Efficiency Reduce impute.KNNImputer asymptotic memory usage by chunking pairwise distance computation. #16397 by Joel Nothman.

Fix Fixed a bug in metrics.plot_roc_curve where the name of the estimator was passed in the metrics.RocCurveDisplay instead of the parameter name. It results in a different plot when calling metrics.RocCurveDisplay.plot for the subsequent times. #16500 by Guillaume Lemaitre.

Fix Fixed a bug in metrics.plot_precision_recall_curve where the name of the estimator was passed in the metrics.PrecisionRecallDisplay instead of the parameter name. It results in a different plot when calling metrics.PrecisionRecallDisplay.plot for the subsequent times. #16505 by Guillaume Lemaitre.

Fix Fix a bug which converted a list of arrays into a 2-D object array instead of a 1-D array containing NumPy arrays. This bug was affecting neighbors.NearestNeighbors.radius_neighbors. #16076 by Guillaume Lemaitre and Alex Shacked.

Fix cluster.KMeans with algorithm="elkan" now uses the same stopping criterion as with the default algorithm="full". #15930 by @inder128.

Fix inspection.permutation_importance will return the same importances when a random_state is given for both n_jobs=1 or n_jobs>1 both with shared memory backends (thread-safety) and isolated memory, process-based backends. Also avoid casting the data as object dtype and avoid read-only error on large dataframes with n_jobs>1 as reported in #15810. Follow-up of #15898 by Shivam Gargsya. #15933 by Guillaume Lemaitre and Olivier Grisel.

Fix inspection.plot_partial_dependence and inspection.PartialDependenceDisplay.plot now consistently checks the number of axes passed in. #15760 by Thomas Fan.

Fix metrics.plot_confusion_matrix now raises error when normalize is invalid. Previously, it runs fine with no normalization. #15888 by Hanmin Qin.

Fix metrics.plot_confusion_matrix now colors the label color correctly to maximize contrast with its background. #15936 by Thomas Fan and @DizietAsahi.

Fix metrics.classification_report does no longer ignore the value of the zero_division keyword argument. #15879 by Bibhash Chandra Mitra.

Fix Fixed a bug in metrics.plot_confusion_matrix to correctly pass the values_format parameter to the ConfusionMatrixDisplay plot() call. #15937 by Stephen Blystone.

Fix model_selection.GridSearchCV and model_selection.RandomizedSearchCV accept scalar values provided in fit_params. Change in 0.22 was breaking backward compatibility. #15863 by Adrin Jalali and Guillaume Lemaitre.

Fix Removed abstractmethod decorator for the method _check_X in naive_bayes.BaseNB that could break downstream projects inheriting from this deprecated public base class. #15996 by Brigitta Sipőcz.

Fix preprocessing.QuantileTransformer now guarantees the quantiles_ attribute to be completely sorted in non-decreasing manner. #15751 by Tirth Patel.

Fix semi_supervised.LabelPropagation and semi_supervised.LabelSpreading now allow callable kernel function to return sparse weight matrix. #15868 by Niklas Smedemark-Margulies.

Fix utils.check_array now correctly converts pandas DataFrame with boolean columns to floats. #15797 by Thomas Fan.

Fix utils.check_is_fitted accepts back an explicit attributes argument to check for specific attributes as explicit markers of a fitted estimator. When no explicit attributes are provided, only the attributes that end with a underscore and do not start with double underscore are used as “fitted” markers. The all_or_any argument is also no longer deprecated. This change is made to restore some backward compatibility with the behavior of this utility in version 0.21. #15947 by Thomas Fan.

API Change From version 0.24 base.BaseEstimator.get_params will raise an AttributeError rather than return None for parameters that are in the estimator’s constructor but not stored as attributes on the instance. #14464 by Joel Nothman.

Fix Fixed a bug that made calibration.CalibratedClassifierCV fail when given a sample_weight parameter of type list (in the case where sample_weights are not supported by the wrapped estimator). #13575 by William de Vazelhes.

Feature cluster.SpectralClustering now accepts precomputed sparse neighbors graph as input. #10482 by Tom Dupre la Tour and Kumar Ashutosh.

Enhancement cluster.SpectralClustering now accepts a n_components parameter. This parameter extends SpectralClustering class functionality to match cluster.spectral_clustering. #13726 by Shuzhe Xiao.

Fix Fixed a bug where cluster.KMeans produced inconsistent results between n_jobs=1 and n_jobs>1 due to the handling of the random state. #9288 by Bryan Yang.

Fix Fixed a bug where elkan algorithm in cluster.KMeans was producing Segmentation Fault on large arrays due to integer index overflow. #15057 by Vladimir Korolev.

Fix MeanShift now accepts a max_iter with a default value of 300 instead of always using the default 300. It also now exposes an n_iter_ indicating the maximum number of iterations performed on each seed. #15120 by Adrin Jalali.

Fix cluster.AgglomerativeClustering and cluster.FeatureAgglomeration now raise an error if affinity='cosine' and X has samples that are all-zeros. #7943 by @mthorrell.

Feature Adds compose.make_column_selector which is used with compose.ColumnTransformer to select DataFrame columns on the basis of name and dtype. #12303 by Thomas Fan.

Fix Fixed a bug in compose.ColumnTransformer which failed to select the proper columns when using a boolean list, with NumPy older than 1.12. #14510 by Guillaume Lemaitre.

Fix Fixed a bug in compose.TransformedTargetRegressor which did not pass **fit_params to the underlying regressor. #14890 by Miguel Cabrera.

Fix The compose.ColumnTransformer now requires the number of features to be consistent between fit and transform. A FutureWarning is raised now, and this will raise an error in 0.24. If the number of features isn’t consistent and negative indexing is used, an error is raised. #14544 by Adrin Jalali.

Feature cross_decomposition.PLSCanonical and cross_decomposition.PLSRegression have a new function inverse_transform to transform data to the original space. #15304 by Jaime Ferrando Huertas.

Enhancement decomposition.KernelPCA now properly checks the eigenvalues found by the solver for numerical or conditioning issues. This ensures consistency of results across solvers (different choices for eigen_solver), including approximate solvers such as 'randomized' and 'lobpcg' (see #12068). #12145 by Sylvain Marié

Fix Fixed a bug where cross_decomposition.PLSCanonical and cross_decomposition.PLSRegression were raising an error when fitted with a target matrix Y in which the first column was constant. #13609 by Camila Williamson.

Fix cross_decomposition.CCA now produces the same results with scipy 1.3 and previous scipy versions. #15661 by Thomas Fan.

Feature datasets.fetch_openml now supports heterogeneous data using pandas by setting as_frame=True. #13902 by Thomas Fan.

Feature datasets.fetch_openml now includes the target_names in the returned Bunch. #15160 by Thomas Fan.

Enhancement The parameter return_X_y was added to datasets.fetch_20newsgroups and datasets.fetch_olivetti_faces . #14259 by Sourav Singh.

Enhancement datasets.make_classification now accepts array-like weights parameter, i.e. list or numpy.array, instead of list only. #14764 by Cat Chenal.

Enhancement The parameter normalize was added to

datasets.fetch_20newsgroups_vectorized. #14740 by Stéphan Tulkens

Fix Fixed a bug in datasets.fetch_openml, which failed to load an OpenML dataset that contains an ignored feature. #14623 by Sarra Habchi.

Efficiency decomposition.NMF(solver='mu') fitted on sparse input matrices now uses batching to avoid briefly allocating an array with size (#non-zero elements, n_components). #15257 by Mart Willocx.

Enhancement decomposition.dict_learning and decomposition.dict_learning_online now accept method_max_iter and pass it to decomposition.sparse_encode. #12650 by Adrin Jalali.

Enhancement decomposition.SparseCoder, decomposition.DictionaryLearning, and decomposition.MiniBatchDictionaryLearning now take a transform_max_iter parameter and pass it to either decomposition.dict_learning or decomposition.sparse_encode. #12650 by Adrin Jalali.

Enhancement decomposition.IncrementalPCA now accepts sparse matrices as input, converting them to dense in batches thereby avoiding the need to store the entire dense matrix at once. #13960 by Scott Gigante.

Fix decomposition.sparse_encode now passes the max_iter to the underlying linear_model.LassoLars when algorithm='lasso_lars'. #12650 by Adrin Jalali.

Fix dummy.DummyClassifier now handles checking the existence of the provided constant in multiouput cases. #14908 by Martina G. Vilas.

API Change The default value of the strategy parameter in dummy.DummyClassifier will change from 'stratified' in version 0.22 to 'prior' in 0.24. A FutureWarning is raised when the default value is used. #15382 by Thomas Fan.

API Change The outputs_2d_ attribute is deprecated in dummy.DummyClassifier and dummy.DummyRegressor. It is equivalent to n_outputs > 1. #14933 by Nicolas Hug

Enhancement A warning will now be raised if a parameter choice means that another parameter will be unused on calling the fit() method for feature_extraction.text.HashingVectorizer, feature_extraction.text.CountVectorizer and feature_extraction.text.TfidfVectorizer. #14602 by Gaurav Chawla.

Fix Functions created by build_preprocessor and build_analyzer of feature_extraction.text.VectorizerMixin can now be pickled. #14430 by Dillon Niederhut.

Fix feature_extraction.text.strip_accents_unicode now correctly removes accents from strings that are in NFKD normalized form. #15100 by Daniel Grady.

Fix Fixed a bug that caused feature_extraction.DictVectorizer to raise an OverflowError during the transform operation when producing a scipy.sparse matrix on large input data. #15463 by Norvan Sahiner.

API Change Deprecated unused copy param for feature_extraction.text.TfidfVectorizer.transform it will be removed in v0.24. #14520 by Guillem G. Subies.

Enhancement Updated the following feature_selection estimators to allow NaN/Inf values in transform and fit: feature_selection.RFE, feature_selection.RFECV, feature_selection.SelectFromModel, and feature_selection.VarianceThreshold. Note that if the underlying estimator of the feature selector does not allow NaN/Inf then it will still error, but the feature selectors themselves no longer enforce this restriction unnecessarily. #11635 by Alec Peters.

Fix Fixed a bug where feature_selection.VarianceThreshold with threshold=0 did not remove constant features due to numerical instability, by using range rather than variance in this case. #13704 by Roddy MacSween.

Feature Gaussian process models on structured data: gaussian_process.GaussianProcessRegressor and gaussian_process.GaussianProcessClassifier can now accept a list of generic objects (e.g. strings, trees, graphs, etc.) as the X argument to their training/prediction methods. A user-defined kernel should be provided for computing the kernel matrix among the generic objects, and should inherit from gaussian_process.kernels.GenericKernelMixin to notify the GPR/GPC model that it handles non-vectorial samples. #15557 by Yu-Hang Tang.

Efficiency gaussian_process.GaussianProcessClassifier.log_marginal_likelihood and gaussian_process.GaussianProcessRegressor.log_marginal_likelihood now accept a clone_kernel=True keyword argument. When set to False, the kernel attribute is modified, but may result in a performance improvement. #14378 by Masashi Shibata.

API Change From version 0.24 gaussian_process.kernels.Kernel.get_params will raise an AttributeError rather than return None for parameters that are in the estimator’s constructor but not stored as attributes on the instance. #14464 by Joel Nothman.

Major Feature Added impute.KNNImputer, to impute missing values using k-Nearest Neighbors. #12852 by Ashim Bhattarai and Thomas Fan and #15010 by Guillaume Lemaitre.

Feature impute.IterativeImputer has new skip_compute flag that is False by default, which, when True, will skip computation on features that have no missing values during the fit phase. #13773 by Sergey Feldman.

Efficiency impute.MissingIndicator.fit_transform avoid repeated computation of the masked matrix. #14356 by Harsh Soni.

Fix impute.IterativeImputer now works when there is only one feature. By Sergey Feldman.

Fix Fixed a bug in impute.IterativeImputer where features where imputed in the reverse desired order with imputation_order either "ascending" or "descending". #15393 by Venkatachalam N.

Major Feature inspection.permutation_importance has been added to measure the importance of each feature in an arbitrary trained model with respect to a given scoring function. #13146 by Thomas Fan.

Feature inspection.partial_dependence and inspection.plot_partial_dependence now support the fast ‘recursion’ method for ensemble.HistGradientBoostingClassifier and ensemble.HistGradientBoostingRegressor. #13769 by Nicolas Hug.

Enhancement inspection.plot_partial_dependence has been extended to now support the new visualization API described in the User Guide. #14646 by Thomas Fan.

Enhancement inspection.partial_dependence accepts pandas DataFrame and pipeline.Pipeline containing compose.ColumnTransformer. In addition inspection.plot_partial_dependence will use the column names by default when a dataframe is passed. #14028 and #15429 by Guillaume Lemaitre.

Fix Fixed a bug where kernel_approximation.Nystroem raised a KeyError when using kernel="precomputed". #14706 by Venkatachalam N.

Efficiency The ‘liblinear’ logistic regression solver is now faster and requires less memory. #14108, #14170, #14296 by Alex Henrie.

Enhancement linear_model.BayesianRidge now accepts hyperparameters alpha_init and lambda_init which can be used to set the initial value of the maximization procedure in fit. #13618 by Yoshihiro Uchida.

Fix linear_model.Ridge now correctly fits an intercept when X is sparse, solver="auto" and fit_intercept=True, because the default solver in this configuration has changed to sparse_cg, which can fit an intercept with sparse data. #13995 by Jérôme Dockès.

Fix linear_model.Ridge with solver='sag' now accepts F-ordered and non-contiguous arrays and makes a conversion instead of failing. #14458 by Guillaume Lemaitre.

Fix linear_model.LassoCV no longer forces precompute=False when fitting the final model. #14591 by Andreas Müller.

Fix linear_model.RidgeCV and linear_model.RidgeClassifierCV now correctly scores when cv=None. #14864 by Venkatachalam N.

Fix Fixed a bug in linear_model.LogisticRegressionCV where the scores_, n_iter_ and coefs_paths_ attribute would have a wrong ordering with penalty='elastic-net'. #15044 by Nicolas Hug

Fix linear_model.MultiTaskLassoCV and linear_model.MultiTaskElasticNetCV with X of dtype int and fit_intercept=True. #15086 by Alex Gramfort.

Fix The liblinear solver now supports sample_weight. #15038 by Guillaume Lemaitre.

Feature manifold.Isomap, manifold.TSNE, and manifold.SpectralEmbedding now accept precomputed sparse neighbors graph as input. #10482 by Tom Dupre la Tour and Kumar Ashutosh.

Feature Exposed the n_jobs parameter in manifold.TSNE for multi-core calculation of the neighbors graph. This parameter has no impact when metric="precomputed" or (metric="euclidean" and method="exact"). #15082 by Roman Yurchak.

Efficiency Improved efficiency of manifold.TSNE when method="barnes-hut" by computing the gradient in parallel. #13213 by Thomas Moreau

Fix Fixed a bug where manifold.spectral_embedding (and therefore manifold.SpectralEmbedding and cluster.SpectralClustering) computed wrong eigenvalues with eigen_solver='amg' when n_samples < 5 * n_components. #14647 by Andreas Müller.

Fix Fixed a bug in manifold.spectral_embedding used in manifold.SpectralEmbedding and cluster.SpectralClustering where eigen_solver="amg" would sometimes result in a LinAlgError. #13393 by Andrew Knyazev #13707 by Scott White

API Change Deprecate training_data_ unused attribute in manifold.Isomap. #10482 by Tom Dupre la Tour.

Major Feature metrics.plot_roc_curve has been added to plot roc curves. This function introduces the visualization API described in the User Guide. #14357 by Thomas Fan.

Feature Added a new parameter zero_division to multiple classification metrics: precision_score, recall_score, f1_score, fbeta_score, precision_recall_fscore_support, classification_report. This allows to set returned value for ill-defined metrics. #14900 by Marc Torrellas Socastro.

Feature Added the metrics.pairwise.nan_euclidean_distances metric, which calculates euclidean distances in the presence of missing values. #12852 by Ashim Bhattarai and Thomas Fan.

Feature New ranking metrics metrics.ndcg_score and metrics.dcg_score have been added to compute Discounted Cumulative Gain and Normalized Discounted Cumulative Gain. #9951 by Jérôme Dockès.

Feature metrics.plot_precision_recall_curve has been added to plot precision recall curves. #14936 by Thomas Fan.

Feature metrics.plot_confusion_matrix has been added to plot confusion matrices. #15083 by Thomas Fan.

Feature Added multiclass support to metrics.roc_auc_score with corresponding scorers 'roc_auc_ovr', 'roc_auc_ovo', 'roc_auc_ovr_weighted', and 'roc_auc_ovo_weighted'. #12789 and #15274 by Kathy Chen, Mohamed Maskani, and Thomas Fan.

Feature Add metrics.mean_tweedie_deviance measuring the Tweedie deviance for a given power parameter. Also add mean Poisson deviance metrics.mean_poisson_deviance and mean Gamma deviance metrics.mean_gamma_deviance that are special cases of the Tweedie deviance for power=1 and power=2 respectively. #13938 by Christian Lorentzen and Roman Yurchak.

Efficiency Improved performance of metrics.pairwise.manhattan_distances in the case of sparse matrices. #15049 by Paolo Toccaceli <ptocca>.

Enhancement The parameter beta in metrics.fbeta_score is updated to accept the zero and float('+inf') value. #13231 by Dong-hee Na.

Enhancement Added parameter squared in metrics.mean_squared_error to return root mean squared error. #13467 by Urvang Patel.

Enhancement Allow computing averaged metrics in the case of no true positives. #14595 by Andreas Müller.

Enhancement Multilabel metrics now supports list of lists as input. #14865 Srivatsan Ramesh, Herilalaina Rakotoarison, Léonard Binet.

Enhancement metrics.median_absolute_error now supports multioutput parameter. #14732 by Agamemnon Krasoulis.

Enhancement ‘roc_auc_ovr_weighted’ and ‘roc_auc_ovo_weighted’ can now be used as the scoring parameter of model-selection tools. #14417 by Thomas Fan.

Enhancement metrics.confusion_matrix accepts a parameters normalize allowing to normalize the confusion matrix by column, rows, or overall. #15625 by Guillaume Lemaitre <glemaitre>.

Fix Raise a ValueError in metrics.silhouette_score when a precomputed distance matrix contains non-zero diagonal entries. #12258 by Stephen Tierney.

API Change scoring="neg_brier_score" should be used instead of scoring="brier_score_loss" which is now deprecated. #14898 by Stefan Matcovici.

Efficiency Improved performance of multimetric scoring in model_selection.cross_validate, model_selection.GridSearchCV, and model_selection.RandomizedSearchCV. #14593 by Thomas Fan.

Enhancement model_selection.learning_curve now accepts parameter return_times which can be used to retrieve computation times in order to plot model scalability (see learning_curve example). #13938 by Hadrien Reboul.

Enhancement model_selection.RandomizedSearchCV now accepts lists of parameter distributions. #14549 by Andreas Müller.

Fix Reimplemented model_selection.StratifiedKFold to fix an issue where one test set could be n_classes larger than another. Test sets should now be near-equally sized. #14704 by Joel Nothman.

Fix The cv_results_ attribute of model_selection.GridSearchCV and model_selection.RandomizedSearchCV now only contains unfitted estimators. This potentially saves a lot of memory since the state of the estimators isn’t stored. ##15096 by Andreas Müller.

API Change model_selection.KFold and model_selection.StratifiedKFold now raise a warning if random_state is set but shuffle is False. This will raise an error in 0.24.

Fix multioutput.MultiOutputClassifier now has attribute classes_. #14629 by Agamemnon Krasoulis.

Fix multioutput.MultiOutputClassifier now has predict_proba as property and can be checked with hasattr. #15488 #15490 by Rebekah Kim

Major Feature Added naive_bayes.CategoricalNB that implements the Categorical Naive Bayes classifier. #12569 by Tim Bicker and Florian Wilhelm.

Major Feature Added neighbors.KNeighborsTransformer and neighbors.RadiusNeighborsTransformer, which transform input dataset into a sparse neighbors graph. They give finer control on nearest neighbors computations and enable easy pipeline caching for multiple use. #10482 by Tom Dupre la Tour.

Feature neighbors.KNeighborsClassifier, neighbors.KNeighborsRegressor, neighbors.RadiusNeighborsClassifier, neighbors.RadiusNeighborsRegressor, and neighbors.LocalOutlierFactor now accept precomputed sparse neighbors graph as input. #10482 by Tom Dupre la Tour and Kumar Ashutosh.

Feature neighbors.RadiusNeighborsClassifier now supports predicting probabilities by using predict_proba and supports more outlier_label options: ‘most_frequent’, or different outlier_labels for multi-outputs. #9597 by Wenbo Zhao.

Efficiency Efficiency improvements for neighbors.RadiusNeighborsClassifier.predict. #9597 by Wenbo Zhao.

Fix neighbors.KNeighborsRegressor now throws error when metric='precomputed' and fit on non-square data. #14336 by Gregory Dexter.

Feature Add max_fun parameter in neural_network.BaseMultilayerPerceptron, neural_network.MLPRegressor, and neural_network.MLPClassifier to give control over maximum number of function evaluation to not meet tol improvement. #9274 by Daniel Perry.

Enhancement pipeline.Pipeline now supports score_samples if the final estimator does. #13806 by Anaël Beaugnon.

Fix The fit in FeatureUnion now accepts fit_params to pass to the underlying transformers. #15119 by Adrin Jalali.

API Change None as a transformer is now deprecated in pipeline.FeatureUnion. Please use 'drop' instead. #15053 by Thomas Fan.

Efficiency preprocessing.PolynomialFeatures is now faster when the input data is dense. #13290 by Xavier Dupré.

Enhancement Avoid unnecessary data copy when fitting preprocessors preprocessing.StandardScaler, preprocessing.MinMaxScaler, preprocessing.MaxAbsScaler, preprocessing.RobustScaler and preprocessing.QuantileTransformer which results in a slight performance improvement. #13987 by Roman Yurchak.

Fix KernelCenterer now throws error when fit on non-square preprocessing.KernelCenterer #14336 by Gregory Dexter.

Fix model_selection.GridSearchCV and model_selection.RandomizedSearchCV now supports the _pairwise property, which prevents an error during cross-validation for estimators with pairwise inputs (such as neighbors.KNeighborsClassifier when metric is set to ‘precomputed’). #13925 by Isaac S. Robson and #15524 by Xun Tang.

Enhancement svm.SVC and svm.NuSVC now accept a break_ties parameter. This parameter results in predict breaking the ties according to the confidence values of decision_function, if decision_function_shape='ovr', and the number of target classes > 2. #12557 by Adrin Jalali.

Enhancement SVM estimators now throw a more specific error when kernel='precomputed' and fit on non-square data. #14336 by Gregory Dexter.

Fix svm.SVC, svm.SVR, svm.NuSVR and svm.OneClassSVM when received values negative or zero for parameter sample_weight in method fit(), generated an invalid model. This behavior occurred only in some border scenarios. Now in these cases, fit() will fail with an Exception. #14286 by Alex Shacked.

Fix The n_support_ attribute of svm.SVR and svm.OneClassSVM was previously non-initialized, and had size 2. It has now size 1 with the correct value. #15099 by Nicolas Hug.

Fix fixed a bug in BaseLibSVM._sparse_fit where n_SV=0 raised a ZeroDivisionError. #14894 by Danna Naser.

Fix The liblinear solver now supports sample_weight. #15038 by Guillaume Lemaitre.

Feature Adds minimal cost complexity pruning, controlled by ccp_alpha, to tree.DecisionTreeClassifier, tree.DecisionTreeRegressor, tree.ExtraTreeClassifier, tree.ExtraTreeRegressor, ensemble.RandomForestClassifier, ensemble.RandomForestRegressor, ensemble.ExtraTreesClassifier, ensemble.ExtraTreesRegressor, ensemble.GradientBoostingClassifier, and ensemble.GradientBoostingRegressor. #12887 by Thomas Fan.

API Change presort is now deprecated in tree.DecisionTreeClassifier and tree.DecisionTreeRegressor, and the parameter has no effect. #14907 by Adrin Jalali.

API Change The classes_ and n_classes_ attributes of tree.DecisionTreeRegressor are now deprecated. #15028 by Mei Guan, Nicolas Hug, and Adrin Jalali.

Feature check_estimator can now generate checks by setting generate_only=True. Previously, running check_estimator will stop when the first check fails. With generate_only=True, all checks can run independently and report the ones that are failing. Read more in Rolling your own estimator. #14381 by Thomas Fan.

Feature Added a pytest specific decorator, parametrize_with_checks, to parametrize estimator checks for a list of estimators. #14381 by Thomas Fan.

Feature A new random variable, utils.fixes.loguniform implements a log-uniform random variable (e.g., for use in RandomizedSearchCV). For example, the outcomes 1, 10 and 100 are all equally likely for loguniform(1, 100). See #11232 by Scott Sievert and Nathaniel Saul, and SciPy PR 10815 <https://github.com/scipy/scipy/pull/10815>.

Enhancement utils.safe_indexing (now deprecated) accepts an axis parameter to index array-like across rows and columns. The column indexing can be done on NumPy array, SciPy sparse matrix, and Pandas DataFrame. An additional refactoring was done. #14035 and #14475 by Guillaume Lemaitre.

Enhancement utils.extmath.safe_sparse_dot works between 3D+ ndarray and sparse matrix. #14538 by Jérémie du Boisberranger.

Fix utils.check_array is now raising an error instead of casting NaN to integer. #14872 by Roman Yurchak.

Fix utils.check_array will now correctly detect numeric dtypes in pandas dataframes, fixing a bug where float32 was upcast to float64 unnecessarily. #15094 by Andreas Müller.

API Change The following utils have been deprecated and are now private:

• choose_check_classifiers_labels

• enforce_estimator_tags_y

• mocking.MockDataFrame

• mocking.CheckingClassifier

• optimize.newton_cg

• random.random_choice_csc

• utils.choose_check_classifiers_labels

• utils.enforce_estimator_tags_y

• utils.optimize.newton_cg

• utils.random.random_choice_csc

• utils.safe_indexing

• utils.mocking

• utils.fast_dict

• utils.seq_dataset

• utils.weight_vector

• utils.fixes.parallel_helper (removed)

• All of utils.testing except for all_estimators which is now in utils.

Fix Fixed a bug where isotonic.IsotonicRegression.fit raised error when X.dtype == 'float32' and X.dtype != y.dtype. #14902 by Lucas.

Fix Port lobpcg from SciPy which implement some bug fixes but only available in 1.3+. #13609 and #14971 by Guillaume Lemaitre.

API Change Scikit-learn now converts any input data structure implementing a duck array to a numpy array (using __array__) to ensure consistent behavior instead of relying on __array_function__ (see NEP 18). #14702 by Andreas Müller.

API Change Replace manual checks with check_is_fitted. Errors thrown when using a non-fitted estimators are now more uniform. #13013 by Agamemnon Krasoulis.