cannot validate SGDClassifier with log_loss

  #24025 commented on Sep 16, 2022 • 0 new comments

• RandomForestClassifier RAM memory increase on newer versions

  #24124 commented on Sep 16, 2022 • 0 new comments

• sklearn.svm.SVR use more RAM memory on newer versions

  #24138 commented on Sep 16, 2022 • 0 new comments

• LogisticRegression doesn't have an offset option

  #24155 commented on Sep 16, 2022 • 0 new comments

• SGDClassifier initial lr undocumented

  #24172 commented on Sep 16, 2022 • 0 new comments

• AgglomerativeClustering's distance_threshold is misleading

  #24176 commented on Sep 16, 2022 • 0 new comments

• Allow X in func or transformer in TransformedTargetRegressor

  #24199 commented on Sep 16, 2022 • 0 new comments

• LinearDiscriminantAnalysis cannot predict_proba if labels are constant

  #17401 commented on Sep 16, 2022 • 0 new comments

• KNeighborsClassifier: allow p value for Minkowski calculation to be less than 1.0 (and greater than 0)

  #22811 commented on Sep 17, 2022 • 0 new comments

• Add option to RocCurveDisplay to display the average of different length ROC curves

  #23983 commented on Sep 17, 2022 • 0 new comments

• Balltree's node_data radii seems to be incorrect

  #24228 commented on Sep 17, 2022 • 0 new comments

• TimeSeriesSplit add skip parameter

  #24243 commented on Sep 17, 2022 • 0 new comments

• Add RepeatedStratifiedGroupKFold

  #24247 commented on Sep 17, 2022 • 0 new comments

• Coordinate descent convergence warnings

  #4780 commented on Sep 17, 2022 • 0 new comments

• ⚠️ CI failed on Linux.ubuntu_atlas ⚠️

  #24131 commented on Sep 18, 2022 • 0 new comments

• ENH Support CSR matrix in type_of_target

  #14862 commented on Sep 17, 2022 • 0 new comments

• ENH Extend PDP for nominal categorical features

  #18298 commented on Sep 13, 2022 • 0 new comments

• TST suppress convergence warnings in coordinate descent

  #20144 commented on Sep 11, 2022 • 0 new comments

• Implemented "precision at recall k" and "recall at precision k"

  #20877 commented on Sep 13, 2022 • 0 new comments

• Added support for sampling for exponential, linear and epanechnikov kernels in KernelDensity

  #21225 commented on Sep 14, 2022 • 0 new comments

• add graph-based clustering

  #21571 commented on Sep 14, 2022 • 0 new comments

• [WIP] decision_function for MultiOutputClassifier

  #21960 commented on Sep 15, 2022 • 0 new comments

• Added a new method to specify monotonicity constraints using dict of feature names in HistGradientBoostingClassifier/Regressor. Fixes #21961

  #21962 commented on Sep 15, 2022 • 0 new comments

• FEAT SLEP006: metadata routing

  #24027 commented on Sep 12, 2022 • 0 new comments

• FEA add LearningCurveDisplay to show plot learning curve

  #24084 commented on Sep 16, 2022 • 0 new comments

• Adds gain scoring metrics

  #24121 commented on Sep 14, 2022 • 0 new comments

• DOC use KBinsDiscretizer in lieu of KMeans in vector quantization example

  #24374 commented on Sep 13, 2022 • 0 new comments

• DOC added description for RANSAC algorithm

  #24402 commented on Sep 15, 2022 • 0 new comments