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_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_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_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_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_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_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_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_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_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_label_encoder_only_dsel_allagree():
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(), k=2)
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
ds_test.neighbors = neighbors_ex1[0, :]
ds_test.distances = distances_ex1[0, :]
predictions = ds_test.predict(query)
assert np.array_equal(predictions, ['dog', 'dog'])
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_DFP_is_used():
query = np.atleast_2d([1, 0])
ds_test = DS(create_pool_classifiers(), DFP=True, safe_k=3)
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[0, :]
ds_test.distances = distances_ex1[0, :]
ds_test.classify_with_ds = MagicMock(return_value=0)
ds_test.predict(query)
assert np.array_equal(ds_test.DFP_mask, np.atleast_2d([1, 1, 0]))
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_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_predict_proba_DFP():
query = np.atleast_2d([1, 1])
ds_test = DS(create_pool_classifiers(), DFP=True, safe_k=3)
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
# change the state of the system
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, :]
ds_test.distances = distances_ex1[0, :]
ds_test.predict_proba_instance = MagicMock(return_value=np.atleast_2d([0.25, 0.75]))
ds_test.predict_proba(query)
assert np.array_equal(ds_test.DFP_mask, np.array([1, 1, 0]))
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_output_profiles_transform():
query = np.array([[1.0, 1.0]])
ds_test = DS(create_pool_classifiers())
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
profile = ds_test._output_profile_transform(query)
assert np.array_equal(profile, np.array([0.5, 0.5, 1.0, 0.0, 0.33, 0.67]))
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.ones((15, 6)) * np.array([0.5, 0.5, 1.0, 0.0, 0.33, 0.67])
assert np.array_equal(dsel_scores, expected)
def test_get_dsel_scores_all_samples():
ds_test = DS(create_pool_classifiers())
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
ds_test.dsel_scores = dsel_scores_ex1
expected = np.ones((15, 2)) * 0.5
assert np.array_equal(ds_test._get_scores_dsel(1), expected)
def test_get_dsel_scores_not_processed():
ds_test = DS(create_pool_classifiers())
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
with pytest.raises(NotFittedError):
ds_test._get_scores_dsel(0)
def test_bad_input_X(X):
ds_test = DS(create_pool_classifiers())
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
with pytest.raises(ValueError):
ds_test.predict(X)
def test_input_X_3D():
X = np.ones((10, 10, 10))
ds_test = DS(create_pool_classifiers())
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
with pytest.raises(ValueError):
ds_test.predict(X)
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_input_shape_fit():
X = X_dsel_ex1
y = np.ones(20)
ds_test = DS(create_pool_classifiers())
with pytest.raises(ValueError):
ds_test.fit(X, y)
