def test_desp_proba(knn_methods): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers, knn_classifier=knn_methods) desp.fit(X_dsel, y_dsel) probas = desp.predict_proba(X_test) expected = np.load( 'deslib/tests/expected_values/desp_proba_integration.npy') assert np.allclose(probas, expected)
def test_desp_proba(): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers, DFP=True) desp.fit(X_dsel, y_dsel) probas = desp.predict_proba(X_test) expected = np.load('deslib/tests/expected_values/desp_proba_DFP.npy') assert np.allclose(probas, expected)
def test_estimate_competence(index, expected): query = np.atleast_2d([1, 1]) des_p_test = DESP(create_pool_classifiers()) des_p_test.fit(X_dsel_ex1, y_dsel_ex1) des_p_test.DFP_mask = np.ones(des_p_test.n_classifiers) des_p_test.neighbors = neighbors_ex1[index, :] des_p_test.distances = distances_ex1[index, :] competences = des_p_test.estimate_competence(query) assert np.isclose(competences, expected, atol=0.01).all()
def test_estimate_competence_batch(): query = np.ones((3, 2)) expected = np.array([[0.57142857, 0.4285714, 0.57142857], [0.71428571, 0.2857142, 0.71428571], [0.2857142, 0.71428571, 0.2857142]]) des_p_test = DESP(create_pool_classifiers()) des_p_test.fit(X_dsel_ex1, y_dsel_ex1) neighbors = neighbors_ex1 distances = distances_ex1 competences = des_p_test.estimate_competence(query, neighbors, distances) assert np.allclose(competences, expected, atol=0.01)
def test_estimate_competence_batch(example_estimate_competence, create_pool_classifiers): X, y, neighbors, distances, dsel_processed, _ = example_estimate_competence expected = np.array([[0.57142857, 0.4285714, 0.57142857], [0.71428571, 0.2857142, 0.71428571], [0.2857142, 0.71428571, 0.2857142]]) des_p_test = DESP(create_pool_classifiers) des_p_test.fit(X, y) competences = des_p_test.estimate_competence(neighbors, distances) assert np.allclose(competences, expected, atol=0.01)
def test_select_two_classes(index, expected): query = np.atleast_2d([1, 1]) des_p_test = DESP(create_pool_classifiers()) des_p_test.fit(X_dsel_ex1, y_dsel_ex1) neighbors = neighbors_ex1[index, :].reshape(1, -1) distances = distances_ex1[index, :].reshape(1, -1) competences = des_p_test.estimate_competence(query, neighbors, distances) selected = des_p_test.select(competences) assert np.array_equal(selected, expected)
def test_select_two_classes(index, expected): query = np.atleast_2d([1, 1]) des_p_test = DESP(create_pool_classifiers()) des_p_test.fit(X_dsel_ex1, y_dsel_ex1) des_p_test.DFP_mask = np.ones(des_p_test.n_classifiers) des_p_test.neighbors = neighbors_ex1[index, :] des_p_test.distances = distances_ex1[index, :] competences = des_p_test.estimate_competence(query) selected = des_p_test.select(competences) assert selected == expected
def test_select_three_classes(index, expected): query = np.atleast_2d([1, 1]) des_p_test = DESP(create_pool_classifiers()) des_p_test.fit(X_dsel_ex1, y_dsel_ex1) des_p_test.n_classes = 3 des_p_test.neighbors = neighbors_ex1[index, :] des_p_test.distances = distances_ex1[index, :] competences = des_p_test.estimate_competence(query) selected = des_p_test.select(competences) assert np.array_equal(selected, expected)
def test_desp(): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers, DFP=True) desp.fit(X_dsel, y_dsel) assert np.isclose(desp.score(X_test, y_test), 0.896969696969697)
def test_desp(knn_methods): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers, knn_classifier=knn_methods) desp.fit(X_dsel, y_dsel) assert np.isclose(desp.score(X_test, y_test), 0.97340425531914898)
def test_desp(): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers, DFP=True, with_IH=True, IH_rate=0.1) desp.fit(X_dsel, y_dsel) assert np.isclose(desp.score(X_test, y_test), 0.906060606060606)
def test_desp(): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers) desp.fit(X_dsel, y_dsel) assert np.isclose(desp.score(X_test, y_test), 0.6954545454545454)
# can estimate probabilities pool_classifiers = RandomForestClassifier(n_estimators=10, max_depth=5) pool_classifiers.fit(X_train, y_train) # Initialize a DS technique. Here we specify the size of the region of competence (5 neighbors) knorau = KNORAU(pool_classifiers) kne = KNORAE(pool_classifiers, k=5) desp = DESP(pool_classifiers, k=5) ola = OLA(pool_classifiers, k=5) mcb = MCB(pool_classifiers, k=5) meta = METADES(pool_classifiers, k=5) # Fit the DS techniques knorau.fit(X_dsel, y_dsel) kne.fit(X_dsel, y_dsel) desp.fit(X_dsel, y_dsel) meta.fit(X_dsel, y_dsel) ola.fit(X_dsel, y_dsel) mcb.fit(X_dsel, y_dsel) # Calculate classification accuracy of each technique print('Classification accuracy RF: ', RF.score(X_test, y_test)) print('Evaluating DS techniques:') print('Classification accuracy KNORAU: ', knorau.score(X_test, y_test)) print('Classification accuracy KNORA-Eliminate: ', kne.score(X_test, y_test)) print('Classification accuracy DESP: ', desp.score(X_test, y_test)) print('Classification accuracy OLA: ', ola.score(X_test, y_test)) print('Classification accuracy MCB: ', mcb.score(X_test, y_test)) print('Classification accuracy META-DES: ', meta.score(X_test, y_test))
def test_desp(knne, expected): pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers() desp = DESP(pool_classifiers, DFP=True, knne=knne) desp.fit(X_dsel, y_dsel) assert np.isclose(desp.score(X_test, y_test), expected)
max_depth=10) pool_classifiers.fit(X_train, y_train) # DS techniques without DFP apriori = APriori(pool_classifiers) aposteriori = APosteriori(pool_classifiers) ola = OLA(pool_classifiers) lca = LCA(pool_classifiers) desp = DESP(pool_classifiers) meta = METADES(pool_classifiers) apriori.fit(X_dsel, y_dsel) aposteriori.fit(X_dsel, y_dsel) ola.fit(X_dsel, y_dsel) lca.fit(X_dsel, y_dsel) desp.fit(X_dsel, y_dsel) meta.fit(X_dsel, y_dsel) print('Evaluating DS techniques:') print('Classification accuracy of OLA: ', ola.score(X_test, y_test)) print('Classification accuracy of LCA: ', lca.score(X_test, y_test)) print('Classification accuracy of A priori: ', apriori.score(X_test, y_test)) print('Classification accuracy of A posteriori: ', aposteriori.score(X_test, y_test)) print('Classification accuracy of DES-P: ', desp.score(X_test, y_test)) print('Classification accuracy of META-DES: ', meta.score(X_test, y_test)) # Testing fire: fire_apriori = APriori(pool_classifiers, DFP=True) fire_aposteriori = APosteriori(pool_classifiers, DFP=True) fire_ola = OLA(pool_classifiers, DFP=True)
def main(): ############################################################################### # Preparing the dataset # --------------------- # In this part we load the breast cancer dataset from scikit-learn and # preprocess it in order to pass to the DS models. An important point here is # to normalize the data so that it has zero mean and unit variance, which is # a common requirement for many machine learning algorithms. # This step can be easily done using the StandardScaler class. rng = np.random.RandomState(123) data = load_breast_cancer() X = data.data y = data.target # split the data into training and test data X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=rng) # Scale the variables to have 0 mean and unit variance scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) # Split the data into training and DSEL for DS techniques X_train, X_dsel, y_train, y_dsel = train_test_split(X_train, y_train, test_size=0.5, random_state=rng) # Train a pool of 100 base classifiers pool_classifiers = BaggingClassifier(Perceptron(max_iter=10), n_estimators=100, random_state=rng) pool_classifiers.fit(X_train, y_train) # Initialize the DS techniques knorau = KNORAU(pool_classifiers) kne = KNORAE(pool_classifiers) desp = DESP(pool_classifiers) ola = OLA(pool_classifiers) mcb = MCB(pool_classifiers) ############################################################################### # Calibrating base classifiers # ----------------------------- # Some dynamic selection techniques requires that the base classifiers estimate # probabilities in order to estimate its competence level. Since the Perceptron # model is not a probabilistic classifier (does not implements the # predict_proba method, it needs to be calibrated for # probability estimation before being used by such DS techniques. This step can # be conducted using the CalibrateClassifierCV class from scikit-learn. Note # that in this example we pass a prefited pool of classifiers to the # calibration method in order to use exactly the same pool used in the other # DS methods. calibrated_pool = [] for clf in pool_classifiers: calibrated = CalibratedClassifierCV(base_estimator=clf, cv='prefit') calibrated.fit(X_dsel, y_dsel) calibrated_pool.append(calibrated) apriori = APriori(calibrated_pool) meta = METADES(calibrated_pool) knorau.fit(X_dsel, y_dsel) kne.fit(X_dsel, y_dsel) desp.fit(X_dsel, y_dsel) ola.fit(X_dsel, y_dsel) mcb.fit(X_dsel, y_dsel) apriori.fit(X_dsel, y_dsel) meta.fit(X_dsel, y_dsel) ############################################################################### # Evaluating the methods # ----------------------- # Let's now evaluate the methods on the test set. We also use the performance # of Bagging (pool of classifiers without any selection) as a baseline # comparison. We can see that the majority of DS methods achieve higher # classification accuracy. print('Evaluating DS techniques:') print('Classification accuracy KNORA-Union: ', knorau.score(X_test, y_test)) print('Classification accuracy KNORA-Eliminate: ', kne.score(X_test, y_test)) print('Classification accuracy DESP: ', desp.score(X_test, y_test)) print('Classification accuracy OLA: ', ola.score(X_test, y_test)) print('Classification accuracy A priori: ', apriori.score(X_test, y_test)) print('Classification accuracy MCB: ', mcb.score(X_test, y_test)) print('Classification accuracy META-DES: ', meta.score(X_test, y_test)) print('Classification accuracy Bagging: ', pool_classifiers.score(X_test, y_test))