def test_transformer_transform_output_type(X_y_binary):
X_np, y_np = X_y_binary
assert isinstance(X_np, np.ndarray)
assert isinstance(y_np, np.ndarray)
y_list = list(y_np)
X_df_no_col_names = pd.DataFrame(X_np)
range_index = pd.RangeIndex(start=0, stop=X_np.shape[1], step=1)
X_df_with_col_names = pd.DataFrame(X_np, columns=['x' + str(i) for i in range(X_np.shape[1])])
y_series_no_name = pd.Series(y_np)
y_series_with_name = pd.Series(y_np, name='target')
datatype_combos = [(X_np, y_np, range_index),
(X_np, y_list, range_index),
(X_df_no_col_names, y_series_no_name, range_index),
(X_df_with_col_names, y_series_with_name, X_df_with_col_names.columns)]
for component_class in _all_transformers():
print('Testing transformer {}'.format(component_class.name))
for X, y, X_cols_expected in datatype_combos:
print('Checking output of transform for transformer "{}" on X type {} cols {}, y type {} name {}'
.format(component_class.name, type(X),
X.columns if isinstance(X, pd.DataFrame) else None, type(y),
y.name if isinstance(y, pd.Series) else None))
component = component_class()
component.fit(X, y=y)
transform_output = component.transform(X, y=y)
assert isinstance(transform_output, ww.DataTable)
if isinstance(component, SelectColumns):
assert transform_output.shape == (X.shape[0], 0)
elif isinstance(component, PCA) or isinstance(component, LinearDiscriminantAnalysis):
assert transform_output.shape[0] == X.shape[0]
assert transform_output.shape[1] <= X.shape[1]
elif isinstance(component, DFSTransformer):
assert transform_output.shape[0] == X.shape[0]
assert transform_output.shape[1] >= X.shape[1]
elif isinstance(component, DelayedFeatureTransformer):
# We just want to check that DelayedFeaturesTransformer outputs a DataFrame
# The dataframe shape and index are checked in test_delayed_features_transformer.py
continue
else:
assert transform_output.shape == X.shape
assert (list(transform_output.columns) == list(X_cols_expected))
transform_output = component.fit_transform(X, y=y)
assert isinstance(transform_output, ww.DataTable)
if isinstance(component, SelectColumns):
assert transform_output.shape == (X.shape[0], 0)
elif isinstance(component, PCA) or isinstance(component, LinearDiscriminantAnalysis):
assert transform_output.shape[0] == X.shape[0]
assert transform_output.shape[1] <= X.shape[1]
elif isinstance(component, DFSTransformer):
assert transform_output.shape[0] == X.shape[0]
assert transform_output.shape[1] >= X.shape[1]
else:
assert transform_output.shape == X.shape
assert (list(transform_output.columns) == list(X_cols_expected))
def test_all_transformers_needs_fitting():
for component_class in _all_transformers() + _all_estimators():
if component_class.__name__ in [
'DropColumns', 'SelectColumns', 'DelayedFeatureTransformer'
]:
assert not component_class.needs_fitting
else:
assert component_class.needs_fitting
def test_all_transformers_check_fit_input_type(data_type, X_y_binary, make_data_type):
X, y = X_y_binary
X = make_data_type(data_type, X)
y = make_data_type(data_type, y)
for component_class in _all_transformers():
if not component_class.needs_fitting:
continue
component = component_class()
component.fit(X, y)
def test_all_transformers_check_fit(X_y_binary):
X, y = X_y_binary
for component_class in _all_transformers():
if not component_class.needs_fitting:
continue
component = component_class()
with pytest.raises(ComponentNotYetFittedError, match=f'You must fit {component_class.__name__}'):
component.transform(X, y)
component.fit(X, y)
component.transform(X, y)
component = component_class()
component.fit_transform(X, y)
component.transform(X, y)
MockComponent, MockEstimator, MockTransformer = test_classes
expected_code = "mockComponent = MockComponent(**{})"
component_code = generate_component_code(MockComponent())
assert component_code == expected_code
expected_code = "mockEstimator = MockEstimator(**{})"
component_code = generate_component_code(MockEstimator())
assert component_code == expected_code
expected_code = "mockTransformer = MockTransformer(**{})"
component_code = generate_component_code(MockTransformer())
assert component_code == expected_code
@pytest.mark.parametrize("transformer_class", _all_transformers())
@pytest.mark.parametrize("use_custom_index", [True, False])
def test_transformer_fit_and_transform_respect_custom_indices(use_custom_index, transformer_class, X_y_binary):
check_names = True
if transformer_class == DFSTransformer:
check_names = False
if use_custom_index:
pytest.skip("The DFSTransformer changes the index so we skip it.")
if transformer_class == PolynomialDetrender:
pytest.skip("Skipping PolynomialDetrender because we test that it respects custom indices in "
"test_polynomial_detrender.py")
X, y = X_y_binary
X = pd.DataFrame(X)