def test_estimate_competence_ratio_batch():
n_samples = 10
query = np.ones((n_samples, 2))
x = np.array([0, 1, 2, 3, 4, 5, 6]).reshape(-1, 1)
y = np.array([0, 0, 0, 0, 1, 1, 1])
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
target = DESKNN(pool_classifiers,
k=7,
pct_accuracy=1,
pct_diversity=1,
metric='ratio')
target.fit(x, y)
neighbors = np.tile([0, 1, 2, 3, 4, 5, 6], (n_samples, 1))
competences, diversity = target.estimate_competence(query, neighbors)
assert np.allclose(competences, [2. / 7, 4. / 7, 5. / 7])
assert np.allclose(diversity, [2.166, 3.666, 4.500], atol=0.01)
def test_select_batch():
"""
Test case: 10 base classifiers; select 5 based on accuracy,
then the 3 most diverse.
accuracies (/10): 4 6 1 2 9 8 7 9 3 2
(should select indices_ 1, 4, 5, 6, 7)
diversity: 0 8 0 0 1 6 7 2 0 0
(should select indices_ 1, 5, 6 as most diverse)
"""
n_samples = 10
pool_classifiers = [create_base_classifier(1) for _ in range(10)]
accuracies = np.tile([4, 6, 1, 2, 9, 8, 7, 9, 3, 2], (n_samples, 1)) / 10.
diversity = np.tile([0, 8, 0, 0, 1, 6, 7, 2, 0, 0], (n_samples, 1))
target = DESKNN(pool_classifiers,
k=7,
pct_accuracy=5. / 10,
pct_diversity=3. / 10)
target.N_ = 5
target.J_ = 3
selected_classifiers = target.select(accuracies, diversity)
expected = np.tile([1, 5, 6], (n_samples, 1))
assert np.array_equal(np.unique(selected_classifiers), np.unique(expected))
def test_estimate_competence():
"""
Test case:
Correct labels: 0000111
classifier 1: 1010000 (2/7 correct)
classifier 2: 1000100 (4/7 correct)
classifier 2: 0010110 (5/7 correct)
Diversity: compute number of common errors (on both classifiers) and divide by 7:
clf1 x clf2: 3/7
clf1 x clf3: 2/7
clf2 x clf3: 1/7
clf1 diversity = (3+2)/7 = -5/7 (negative because we use the negative of double error)
clf2 diversity = (3+1)/7 = -4/7
clf3 diversity = (2+1)/7 = -3/7
"""
query = np.ones((1, 2))
x = np.array([0, 1, 2, 3, 4, 5, 6]).reshape(-1, 1)
y = np.array([0, 0, 0, 0, 1, 1, 1])
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
target = DESKNN(pool_classifiers, k=7, pct_accuracy=1, pct_diversity=1)
target.fit(x, y)
neighbors = np.array([[0, 1, 2, 3, 4, 5, 6]])
competences, diversity = target.estimate_competence(query, neighbors)
assert np.allclose(competences, [2. / 7, 4. / 7, 5. / 7])
assert np.allclose(diversity, [-5. / 7, -4. / 7, -3. / 7])
def test_classify_instance():
query = np.atleast_2d([1, -1])
des_knn_test = DESKNN(create_pool_classifiers() * 4, k=2)
des_knn_test.select = MagicMock(return_value=[0, 1, 2, 3, 5, 6, 7, 9])
predicted = des_knn_test.classify_instance(query)
assert predicted == 0
def test_select_less_diverse():
"""
Test case: 10 base classifiers; select 5 based on accuracy,
then the 3 less diverse
accuracies (/10): 4 6 1 2 9 8 7 9 3 2
(should select indices_ 1, 4, 5, 6, 7)
diversity: 0 8 0 0 1 6 7 2 0 0
(should select indices_ 4, 5, 7 as most diverse)
"""
pool_classifiers = [create_base_classifier(1) for _ in range(10)]
accuracies = np.array([[4, 6, 1, 2, 9, 8, 7, 9, 3, 2]]) / 10.
diversity = np.array([[0, 8, 0, 0, 1, 6, 7, 2, 0, 0]])
target = DESKNN(pool_classifiers,
k=7,
pct_accuracy=5. / 10,
pct_diversity=3. / 10,
more_diverse=False)
target.N_ = 5
target.J_ = 3
selected_classifiers = target.select(accuracies, diversity)
expected = np.array([[4, 5, 7]])
assert np.array_equal(np.unique(selected_classifiers), np.unique(expected))
def test_desknn_proba():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
desknn = DESKNN(pool_classifiers, DFP=True)
desknn.fit(X_dsel, y_dsel)
probas = desknn.predict_proba(X_test)
expected = np.load('deslib/tests/expected_values/desknn_probas_DFP.npy')
assert np.allclose(probas, expected)
def test_J_higher_than_N():
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
desknn = DESKNN([create_base_classifier(1)] * 100,
pct_accuracy=0.3,
pct_diversity=0.5)
desknn.fit(X, y)
def test_desknn_proba(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
desknn = DESKNN(pool_classifiers, knn_classifier=knn_methods)
desknn.fit(X_dsel, y_dsel)
probas = desknn.predict_proba(X_test)
expected = np.load(
'deslib/tests/expected_values/desknn_proba_integration.npy')
assert np.allclose(probas, expected)
def test_classify_instance():
query = np.atleast_2d([1, -1])
des_knn_test = DESKNN(create_pool_classifiers() * 4, k=2)
des_knn_test.select = MagicMock(return_value=[0, 1, 2, 3, 5, 6, 7, 9])
predictions = []
for clf in des_knn_test.pool_classifiers:
predictions.append(clf.predict(query)[0])
predicted = des_knn_test.classify_instance(query, predictions=np.array(predictions))
assert predicted == 0
def test_classify_with_ds_diff_sizes():
query = np.ones((10, 2))
predictions = np.ones((5, 3))
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
desknn_test = DESKNN(pool_classifiers)
with pytest.raises(ValueError):
desknn_test.classify_with_ds(query, predictions)
def test_classify_with_ds_single_sample():
query = np.ones(2)
predictions = np.array([0, 1, 0])
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
desknn_test = DESKNN(pool_classifiers)
desknn_test.estimate_competence = MagicMock(
return_value=(np.ones(3), np.ones(3)))
desknn_test.select = MagicMock(return_value=np.array([[0, 2]]))
result = desknn_test.classify_with_ds(query, predictions)
assert np.allclose(result, 0)
def test_soft_voting_no_proba(create_X_y):
from sklearn.linear_model import Perceptron
X, y = create_X_y
clf = Perceptron()
clf.fit(X, y)
with pytest.raises(ValueError):
DESKNN([clf, clf], voting='soft').fit(X, y)
def test_select():
"""
Test case: 10 base classifiers; select 5 based on accuracy, then the 3 most diverse
accuracies (/10): 4 6 1 2 9 8 7 9 3 2 (should select indices 1, 4, 5, 6, 7)
diversity: 0 8 0 0 1 6 7 2 0 0 (should select indices 1, 5, 6 as most diverse)
"""
pool_classifiers = [create_base_classifier(1) for _ in range(10)]
accuracies = np.array([4, 6, 1, 2, 9, 8, 7, 9, 3, 2]) / 10.
diversity = np.array([0, 8, 0, 0, 1, 6, 7, 2, 0, 0])
target = DESKNN(pool_classifiers, k=7, pct_accuracy=5./10, pct_diversity=3./10)
target.estimate_competence = lambda x: (accuracies, diversity)
selected_indices = target.select(2)
assert set(selected_indices) == {1, 5, 6}
def test_estimate_competence_Q():
query = np.ones((1, 2))
x = np.array([0, 1, 2, 3, 4, 5, 6]).reshape(-1, 1)
y = np.array([0, 0, 0, 0, 1, 1, 1])
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
target = DESKNN(pool_classifiers,
k=7,
pct_accuracy=1,
pct_diversity=1,
metric='Q')
target.fit(x, y)
target.DFP_mask = np.ones(target.n_classifiers)
target._get_region_competence = lambda x: (
None, np.array([[0, 1, 2, 3, 4, 5, 6]]))
competences, diversity = target.estimate_competence(query)
assert np.allclose(competences, [2. / 7, 4. / 7, 5. / 7])
assert np.allclose(diversity, [2, 1.2, 1.2])
def test_estimate_competence_Q():
x = np.array([0, 1, 2, 3, 4, 5, 6]).reshape(-1, 1)
y = np.array([0, 0, 0, 0, 1, 1, 1])
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
target = DESKNN(pool_classifiers, k=7, pct_accuracy=1, pct_diversity=1,
metric='Q')
target.fit(x, y)
neighbors = np.array([[0, 1, 2, 3, 4, 5, 6]])
competences, diversity = target.estimate_competence(neighbors)
assert np.allclose(competences, [2. / 7, 4. / 7, 5. / 7])
assert np.allclose(diversity, [2, 1.2, 1.2])
def test_estimate_competence_ratio():
x = np.array([0, 1, 2, 3, 4, 5, 6]).reshape(-1, 1)
y = np.array([0, 0, 0, 0, 1, 1, 1])
clf1 = create_base_classifier(np.array([1, 0, 1, 0, 0, 0, 0]))
clf2 = create_base_classifier(np.array([1, 0, 0, 0, 1, 0, 0]))
clf3 = create_base_classifier(np.array([0, 0, 1, 0, 1, 1, 0]))
pool_classifiers = [clf1, clf2, clf3]
target = DESKNN(pool_classifiers, k=7, pct_accuracy=1, pct_diversity=1, metric='Ratio')
target.fit(x, y)
target.DFP_mask = np.ones(target.n_classifiers)
target._get_region_competence = lambda x: (None, [0, 1, 2, 3, 4, 5, 6])
competences, diversity = target.estimate_competence(2)
assert np.allclose(competences, [2./7, 4./7, 5./7])
assert np.allclose(diversity, [2.166, 3.666, 4.500], atol=0.01)
def test_J_higher_than_N():
with pytest.raises(ValueError):
DESKNN([create_base_classifier(1)]*100, pct_accuracy=0.3, pct_diversity=0.5)
def test_desknn(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
desknn = DESKNN(pool_classifiers, knn_classifier=knn_methods)
desknn.fit(X_dsel, y_dsel)
assert np.isclose(desknn.score(X_test, y_test), 0.97340425531914898)
def test_input_diversity_parameter():
with pytest.raises(ValueError):
DESKNN([create_base_classifier(1)]*100, metric='abc')
def test_predict_proba():
X = np.random.randn(15, 5)
y = np.array([0, 1, 0, 0, 0] * 3)
clf1 = Perceptron()
clf1.fit(X, y)
DESKNN([clf1, clf1, clf1]).fit(X, y)
def test_pect_zero():
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
desknn = DESKNN(pct_accuracy=0.0, pct_diversity=0.0)
desknn.fit(X, y)
def test_J_higher_than_N():
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
desknn = DESKNN(pct_accuracy=0.3, pct_diversity=0.5)
desknn.fit(X, y)
def test_input_diversity_parameter():
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
desknn = DESKNN(metric='abc')
desknn.fit(X, y)
def test_desknn():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
desknn = DESKNN(pool_classifiers, DFP=True)
desknn.fit(X_dsel, y_dsel)
assert np.isclose(desknn.score(X_test, y_test), 0.89393939393939392)
def test_input_diversity_parameter():
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
desknn = DESKNN([create_base_classifier(1)] * 100, metric='abc')
desknn.fit(X, y)
def test_wrong_voting_value(voting, create_X_y, create_pool_classifiers):
X, y = create_X_y
pool = create_pool_classifiers
with pytest.raises(ValueError):
DESKNN(pool, voting=voting).fit(X, y)
def test_check_estimator():
check_estimator(DESKNN())
def test_J_N_values():
with pytest.raises(ValueError):
DESKNN([create_base_classifier(1)]*100, pct_accuracy=0.5, pct_diversity=0)
