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_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_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_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_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_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_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_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_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)
