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_prepare_quantiles_output_set_attributes(self, mocker, weights_column):
"""Test the output of prepare_quantiles is set to capping_values and_replacement_values attributes."""
df = d.create_df_9()
x = CappingTransformer(
quantiles={"a": [0.1, 1], "b": [0.5, None]}, weights_column=weights_column
)
mocked_return_values = [["aaaa", "bbbb"], [1234, None]]
mocker.patch(
"tubular.capping.CappingTransformer.prepare_quantiles",
side_effect=mocked_return_values,
)
x.fit(df)
h.test_object_attributes(
obj=x,
expected_attributes={
"capping_values": {
"a": mocked_return_values[0],
"b": mocked_return_values[1],
},
"_replacement_values": {
"a": mocked_return_values[0],
"b": mocked_return_values[1],
},
},
msg="weighted_quantile output set to capping_values, _replacement_values attributes",
)
def test_prepare_quantiles_call_weight(self, mocker):
"""Test the call to prepare_quantiles if weights_column is set."""
df = d.create_df_9()
x = CappingTransformer(
quantiles={"a": [0.1, 1], "b": [0.5, None]}, weights_column="c"
)
expected_call_args = {
0: {
"args": (d.create_df_9()["a"], [0.1, 1], d.create_df_9()["c"]),
"kwargs": {},
},
1: {
"args": (d.create_df_9()["b"], [0.5, None], d.create_df_9()["c"]),
"kwargs": {},
},
}
with h.assert_function_call(
mocker,
tubular.capping.CappingTransformer,
"prepare_quantiles",
expected_call_args,
):
x.fit(df)
def test_quantiles_none_error(self):
"""Test that an exception is raised if quantiles is None when fit is run."""
with pytest.warns(
UserWarning,
match="quantiles not set so no fitting done in CappingTransformer",
):
df = d.create_df_3()
x = CappingTransformer(capping_values={"a": [2, 5], "b": [-1, 8]})
x.fit(df)
def test_super_fit_call(self, mocker):
"""Test the call to BaseTransformer.fit."""
df = d.create_df_9()
x = CappingTransformer(
quantiles={"a": [0.1, 1], "b": [0.5, None]}, weights_column="c"
)
expected_call_args = {0: {"args": (d.create_df_9(), None), "kwargs": {}}}
with h.assert_function_call(
mocker, tubular.base.BaseTransformer, "fit", expected_call_args
):
x.fit(df)
def test_quantile_combinations_handled(self, quantiles, weights_column):
"""Test that a given combination of None and non-None quantile values can be calculated successfully."""
df = d.create_df_9()
x = CappingTransformer(
quantiles={"a": quantiles}, weights_column=weights_column
)
try:
x.fit(df)
except Exception as err:
pytest.fail(
f"unexpected exception when calling fit with quantiles {quantiles} - {err}"
)