num_permutations: number of permutations for creating subsequences of *k* elements.num_combinations: combinations for creating subsequences of *k* elements.EyepadAlign: align face images based on eye location.extract_face_landmarks: extract 68 landmark features from face images.find_files: Find files based on substring matches.find_filegroups: Find files that only differ via their file extensions.SequentialFeatureSelector: The popular forward and backward feature selection approaches (including floating variants).ExhaustiveFeatureSelector: Optimal feature sets by considering all possible feature combinations.ColumnSelector: Scikit-learn utility function to select specific columns in a pipeline.PrincipalComponentAnalysis: Principal component analysis (PCA) for dimensionality reduction.LinearDiscriminantAnalysis: Linear discriminant analysis for dimensionality reduction.scoring: computing various performance metrics.RandomHoldoutSplit: split a dataset into a train and validation subset for validation.PredefinedHoldoutSplit: Utility for the holdout method compatible with scikit-learn.permutation_test: Permutation test for hypothesis testing.paired_ttest_resample: Resampled paired *t* test.paired_ttest_kfold_cv: K-fold cross-validated paired *t* test.paired_ttest_5x2cv: 5x2cv paired *t* test for classifier comparisons.mcnemar: McNemar's test for classifier comparisons.mcnemar_tables: contingency tables for McNemar's test and Cochran's Q test.mcnemar_table: Contingency table for McNemar's test.lift_score: Lift score for classification and association rule mining.
#Sequential search in javascript series#
GroupTimeSeriesSplit: A scikit-learn compatible version of the time series validation with groups.ftest: F-test for classifier comparisons.feature_importance_permutation: Estimate feature importance via feature permutation.create_counterfactual: Interpreting models via counterfactuals.confusion_matrix: creating a confusion matrix for model evaluation.combined_ftest_5x2cv: 5x2cv combined *F* test for classifier comparisons.cochrans_q: Cochran's Q test for comparing multiple classifiers.BootstrapOutOfBag: A scikit-learn compatible version of the out-of-bag bootstrap.bootstrap: The ordinary nonparametric boostrap for arbitrary parameters.bias_variance_decomp: Bias-variance decomposition for classification and regression losses.accuracy_score: Computing standard, balanced, and per-class accuracy.wine_data: A 3-class wine dataset for classification.three_blobs_data: The synthetic blobs for classification.mnist_data: A subset of the MNIST dataset for classification.
0 kommentar(er)
