def test_select_kbest_classif(): # Test whether the relative univariate feature selection # gets the correct items in a simple classification problem # with the k best heuristic X, y = make_classification(n_samples=200, n_features=20, n_informative=3, n_redundant=2, n_repeated=0, n_classes=8, n_clusters_per_class=1, flip_y=0.0, class_sep=10, shuffle=False, random_state=0) univariate_filter = SelectKBest(f_classif, k=5) X_r = univariate_filter.fit(X, y).transform(X) X_r2 = GenericUnivariateSelect(f_classif, mode='k_best', param=5).fit(X, y).transform(X) assert_array_equal(X_r, X_r2) support = univariate_filter.get_support() gtruth = np.zeros(20) gtruth[:5] = 1 assert_array_equal(support, gtruth)
def test_mutual_info_classif(): X, y = make_classification(n_samples=100, n_features=5, n_informative=1, n_redundant=1, n_repeated=0, n_classes=2, n_clusters_per_class=1, flip_y=0.0, class_sep=10, shuffle=False, random_state=0) # Test in KBest mode. univariate_filter = SelectKBest(mutual_info_classif, k=2) X_r = univariate_filter.fit(X, y).transform(X) X_r2 = GenericUnivariateSelect(mutual_info_classif, mode='k_best', param=2).fit(X, y).transform(X) assert_array_equal(X_r, X_r2) support = univariate_filter.get_support() gtruth = np.zeros(5) gtruth[:2] = 1 assert_array_equal(support, gtruth) # Test in Percentile mode. univariate_filter = SelectPercentile(mutual_info_classif, percentile=40) X_r = univariate_filter.fit(X, y).transform(X) X_r2 = GenericUnivariateSelect(mutual_info_classif, mode='percentile', param=40).fit(X, y).transform(X) assert_array_equal(X_r, X_r2) support = univariate_filter.get_support() gtruth = np.zeros(5) gtruth[:2] = 1 assert_array_equal(support, gtruth)
def test_select_heuristics_classif(): # Test whether the relative univariate feature selection # gets the correct items in a simple classification problem # with the fdr, fwe and fpr heuristics X, y = make_classification(n_samples=200, n_features=20, n_informative=3, n_redundant=2, n_repeated=0, n_classes=8, n_clusters_per_class=1, flip_y=0.0, class_sep=10, shuffle=False, random_state=0) univariate_filter = SelectFwe(f_classif, alpha=0.01) X_r = univariate_filter.fit(X, y).transform(X) gtruth = np.zeros(20) gtruth[:5] = 1 for mode in ['fdr', 'fpr', 'fwe']: X_r2 = GenericUnivariateSelect(f_classif, mode=mode, param=0.01).fit(X, y).transform(X) assert_array_equal(X_r, X_r2) support = univariate_filter.get_support() assert_array_almost_equal(support, gtruth)
def test_select_percentile_classif_sparse(): # Test whether the relative univariate feature selection # gets the correct items in a simple classification problem # with the percentile heuristic X, y = make_classification(n_samples=200, n_features=20, n_informative=3, n_redundant=2, n_repeated=0, n_classes=8, n_clusters_per_class=1, flip_y=0.0, class_sep=10, shuffle=False, random_state=0) X = sparse.csr_matrix(X) univariate_filter = SelectPercentile(f_classif, percentile=25) X_r = univariate_filter.fit(X, y).transform(X) X_r2 = GenericUnivariateSelect(f_classif, mode='percentile', param=25).fit(X, y).transform(X) assert_array_equal(X_r.toarray(), X_r2.toarray()) support = univariate_filter.get_support() gtruth = np.zeros(20) gtruth[:5] = 1 assert_array_equal(support, gtruth) X_r2inv = univariate_filter.inverse_transform(X_r2) assert sparse.issparse(X_r2inv) support_mask = safe_mask(X_r2inv, support) assert X_r2inv.shape == X.shape assert_array_equal(X_r2inv[:, support_mask].toarray(), X_r.toarray()) # Check other columns are empty assert X_r2inv.getnnz() == X_r.getnnz()
def test_select_kbest_all(): # Test whether k="all" correctly returns all features. X, y = make_classification(n_samples=20, n_features=10, shuffle=False, random_state=0) univariate_filter = SelectKBest(f_classif, k='all') X_r = univariate_filter.fit(X, y).transform(X) assert_array_equal(X, X_r)
def test_select_kbest_zero(): # Test whether k=0 correctly returns no features. X, y = make_classification(n_samples=20, n_features=10, shuffle=False, random_state=0) univariate_filter = SelectKBest(f_classif, k=0) univariate_filter.fit(X, y) support = univariate_filter.get_support() gtruth = np.zeros(10, dtype=bool) assert_array_equal(support, gtruth) X_selected = assert_warns_message(UserWarning, 'No features were selected', univariate_filter.transform, X) assert X_selected.shape == (20, 0)
def test_f_classif_multi_class(): # Test whether the F test yields meaningful results # on a simple simulated classification problem X, y = make_classification(n_samples=200, n_features=20, n_informative=3, n_redundant=2, n_repeated=0, n_classes=8, n_clusters_per_class=1, flip_y=0.0, class_sep=10, shuffle=False, random_state=0) F, pv = f_classif(X, y) assert (F > 0).all() assert (pv > 0).all() assert (pv < 1).all() assert (pv[:5] < 0.05).all() assert (pv[5:] > 1.e-4).all()
def test_f_classif_constant_feature(): # Test that f_classif warns if a feature is constant throughout. X, y = make_classification(n_samples=10, n_features=5) X[:, 0] = 2.0 assert_warns(UserWarning, f_classif, X, y)
Using a sub-pipeline, the fitted coefficients can be mapped back into the original feature space. """ from mrex import svm from mrex.datasets import samples_generator from mrex.feature_selection import SelectKBest, f_regression from mrex.pipeline import make_pipeline from mrex.model_selection import train_test_split from mrex.metrics import classification_report print(__doc__) # import some data to play with X, y = samples_generator.make_classification(n_features=20, n_informative=3, n_redundant=0, n_classes=4, n_clusters_per_class=2) X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42) # ANOVA SVM-C # 1) anova filter, take 3 best ranked features anova_filter = SelectKBest(f_regression, k=3) # 2) svm clf = svm.LinearSVC() anova_svm = make_pipeline(anova_filter, clf) anova_svm.fit(X_train, y_train) y_pred = anova_svm.predict(X_test) print(classification_report(y_test, y_pred))