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_super_fit_call(self, mocker):
"""Test the call to CappingTransformer.fit."""
spy = mocker.spy(tubular.capping.CappingTransformer, "fit")
df = d.create_df_9()
x = OutOfRangeNullTransformer(quantiles={
"a": [0.1, 1],
"b": [0.5, None]
},
weights_column="c")
x.fit(df)
assert (spy.call_count == 1
), "unexpected number of calls to CappingTransformer.fit"
call_args = spy.call_args_list[0]
call_pos_args = call_args[0]
call_kwargs = call_args[1]
assert call_pos_args == (
x, ), "unexpected positional args in CappingTransformer.fit call"
expected_kwargs = {"X": d.create_df_9(), "y": None}
h.assert_equal_dispatch(
expected=expected_kwargs,
actual=call_kwargs,
msg="unexpected kwargs in CappingTransformer.fit call",
)
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_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_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_one_hot_encoder_init_called(self, mocker):
"""Test that init calls OneHotEncoder.init.
Again not using h.assert_function_call for this as it does not handle self being passed to OneHotEncoder.init
"""
expected_keyword_args = {"sparse": False, "handle_unknown": "ignore"}
mocker.patch("sklearn.preprocessing.OneHotEncoder.__init__")
x = OneHotEncodingTransformer(
columns=None, verbose=True, copy=True, separator="x", drop_original=True
)
assert (
sklearn.preprocessing.OneHotEncoder.__init__.call_count == 1
), f"Not enough calls to OneHotEncoder.__init__ -\n Expected: 1\n Actual: {sklearn.preprocessing.OneHotEncoder.__init__.call_count}"
call_args = sklearn.preprocessing.OneHotEncoder.__init__.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.__init__ in OneHotEncodingTransformer.init",
)
assert (
len(call_pos_args) == 1
), f"Unepxected number of positional args in OneHotEncoder.__init__ call -\n Expected: 1\n Actual: {len(call_pos_args)}"
assert (
call_pos_args[0] is x
), f"Unexpected positional arg (self) in OneHotEncoder.__init__ call -\n Expected: self\n Actual: {call_pos_args[0]}"
def test_X_returned(self, df, expected):
"""Test that X is returned from transform."""
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)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Check X returned from transform",
)
def test_scaler_transform_call(self, mocker, scaler, scaler_type_str):
"""Test that the call to the scaler.transform method."""
df = d.create_df_3()
x = ScalingTransformer(columns=["b", "c"],
scaler=scaler,
scaler_kwargs={"copy": True})
x.fit(df)
mocked = mocker.patch(
f"sklearn.preprocessing.{scaler_type_str}.transform",
return_value=df[["b", "c"]],
)
x.transform(df)
assert mocked.call_count == 1, "unexpected number of calls to scaler fit"
call_args = mocked.call_args_list[0]
call_pos_args = call_args[0]
call_kwargs = call_args[1]
expected_positional_args = (df[["b", "c"]], )
h.assert_equal_dispatch(
expected=expected_positional_args,
actual=call_pos_args,
msg=
f"unexpected positional args in {scaler_type_str} transform call",
)
assert (call_kwargs == {}
), f"unexpected kwargs in {scaler_type_str} transform call"
def test_output_from_scaler_transform_set_to_columns(
self, mocker, scaler, scaler_type_str):
"""Test that the call to the scaler.transform method."""
df = d.create_df_3()
x = ScalingTransformer(columns=["b", "c"],
scaler=scaler,
scaler_kwargs={"copy": True})
x.fit(df)
scaler_transform_output = pd.DataFrame({
"b": [1, 2, 3, 4, 5, 6, 7],
"c": [7, 6, 5, 4, 3, 2, 1]
})
mocker.patch(
f"sklearn.preprocessing.{scaler_type_str}.transform",
return_value=scaler_transform_output,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=scaler_transform_output,
actual=df_transformed[["b", "c"]],
msg=
f"output from {scaler_type_str} transform not assigned to columns",
)
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_super_init_called(self, mocker):
"""Test that init calls BaseNominalTransformer.init.
Note, not using h.assert_function_call for this as it does not handle self being passed to BaseNominalTransformer.init.
"""
expected_keyword_args = {"columns": None, "verbose": True, "copy": True}
mocker.patch("tubular.nominal.BaseNominalTransformer.__init__")
x = OneHotEncodingTransformer(columns=None, verbose=True, copy=True)
assert (
tubular.nominal.BaseNominalTransformer.__init__.call_count == 1
), f"Not enough calls to BaseNominalTransformer.__init__ -\n Expected: 1\n Actual: {tubular.nominal.BaseNominalTransformer.__init__.call_count}"
call_args = tubular.nominal.BaseNominalTransformer.__init__.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.__init__ in OneHotEncodingTransformer.init",
)
assert (
len(call_pos_args) == 1
), f"Unepxected number of positional args in BaseNominalTransformer.__init__ call -\n Expected: 1\n Actual: {len(call_pos_args)}"
assert (
call_pos_args[0] is x
), f"Unexpected positional arg (self) in BaseNominalTransformer.__init__ call -\n Expected: self\n Actual: {call_pos_args[0]}"
def test_value_set_in_transform(self, df, expected):
"""Test that transform sets the value as expected."""
x = SetValueTransformer(columns=["a", "b"], value="a")
df_transformed = x.transform(df)
h.assert_equal_dispatch(
actual=df_transformed,
expected=expected,
msg="incorrect value after SetValueTransformer transform",
)
def test_X_returned(self, df, expected):
"""Test that X is returned from transform."""
x = BaseTransformer(columns="a", copy=True)
df_transformed = x.transform(X=df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Check X returned from transform",
)
def test_null_indicator_columns_correct(self, df, expected):
"""Test that the created indicator column is correct - and unrelated columns are unchanged"""
x = NullIndicator(columns=["b", "c"])
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Check null indicator columns created correctly in transform.",
)
def test_expected_output_1(self, df, expected):
"""Test that transform is giving the expected output when applied to float column."""
x1 = BaseImputer()
x1.columns = ["a"]
x1.impute_values_ = {"a": 7}
df_transformed = x1.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="ArbitraryImputer transform col a",
)
def test_expected_output_3(self, df, expected):
"""Test that transform is giving the expected output when applied to object and categorical columns."""
x1 = BaseImputer()
x1.columns = ["b", "c"]
x1.impute_values_ = {"b": "g", "c": "f"}
df_transformed = x1.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="ArbitraryImputer transform col b, c",
)
def test_fit_not_changing_data(self):
"""Test fit does not change X."""
df = d.create_OrdinalEncoderTransformer_test_df()
x = OrdinalEncoderTransformer(response_column="a", columns="b")
x.fit(df)
h.assert_equal_dispatch(
expected=d.create_OrdinalEncoderTransformer_test_df(),
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 = 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 = 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_columns_set_to_all_columns_when_none(self):
"""Test that X.columns are set to self.columns if self.columns is None when function called."""
df = d.create_df_1()
x = BaseTransformer(columns=None)
x.columns_set_or_check(X=df)
h.assert_equal_dispatch(
expected=list(df.columns.values),
actual=x.columns,
msg="x.columns set when None",
)
def test_X_returned(self):
"""Test that the input X is returned from the method."""
df = d.create_df_2()
x = ScalingTransformer(columns=["a"], scaler="standard")
df_returned = x.check_numeric_columns(df)
h.assert_equal_dispatch(
expected=df,
actual=df_returned,
msg="unexepcted object returned from check_numeric_columns",
)
def test_fit_not_changing_data(self):
"""Test fit does not change X."""
df = d.create_df_5()
x = GroupRareLevelsTransformer(columns=["a", "b", "c"])
x.fit(df)
h.assert_equal_dispatch(
expected=d.create_df_5(),
actual=df,
msg="Check X not changing during fit",
)
def test_columns_none_get_cat_columns(self):
"""If self.columns is None then object and categorical columns are set as self.columns."""
df = d.create_df_4()
x = BaseNominalTransformer()
x.columns = None
x.columns_set_or_check(df)
h.assert_equal_dispatch(expected=["b", "c"],
actual=x.columns,
msg="nominal columns getting")
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_nulls_imputed_correctly(self, df, expected):
"""Test missing values are filled with the correct values."""
x = MedianImputer(columns=["a", "b", "c"])
# set the impute values dict directly rather than fitting x on df so test works with helpers
x.impute_values_ = {"a": 3.5, "b": 5.0, "c": -1.5}
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Check nulls filled correctly in transform",
)
def test_unseen_categories_encoded_as_all_zeroes(self, df_test, expected):
"""Test OneHotEncodingTransformer.transform encodes unseen categories correctly (all 0s)."""
# transformer is fit on the whole dataset separately from the input df to work with the decorators
df_train = d.create_df_7()
x = OneHotEncodingTransformer(columns=["a", "b", "c"], verbose=False)
x.fit(df_train)
df_transformed = x.transform(df_test)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="unseen category rows not encoded as 0s",
)
def test_nulls_imputed_correctly_2(self, df, expected):
"""Test missing values are filled with the correct values - and unrelated columns are not changed."""
x = ModeImputer(columns=["a"])
# set the impute values dict directly rather than fitting x on df so test works with helpers
x.impute_values_ = {"a": 1.0}
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Check nulls filled correctly in transform",
)
def test_mappings_unchanged(self):
"""Test that mappings is unchanged in 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")
x.transform(df)
h.assert_equal_dispatch(
expected=mapping,
actual=x.mappings,
msg="CrossColumnMappingTransformer.transform has changed self.mappings unexpectedly",
)
def test_original_columns_kept_when_specified(self):
"""Test OneHotEncodingTransformer.transform keeps original columns when specified."""
df = d.create_df_7()
x = OneHotEncodingTransformer(drop_original=False)
x.fit(df)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=list(set()),
actual=list(set(["a", "b", "c"]) - set(df_transformed.columns)),
msg="original columns not kept",
)
def test_expected_output_4(self, df, expected):
"""Test that transform is giving the expected output when adding one and not dropping original columns."""
x1 = LogTransformer(columns=["a", "b"],
add_1=True,
drop=False,
suffix="new_col")
df_transformed = x1.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg=
"LogTransformer transform not adding 1 and dropping original columns",
)
