def test_preprocess_dsel_scores(): ds_test = DS(create_pool_classifiers()) ds_test.fit(X_dsel_ex1, y_dsel_ex1) dsel_scores = ds_test._preprocess_dsel_scores() expected = np.array([[0.5, 0.5], [1.0, 0.0], [0.33, 0.67]]) expected = np.tile(expected, (15, 1, 1)) assert np.array_equal(dsel_scores, expected)
def test_all_classifiers_agree(): # 10 classifiers that return 1 pool_classifiers = [create_base_classifier(return_value=1)] * 10 ds = DS(pool_classifiers) x = np.ones((1, 10)) assert ds._all_classifier_agree(x)
def test_not_all_classifiers_agree(): # 10 classifiers that return 1, and one that returns 2 pool_classifiers = [create_base_classifier(return_value=1)] * 10 pool_classifiers.append(create_base_classifier(return_value=2)) ds = DS(pool_classifiers) x = np.ones((1, 10)) assert not ds._all_classifier_agree(x)
def test_instance_hardness_region_all_same(): X = X_dsel_ex1 y = y_dsel_ex1 ds_test = DS(create_pool_classifiers()) ds_test.fit(X, y) neighbors = [0, 1, 2, 6, 7, 8, 13] IH = ds_test._hardness_region_competence(neighbors) assert IH == 0.0
def test_instance_hardness_region(index, expected): X = X_dsel_ex1 y = y_dsel_ex1 ds_test = DS(create_pool_classifiers()) ds_test.fit(X, y) neighbors = neighbors_ex1[index, :] IH = ds_test._hardness_region_competence(neighbors) assert np.isclose(IH, expected, atol=0.01)
def test_IH_is_used(index, expected): query = np.atleast_2d([1, 0]) ds_test = DS(create_pool_classifiers(), with_IH=True, IH_rate=0.5) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.processed_dsel = dsel_processed_ex1 ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 ds_test.neighbors = neighbors_ex1[index, :] ds_test.distances = distances_ex1[index, :] predicted = ds_test.predict(query) assert predicted == expected
def test_IH_is_used(): expected = [0, 0, 1] query = np.ones((3, 2)) ds_test = DS(create_pool_classifiers(), with_IH=True, IH_rate=0.5) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.processed_dsel = dsel_processed_ex1 ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 ds_test.neighbors = neighbors_ex1 ds_test.distances = distances_ex1 predicted = ds_test.predict(query) assert np.array_equal(predicted, expected)
def test_label_encoder_base(): from sklearn.linear_model import LogisticRegression X_dsel_ex1 = np.array([[-1, 1], [-0.75, 0.5], [-1.5, 1.5]]) y_dsel_ex1 = np.array(['cat', 'dog', 'plane']) x = [[-2, -2], [2, 2]] y = ['cat', 'dog'] pool_classifiers = [LogisticRegression().fit(x, y) for _ in range(2)] query = np.atleast_2d([[1, 0], [-1, -1]]) ds_test = DS(pool_classifiers, k=2) ds_test.fit(X_dsel_ex1, y_dsel_ex1) predictions = ds_test.predict(query) assert np.equal(predictions, ['cat', 'dog'])
def test_get_dsel_scores(): ds_test = DS(create_pool_classifiers()) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.dsel_scores = dsel_scores_ex1 assert np.array_equal(ds_test._get_scores_dsel(0, 0), np.array([1.0, 0.0])) assert np.array_equal(ds_test._get_scores_dsel(1, 0), np.array([0.5, 0.5])) assert np.array_equal(ds_test._get_scores_dsel(2, 0), np.array([0.8, 0.2]))
def test_predict_proba_exists(): query = np.array([[1.0, 1.0]]) X = X_dsel_ex1 y = y_dsel_ex1 clf1 = Perceptron() clf1.fit(X, y) with pytest.raises(ValueError): DS([clf1, clf1])
def test_predict_proba_instance_called(index): query = np.atleast_2d([1, 1]) ds_test = DS(create_pool_classifiers(), with_IH=True, IH_rate=0.10) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.neighbors = neighbors_ex1[index, :] ds_test.distances = distances_ex1[index, :] ds_test.predict_proba_instance = MagicMock(return_value=np.atleast_2d([0.25, 0.75])) proba = ds_test.predict_proba(query) assert np.isclose(proba, np.atleast_2d([0.25, 0.75])).all()
def test_frienemy_all_classifiers_crosses(index): ds_test = DS(create_pool_classifiers()) ds_test.processed_dsel = dsel_processed_all_ones ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 ds_test.neighbors = neighbors_ex1[index, :] result = ds_test._frienemy_pruning() assert result.all() == 1.0
def test_predict_proba_all_agree(): query = np.atleast_2d([1, 1]) ds_test = DS(create_pool_classifiers()) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.dsel_scores = dsel_scores_ex1 ds_test._all_classifier_agree = MagicMock(return_value=True) proba = ds_test.predict_proba(query) assert np.isclose(proba, np.atleast_2d([0.61, 0.39])).all()
def test_frienemy_safe_region(): ds_test = DS(create_pool_classifiers(), safe_k=3) ds_test.processed_dsel = dsel_processed_ex1 ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 ds_test.neighbors = np.array([0, 1, 2, 6, 7, 8, 14]) result = ds_test._frienemy_pruning() assert np.array_equal(result, np.array([[1, 1, 1]]))
def test_frienemy_not_all_classifiers_crosses(): ds_test = DS(create_pool_classifiers(), safe_k=3) ds_test.processed_dsel = dsel_processed_ex1 ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 ds_test.neighbors = neighbors_ex1[0, :] result = ds_test._frienemy_pruning() assert np.array_equal(result, np.array([[1, 1, 0]]))
def test_predict_proba_IH_knn(index): query = np.atleast_2d([1, 1]) ds_test = DS(create_pool_classifiers(), with_IH=True, IH_rate=0.5) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.dsel_scores = dsel_scores_ex1 ds_test.neighbors = neighbors_ex1[index, :] ds_test.distances = distances_ex1[index, :] ds_test.roc_algorithm.predict_proba = MagicMock(return_value=np.atleast_2d([0.45, 0.55])) proba = ds_test.predict_proba(query) assert np.isclose(proba, np.atleast_2d([0.45, 0.55])).all()
def test_label_encoder_only_dsel(): X_dsel_ex1 = np.array([[-1, 1], [-0.75, 0.5], [-1.5, 1.5]]) y_dsel_ex1 = np.array(['cat', 'dog', 'plane']) query = np.atleast_2d([[1, 0], [-1, -1]]) ds_test = DS(create_pool_classifiers_dog_cat_plane(), k=2) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.neighbors = neighbors_ex1[0, :] ds_test.distances = distances_ex1[0, :] ds_test.classify_instance = Mock() ds_test.classify_instance.side_effect = [1, 0] predictions = ds_test.predict(query) assert np.array_equal(predictions, ['dog', 'cat'])
def test_frienemy_not_all_classifiers_crosses_batch(): expected = np.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]]) ds_test = DS(create_pool_classifiers(), safe_k=3) ds_test.processed_dsel = dsel_processed_ex1 ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 # passing three samples to compute the DFP at the same time ds_test.neighbors = neighbors_ex1 result = ds_test._frienemy_pruning() assert np.array_equal(result, expected)
def test_input_X_1D(): X = np.ones(10) ds_test = DS(create_pool_classifiers()) ds_test.fit(X_dsel_ex1, y_dsel_ex1) with pytest.raises(Warning): ds_test.predict(X)
def test_frienemy_no_classifier_crosses(): X = X_dsel_ex1 y = y_dsel_ex1 ds_test = DS(create_pool_classifiers()) ds_test.fit(X, y) ds_test.neighbors = neighbors_ex1[0, :] mask = ds_test._frienemy_pruning() assert mask.size == 3 and mask.all() == 1
def test_label_encoder_only_dsel(): X_dsel_ex1 = np.array([[-1, 1], [-0.75, 0.5], [-1.5, 1.5]]) y_dsel_ex1 = np.array(['cat', 'dog', 'plane']) query = np.atleast_2d([[1, 0], [-1, -1]]) ds_test = DS(create_pool_classifiers_dog_cat_plane(), k=2) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.neighbors = neighbors_ex1[0, :] ds_test.distances = distances_ex1[0, :] ds_test.classify_with_ds = Mock() ds_test.classify_with_ds.return_value = [ 1, 0 ] # changed here due to batch processing predictions = ds_test.predict(query) assert np.array_equal(predictions, ['dog', 'cat'])
def test_frienemy_no_classifier_crosses(): X = X_dsel_ex1 y = y_dsel_ex1 ds_test = DS(create_pool_classifiers()) ds_test.fit(X, y) ds_test.neighbors = neighbors_ex1[0, :] mask = ds_test._frienemy_pruning() assert mask.shape == (1, 3) and np.allclose(mask, 1)
def test_frienemy_safe_region_batch(): n_samples = 10 n_classifiers = 3 expected = np.ones((n_samples, n_classifiers)) ds_test = DS(create_pool_classifiers(), safe_k=3) ds_test.processed_dsel = dsel_processed_ex1 ds_test.DSEL_target = y_dsel_ex1 ds_test.DSEL_data = X_dsel_ex1 ds_test.neighbors = np.tile(np.array([0, 1, 2, 6, 7, 8, 14]), (n_samples, 1)) result = ds_test._frienemy_pruning() assert np.array_equal(result, expected)
def test_predict_proba_all_agree(): query = np.atleast_2d([1, 1]) ds_test = DS(create_pool_classifiers()) ds_test.fit(X_dsel_ex1, y_dsel_ex1) ds_test.dsel_scores = dsel_scores_ex1 backup_all_agree = DS._all_classifier_agree DS._all_classifier_agree = MagicMock(return_value=np.array([True])) proba = ds_test.predict_proba(query) DS._all_classifier_agree = backup_all_agree assert np.allclose(proba, np.atleast_2d([0.61, 0.39]))
def test_not_fitted_ds(): query = np.array([[1.0, 1.0]]) ds_test = DS(create_pool_classifiers()) with pytest.raises(NotFittedError): ds_test.predict(query)
def test_all_classifiers_agree(): # 10 classifiers that return 1 predictions = np.ones((1, 10)) assert np.all(DS._all_classifier_agree(predictions))
def test_empty_pool(): pool_classifiers = [] with pytest.raises(ValueError): DS(pool_classifiers)
def test_different_input_shape(): query = np.array([[1.0, 1.0, 2.0]]) ds_test = DS(create_pool_classifiers()) ds_test.fit(X_dsel_ex1, y_dsel_ex1) with pytest.raises(ValueError): ds_test.predict(query)
def test_valid_safe_k(k, safe_k): with pytest.raises(ValueError): DS([create_base_classifier(1)], k=k, safe_k=safe_k)
def test_check_safe_k_value(safe_k): pool_classifiers = create_pool_classifiers() with pytest.raises(ValueError): DS(pool_classifiers, safe_k=safe_k)