def test_input_shape_fit():
X = np.ones((15, 2))
y = np.ones(20)
ds_test = BaseDS()
with pytest.raises(ValueError):
ds_test.fit(X, y)
def test_all_classifiers_agree():
# 10 classifiers that return 1
predictions = np.ones((1, 10))
assert np.all(BaseDS._all_classifier_agree(predictions))
def test_not_fitted_ds():
query = np.array([[1.0, 1.0]])
ds_test = BaseDS()
with pytest.raises(NotFittedError):
ds_test.predict(query)
def test_valid_selection_mode(knn_method):
with pytest.raises(ValueError):
ds = BaseDS(create_pool_classifiers(), knn_classifier=knn_method)
ds.fit(X_dsel_ex1, y_dsel_ex1)
def test_string_selection_mode(create_X_y):
X, y = create_X_y
ds = BaseDS(knn_classifier="knn")
ds.fit(X, y)
assert (isinstance(ds.roc_algorithm_, KNeighborsClassifier))
def test_check_safe_k_value(safe_k):
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
ds_test = BaseDS(safe_k=safe_k)
ds_test.fit(X, y)
def test_valid_safe_k(k, safe_k):
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
ds = BaseDS([create_base_classifier(1)], k=k, safe_k=safe_k)
ds.fit(X, y)
def test_input_shape_fit():
X = X_dsel_ex1
y = np.ones(20)
ds_test = BaseDS(create_pool_classifiers())
with pytest.raises(ValueError):
ds_test.fit(X, y)
def test_bad_input_X(X):
ds_test = BaseDS(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 = BaseDS(create_pool_classifiers())
ds_test.fit(X_dsel_ex1, y_dsel_ex1)
with pytest.raises(ValueError):
ds_test.predict(query)
def test_not_fitted_ds():
query = np.array([[1.0, 1.0]])
ds_test = BaseDS(create_pool_classifiers())
with pytest.raises(NotFittedError):
ds_test.predict(query)
def test_string_selection_mode():
ds = BaseDS(create_pool_classifiers(), knn_classifier="knn")
ds.fit(X_dsel_ex1, y_dsel_ex1)
assert(isinstance(ds.roc_algorithm_, KNeighborsClassifier))
def test_valid_selection_mode(knn_method, create_X_y):
X, y = create_X_y
with pytest.raises(ValueError):
ds = BaseDS(knn_classifier=knn_method)
ds.fit(X, y)
def test_valid_safe_k(k, safe_k):
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises(ValueError):
ds = BaseDS(k=k, safe_k=safe_k)
ds.fit(X, y)
def test_not_all_classifiers_agree():
# 10 classifiers that return 1, and one that returns 2
predictions = np.ones((10, 11))
predictions[:, -1] = 2
assert not np.all(BaseDS._all_classifier_agree(predictions))
def test_input_IH_rate(IH_rate):
X = np.random.rand(10, 2)
y = np.ones(10)
with pytest.raises((ValueError, TypeError)):
ds = BaseDS(create_pool_classifiers(), with_IH=True, IH_rate=IH_rate)
ds.fit(X, y)
def test_bad_input_X(X_test, create_X_y):
X_train, y_train = create_X_y
ds_test = BaseDS()
ds_test.fit(X_train, y_train)
with pytest.raises(ValueError):
ds_test.predict(X_test)
def test_pool_single_model(create_X_y):
X, y = create_X_y
pool = [create_base_classifier(return_value=0, return_prob=[0.9, 0.1])]
ds_tst = BaseDS(pool_classifiers=pool)
with pytest.raises(ValueError):
ds_tst.fit(X, y)
