def test_super_transform_call(self, mocker):
"""Test the call to BaseMappingTransformer.transform."""
df = d.create_df_1()
mapping = {
"b": {
"a": 1.1,
"b": 1.2,
"c": 1.3,
"d": 1.4,
"e": 1.5,
"f": 1.6
}
}
x = CrossColumnAddTransformer(mappings=mapping, adjust_column="a")
expected_call_args = {0: {"args": (d.create_df_1(), ), "kwargs": {}}}
with h.assert_function_call(
mocker,
tubular.base.BaseTransformer,
"transform",
expected_call_args,
return_value=d.create_df_1(),
):
x.transform(df)
def test_super_transform_call(self, mocker):
"""Test the call to BaseTransformer.transform."""
df = d.create_df_1()
mapping = {
"a": {
1: "a",
2: "b",
3: "c",
4: "d",
5: "e",
6: "f"
},
"b": {
"a": 1,
"b": 2,
"c": 3,
"d": 4,
"e": 5,
"f": 6
},
}
x = BaseMappingTransformer(mappings=mapping)
expected_call_args = {0: {"args": (d.create_df_1(), ), "kwargs": {}}}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
def test_one_hot_encoder_fit_called(self, mocker):
"""Test that fit calls OneHotEncoder.fit."""
expected_keyword_args = {"X": d.create_df_1()[["b"]], "y": None}
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
mocker.patch("sklearn.preprocessing.OneHotEncoder.fit")
x.fit(df)
assert (
sklearn.preprocessing.OneHotEncoder.fit.call_count == 1
), f"Not enough calls to OneHotEncoder.fit -\n Expected: 1\n Actual: {sklearn.preprocessing.OneHotEncoder.fit.call_count}"
call_args = sklearn.preprocessing.OneHotEncoder.fit.call_args_list[0]
call_pos_args = call_args[0]
call_kwargs = call_args[1]
h.assert_equal_dispatch(
expected=expected_keyword_args,
actual=call_kwargs,
msg="kwargs for OneHotEncoder.fit in OneHotEncodingTransformer.init",
)
assert (
len(call_pos_args) == 1
), f"Unepxected number of positional args in OneHotEncoder.fit call -\n Expected: 1\n Actual: {len(call_pos_args)}"
assert (
call_pos_args[0] is x
), f"Unexpected positional arg (self) in OneHotEncoder.fit call -\n Expected: self\n Actual: {call_pos_args[0]}"
def test_base_nominal_transformer_fit_called(self, mocker):
"""Test that fit calls BaseNominalTransformer.fit."""
expected_keyword_args = {"X": d.create_df_1(), "y": None}
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
mocker.patch("tubular.nominal.BaseNominalTransformer.fit")
x.fit(df)
assert (
tubular.nominal.BaseNominalTransformer.fit.call_count == 1
), f"Not enough calls to BaseNominalTransformer.fit -\n Expected: 1\n Actual: {tubular.nominal.BaseNominalTransformer.fit.call_count}"
call_args = tubular.nominal.BaseNominalTransformer.fit.call_args_list[0]
call_pos_args = call_args[0]
call_kwargs = call_args[1]
h.assert_equal_dispatch(
expected=expected_keyword_args,
actual=call_kwargs,
msg="kwargs for BaseNominalTransformer.fit in OneHotEncodingTransformer.init",
)
assert (
len(call_pos_args) == 1
), f"Unepxected number of positional args in BaseNominalTransformer.fit call -\n Expected: 1\n Actual: {len(call_pos_args)}"
assert (
call_pos_args[0] is x
), f"Unexpected positional arg (self) in BaseNominalTransformer.fit call -\n Expected: self\n Actual: {call_pos_args[0]}"
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_df_1()
x = NullIndicator(columns="a")
expected_call_args = {0: {"args": (d.create_df_1(), ), "kwargs": {}}}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
def test_fit_not_changing_data(self):
"""Test fit does not change X."""
df = d.create_df_1()
x = ModeImputer(columns="a")
x.fit(df)
h.assert_equal_dispatch(
expected=d.create_df_1(),
actual=df,
msg="Check X not changing during fit",
)
def test_fit_not_changing_data(self):
"""Test fit does not change X."""
df = d.create_df_1()
x = NominalToIntegerTransformer(columns=["a", "b"])
x.fit(df)
h.assert_equal_dispatch(
expected=d.create_df_1(),
actual=df,
msg="Check X not changing during fit",
)
def test_fit_not_changing_data(self):
"""Test fit does not change X."""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
x.fit(df)
h.assert_equal_dispatch(
expected=d.create_df_1(),
actual=df,
msg="Check X not changing during fit",
)
def test_mappings_unchanged(self):
"""Test that mappings is unchanged in transform."""
df = d.create_df_1()
mapping = {
"a": {
1: "a",
2: "b",
3: "c",
4: "d",
5: "e",
6: "f"
},
"b": {
"a": 1,
"b": 2,
"c": 3,
"d": 4,
"e": 5,
"f": 6
},
}
x = BaseMappingTransformer(mappings=mapping)
x.transform(df)
h.assert_equal_dispatch(
expected=mapping,
actual=x.mappings,
msg=
"BaseMappingTransformer.transform has changed self.mappings unexpectedly",
)
def test_check_is_fitted_call(self, mocker):
"""Test the call to check_is_fitted."""
df = d.create_df_1()
mapping = {
"a": {
1: "a",
2: "b",
3: "c",
4: "d",
5: "e",
6: "f"
},
"b": {
"a": 1,
"b": 2,
"c": 3,
"d": 4,
"e": 5,
"f": 6
},
}
x = BaseMappingTransformMixin()
x.columns = ["a", "b"]
x.mappings = mapping
expected_call_args = {0: {"args": (["mappings"], ), "kwargs": {}}}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"check_is_fitted", expected_call_args):
x.transform(df)
def test_categories_not_modified(self):
"""Test that the categories from fit are not changed in transform."""
df_train = d.create_df_1()
df_test = d.create_df_7()
x = OneHotEncodingTransformer(columns=["a", "b"], verbose=False)
x2 = OneHotEncodingTransformer(columns=["a", "b"], verbose=False)
x.fit(df_train)
x2.fit(df_train)
x.transform(df_test)
h.assert_equal_dispatch(
expected=list(x2.categories_[0]),
actual=list(x.categories_[0]),
msg="categories_ (index 0) modified during transform",
)
h.assert_equal_dispatch(
expected=list(x2.categories_[1]),
actual=list(x.categories_[1]),
msg="categories_ (index 1) modified during transform",
)
def test_exception_raised(self):
"""Test an exception is raised if non-mappable rows are present in X."""
df = d.create_df_1()
x = BaseNominalTransformer()
x.columns = ["a", "b"]
x.mappings = {
"a": {
1: 2,
2: 3,
3: 4,
4: 5,
5: 6,
6: 7
},
"b": {
"a": 1,
"c": 2,
"d": 3,
"e": 4,
"f": 5
},
}
with pytest.raises(
ValueError,
match=
"nulls would be introduced into column b from levels not present in mapping",
):
x.check_mappable_rows(df)
def test_columns_check_call(self, mocker):
"""Test the first call to BaseTransformer columns_check."""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
x.fit(df)
expected_call_args = {0: {"args": (d.create_df_1(),), "kwargs": {}}}
with h.assert_function_call(
mocker, tubular.base.BaseTransformer, "columns_check", expected_call_args
):
x.transform(df)
def test_mappings_unchanged(self):
"""Test that mappings is unchanged in transform."""
df = d.create_df_1()
mapping = {
"b": {
"a": 1.1,
"b": 1.2,
"c": 1.3,
"d": 1.4,
"e": 1.5,
"f": 1.6
}
}
x = CrossColumnAddTransformer(mappings=mapping, adjust_column="a")
x.transform(df)
h.assert_equal_dispatch(
expected=mapping,
actual=x.mappings,
msg=
"CrossColumnAddTransformer.transform has changed self.mappings unexpectedly",
)
def test_columns_set_or_check_called(self, mocker):
"""Test that fit calls BaseNominalTransformer.columns_set_or_check."""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
expected_call_args = {0: {"args": (d.create_df_1(),), "kwargs": {}}}
with h.assert_function_call(
mocker,
tubular.nominal.BaseNominalTransformer,
"columns_set_or_check",
expected_call_args,
):
x.fit(df)
def test_base_nominal_transformer_transform_called(self, mocker):
"""Test that BaseNominalTransformer.transform called."""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
x.fit(df)
mocker.patch(
"tubular.nominal.BaseNominalTransformer.transform",
return_value=d.create_df_1(),
)
x.transform(df)
assert (
tubular.nominal.BaseNominalTransformer.transform.call_count == 1
), f"Not enough calls to BaseNominalTransformer.transform -\n Expected: 1\n Actual: {tubular.nominal.BaseNominalTransformer.transform.call_count}"
call_args = tubular.nominal.BaseNominalTransformer.transform.call_args_list[0]
call_pos_args = call_args[0]
call_kwargs = call_args[1]
h.assert_equal_dispatch(
expected={},
actual=call_kwargs,
msg="kwargs for BaseNominalTransformer.transform in OneHotEncodingTransformer.init",
)
expected_pos_args = (x, d.create_df_1())
assert (
len(call_pos_args) == 2
), f"Unepxected number of positional args in BaseNominalTransformer.transform call -\n Expected: 2\n Actual: {len(call_pos_args)}"
h.assert_frame_equal_msg(
expected=expected_pos_args[1],
actual=call_pos_args[1],
msg_tag="X positional arg in BaseNominalTransformer.transform call",
)
assert (
expected_pos_args[0] == call_pos_args[0]
), "self positional arg in BaseNominalTransformer.transform call"
def test_y_multi_col_df_error(self):
"""Test an error is raised if y is passed as a multi column pd.DataFrame."""
df = d.create_df_1()
x = BaseTransformer(columns="a")
with pytest.raises(ValueError):
x.fit(X=df, y=df)
def test_fit_returns_self(self):
"""Test fit returns self?"""
df = d.create_df_1()
x = ModeImputer(columns="a")
x_fitted = x.fit(df)
assert x_fitted is x, "Returned value from ModeImputer.fit not as expected."
def test_columns_not_in_X_error(self):
"""Test an error is raised if self.columns contains a value not in X."""
df = d.create_df_1()
x = BaseTransformer(columns=["a", "z"])
with pytest.raises(ValueError):
x.columns_check(X=df)
def test_non_pd_type_error(self):
"""Test an error is raised if y is not passed as a pd.DataFrame or pd.Series."""
df = d.create_df_1()
x = BaseTransformer(columns="a")
with pytest.raises(ValueError):
x.fit(X=df, y=[1, 2, 3, 4, 5, 6])
def test_super_transform_call(self, mocker):
"""Test the call to BaseMappingTransformer.transform."""
df = d.create_df_1()
mapping = {"a": {1: "aa", 2: "bb", 3: "cc", 4: "dd", 5: "ee", 6: "ff"}}
x = CrossColumnMappingTransformer(mappings=mapping, adjust_column="b")
expected_call_args = {0: {"args": (d.create_df_1(),), "kwargs": {}}}
with h.assert_function_call(
mocker,
tubular.mapping.BaseMappingTransformer,
"transform",
expected_call_args,
return_value=d.create_df_1(),
):
x.transform(df)
def test_successful_usage(mocker):
"""Test an example of successful run of h.assert_function_call_count."""
df = d.create_df_1()
x = tubular.base.BaseTransformer(columns="a")
with h.assert_function_call_count(mocker, tubular.base.BaseTransformer,
"columns_set_or_check", 1):
x.fit(X=df)
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_df_1()
x = NominalToIntegerTransformer(columns="a")
x.fit(df)
expected_call_args = {0: {"args": (d.create_df_1(), ), "kwargs": {}}}
with h.assert_function_call(
mocker,
tubular.base.BaseTransformer,
"transform",
expected_call_args,
return_value=d.create_df_1(),
):
x.transform(df)
def test_super_transform_call(self, mocker):
"""Test the call to BaseMappingTransformMixin.transform."""
df = d.create_df_1()
mapping = {
"a": {1: "a", 2: "b", 3: "c", 4: "d", 5: "e", 6: "f"},
"b": {"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6},
}
x = MappingTransformer(mappings=mapping)
spy = mocker.spy(tubular.mapping.BaseMappingTransformMixin, "transform")
x.transform(df)
assert (
spy.call_count == 1
), "unexpected number of calls to BaseMappingTransformMixin.transform"
call_args = spy.call_args_list[0]
call_pos_args = call_args[0]
call_kwargs = call_args[1]
expected_kwargs = {}
assert (
call_kwargs == expected_kwargs
), "unexpected kwargs in BaseMappingTransformMixin.transform call"
expected_pos_args = (x, d.create_df_1())
assert (
expected_pos_args[0] == call_pos_args[0]
), "unexpected 1st positional arg in BaseMappingTransformMixin.transform call"
h.assert_equal_dispatch(
expected_pos_args[1],
call_pos_args[1],
"unexpected 2ns positional arg in BaseMappingTransformMixin.transform call",
)
def test_columns_none_error(self):
"""Test an error is raised if self.columns is None."""
df = d.create_df_1()
x = BaseTransformer(columns=None)
assert x.columns is None, f"self.columns should be None but got {x.columns}"
with pytest.raises(ValueError):
x.columns_check(X=df)
def test_fit_returns_self(self):
"""Test fit returns self?"""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
x_fitted = x.fit(df)
assert (
x_fitted is x
), "Returned value from OneHotEncodingTransformer.fit not as expected."
def test_adjust_col_not_in_x_error(self):
"""Test that an exception is raised if the adjust_column is not present in the dataframe."""
df = d.create_df_1()
mapping = {"a": {1: "aa", 2: "bb", 3: "cc", 4: "dd", 5: "ee", 6: "ff"}}
x = CrossColumnMappingTransformer(mappings=mapping, adjust_column="c")
with pytest.raises(ValueError, match="variable c is not in X"):
x.transform(df)
def test_adjust_col_not_in_x_error(self):
"""Test that an exception is raised if the adjust_column is not present in the dataframe."""
df = d.create_df_1()
mapping = {"b": {"a": 1.1, "b": 1.2, "c": 1.3, "d": 1.4, "e": 1.5, "f": 1.6}}
x = CrossColumnMultiplyTransformer(mappings=mapping, adjust_column="c")
with pytest.raises(ValueError, match="variable c is not in X"):
x.transform(df)
def test_fit_returns_self(self):
"""Test fit returns self?"""
df = d.create_df_1()
x = NominalToIntegerTransformer(columns=["a", "b"])
x_fitted = x.fit(df)
assert (
x_fitted is x
), "Returned value from NominalToIntegerTransformer.fit not as expected."
def test_columns_str_error(self):
"""Test an error is raised if self.columns is not a list."""
df = d.create_df_1()
x = BaseTransformer(columns=None)
x.columns = "a"
with pytest.raises(ValueError):
x.columns_check(X=df)