def test_attributes_unchanged_from_transform(self):
"""Test that attributes are unchanged after transform is run."""
df = d.create_df_9()
x = CappingTransformer(quantiles={"a": [0.2, 1], "b": [0, 1]})
x.fit(df)
x2 = CappingTransformer(quantiles={"a": [0.2, 1], "b": [0, 1]})
x2.fit(df)
x2.transform(df)
assert (
x.capping_values == x2.capping_values
), "capping_values attribute modified in transform"
assert (
x._replacement_values == x2._replacement_values
), "_replacement_values attribute modified in transform"
assert (
x.weights_column == x2.weights_column
), "weights_column attribute modified in transform"
assert x.quantiles == x2.quantiles, "quantiles attribute modified in transform"
def test_check_is_fitted_call_count(self, mocker):
"""Test there are 2 calls to BaseTransformer check_is_fitted in transform."""
df = d.create_df_3()
x = CappingTransformer(capping_values={"a": [2, 5], "b": [-1, 8]})
with h.assert_function_call_count(
mocker, tubular.base.BaseTransformer, "check_is_fitted", 2
):
x.transform(df)
def test_non_numeric_column_error(self):
"""Test that transform will raise an error if a column to transform is not numeric."""
df = d.create_df_5()
x = CappingTransformer(capping_values={"a": [2, 5], "b": [-1, 8], "c": [-1, 8]})
with pytest.raises(
TypeError, match=r"The following columns are not numeric in X; \['b', 'c'\]"
):
x.transform(df)
def test_quantile_not_fit_error(self):
"""Test that transform will raise an error if quantiles are specified in init but fit is not run before calling transform."""
df = d.create_df_9()
x = CappingTransformer(quantiles={"a": [0.2, 1], "b": [0, 1]})
with pytest.raises(
ValueError,
match="capping_values attribute is an empty dict - perhaps the fit method has not been run yet",
):
x.transform(df)
def test_replacement_values_dict_not_set_error(self):
"""Test that transform will raise an error if _replacement_values is an empty dict."""
df = d.create_df_9()
x = CappingTransformer(quantiles={"a": [0.2, 1], "b": [0, 1]})
# manually set attribute to get past the capping_values attribute is an empty dict exception
x.capping_values = {"a": [1, 4]}
with pytest.raises(
ValueError,
match="_replacement_values attribute is an empty dict - perhaps the fit method has not been run yet",
):
x.transform(df)
def test_learnt_values_not_modified(self):
"""Test that the replacements from fit are not changed in transform."""
capping_values_dict = {"a": [2, 5], "b": [-1, 8]}
df = d.create_df_3()
x = CappingTransformer(capping_values_dict)
x.transform(df)
h.test_object_attributes(
obj=x,
expected_attributes={"capping_values": capping_values_dict},
msg="Attributes for CappingTransformer set in init",
)
def test_check_is_fitted_call_1(self, mocker):
"""Test the first call to BaseTransformer check_is_fitted in transform."""
df = d.create_df_3()
x = CappingTransformer(capping_values={"a": [2, 5], "b": [-1, 8]})
expected_call_args = {
0: {"args": (["capping_values"],), "kwargs": {}},
1: {"args": (["_replacement_values"],), "kwargs": {}},
}
with h.assert_function_call(
mocker, tubular.base.BaseTransformer, "check_is_fitted", expected_call_args
):
x.transform(df)
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_df_3()
x = CappingTransformer(capping_values={"a": [2, 5], "b": [-1, 8]})
expected_call_args = {0: {"args": (d.create_df_3(),), "kwargs": {}}}
with h.assert_function_call(
mocker,
tubular.base.BaseTransformer,
"transform",
expected_call_args,
return_value=d.create_df_3(),
):
x.transform(df)
def test_non_cap_column_left_untouched(self, df, expected):
"""Test that capping is applied only to specific columns, others remain the same."""
x = CappingTransformer(capping_values={"a": [2, 10]})
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag="Unexpected values in CappingTransformer.transform, with columns meant to not be transformed",
)
def test_expected_output_min_and_max_combinations(self, df, expected):
"""Test that capping is applied correctly in transform."""
x = CappingTransformer(
capping_values={"a": [2, 5], "b": [None, 7], "c": [0, None]}
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag="Unexpected values in CappingTransformer.transform",
)