def test_sparse_regression(): """Check regression for various parameter settings on sparse input.""" rng = check_random_state(0) X_train, X_test, y_train, y_test = train_test_split(boston.data[:50], boston.target[:50], random_state=rng) class CustomSVR(SVR): """SVC variant that records the nature of the training set""" def fit(self, X, y): super(CustomSVR, self).fit(X, y) self.data_type_ = type(X) return self parameter_sets = [ {"max_samples": 0.5, "max_features": 2, "bootstrap": True, "bootstrap_features": True}, {"max_samples": 1.0, "max_features": 4, "bootstrap": True, "bootstrap_features": True}, {"max_features": 2, "bootstrap": False, "bootstrap_features": True}, {"max_samples": 0.5, "bootstrap": True, "bootstrap_features": False}, ] for sparse_format in [csc_matrix, csr_matrix]: X_train_sparse = sparse_format(X_train) X_test_sparse = sparse_format(X_test) for params in parameter_sets: # Trained on sparse format sparse_classifier = LazyBaggingRegressor( base_estimator=CustomSVR(), random_state=1, **params ).fit(X_train_sparse, y_train) sparse_results = sparse_classifier.predict(X_test_sparse) # Trained on dense format dense_results = LazyBaggingRegressor( base_estimator=CustomSVR(), random_state=1, **params ).fit(X_train, y_train).predict(X_test) sparse_type = type(X_train_sparse) types = [i.data_type_ for i in sparse_classifier.estimators_] assert_array_equal(sparse_results, dense_results) assert all([t == sparse_type for t in types]) assert_array_equal(sparse_results, dense_results)
def test_single_estimator(): """Check singleton ensembles.""" rng = check_random_state(0) X_train, X_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=rng) clf1 = LazyBaggingRegressor(base_estimator=KNeighborsRegressor(), n_estimators=1, bootstrap=False, bootstrap_features=False, random_state=rng).fit(X_train, y_train) clf2 = KNeighborsRegressor().fit(X_train, y_train) assert_array_equal(clf1.predict(X_test), clf2.predict(X_test))