def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_df_7()
x = SetValueTransformer(columns=["a", "b"], value=1)
expected_call_args = {0: {"args": (d.create_df_7(), ), "kwargs": {}}}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_df_7()
x = SeriesStrMethodTransformer(new_column_name="cc",
pd_method_name="find",
columns=["c"])
expected_call_args = {0: {"args": (d.create_df_7(), ), "kwargs": {}}}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
def test_attributes_unchanged_by_transform(self):
"""Test that attributes set in init are unchanged by the transform method."""
df = d.create_df_7()
x = SeriesStrMethodTransformer(
new_column_name="b",
pd_method_name="pad",
columns=["b"],
pd_method_kwargs={"width": 10},
)
x2 = SeriesStrMethodTransformer(
new_column_name="b",
pd_method_name="pad",
columns=["b"],
pd_method_kwargs={"width": 10},
)
x.transform(df)
assert (
x.new_column_name == x2.new_column_name
), "new_column_name changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_name == x2.pd_method_name
), "pd_method_name changed by SeriesDtMethodTransformer.transform"
assert (x.columns == x2.columns
), "columns changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_kwargs == x2.pd_method_kwargs
), "pd_method_kwargs changed by SeriesDtMethodTransformer.transform"
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 expected_df_2():
"""Expected output of test_expected_output_overwrite."""
df = d.create_df_7()
df["b"] = df["b"].str.pad(width=10)
return df
def expected_df_1():
"""Expected output of test_expected_output_no_overwrite."""
df = d.create_df_7()
df["b_new"] = df["b"].str.find(sub="a")
return df
def test_warning_generated_by_unseen_categories(self):
"""Test OneHotEncodingTransformer.transform triggers a warning for unseen categories."""
df_train = d.create_df_7()
df_test = d.create_df_8()
x = OneHotEncodingTransformer(verbose=True)
x.fit(df_train)
with pytest.warns(Warning):
x.transform(df_test)
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_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_original_columns_dropped_when_specified(self):
"""Test OneHotEncodingTransformer.transform drops original columns get when specified."""
df = d.create_df_7()
x = OneHotEncodingTransformer(columns=["a", "b", "c"], drop_original=True)
x.fit(df)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=["a", "b", "c"],
actual=[
x for x in df.columns.values if x not in df_transformed.columns.values
],
msg="original columns not dropped",
)
def test_expected_output(self, df_test, expected):
"""Test that OneHotEncodingTransformer.transform encodes the feature correctly.
Also tests that OneHotEncodingTransformer.transform does not modify unrelated columns.
"""
# 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="b")
x.fit(df_train)
df_transformed = x.transform(df_test)
h.assert_frame_equal_msg(
expected=expected,
actual=df_transformed,
msg_tag="Unspecified columns changed in transform",
)
def test_renaming_feature_works_as_expected(self):
"""Test OneHotEncodingTransformer.transform() is renaming features correctly."""
df = d.create_df_7()
df = df[["b", "c"]]
x = OneHotEncodingTransformer(
columns=["b", "c"], separator="|", drop_original=True
)
x.fit(df)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=["b|x", "b|y", "b|z", "c|a", "c|b", "c|c"],
actual=list(df_transformed.columns.values),
msg="renaming columns feature in OneHotEncodingTransformer.transform",
)
class TestTransform(object):
"""Tests for the transform method on CrossColumnMappingTransformer."""
def expected_df_1():
"""Expected output for test_expected_output."""
df = pd.DataFrame(
{"a": [1, 2, 3, 4, 5, 6], "b": ["aa", "bb", "cc", "dd", "ee", "ff"]}
)
return df
def expected_df_2():
"""Expected output for test_non_specified_values_unchanged."""
df = pd.DataFrame(
{"a": [1, 2, 3, 4, 5, 6], "b": ["aa", "bb", "cc", "d", "e", "f"]}
)
return df
def expected_df_3():
"""Expected output for test_multiple_mappings_ordered_dict."""
df = pd.DataFrame(
{
"a": [4, 2, 2, 1, 3],
"b": ["x", "z", "y", "x", "x"],
"c": ["cc", "dd", "bb", "cc", "cc"],
}
)
return df
def test_arguments(self):
"""Test that transform has expected arguments."""
h.test_function_arguments(
func=CrossColumnMappingTransformer.transform,
expected_arguments=["self", "X"],
expected_default_values=None,
)
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"}}
x = CrossColumnMappingTransformer(mappings=mapping, adjust_column="b")
expected_call_args = {0: {"args": (["adjust_column"],), "kwargs": {}}}
with h.assert_function_call(
mocker, tubular.base.BaseTransformer, "check_is_fitted", expected_call_args
):
x.transform(df)
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_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)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_df_1(), expected_df_1())
+ h.index_preserved_params(d.create_df_1(), expected_df_1()),
)
def test_expected_output(self, df, expected):
"""Test that transform is giving the expected output."""
mapping = {"a": {1: "aa", 2: "bb", 3: "cc", 4: "dd", 5: "ee", 6: "ff"}}
x = CrossColumnMappingTransformer(mappings=mapping, adjust_column="b")
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag="expected output from cross column mapping transformer",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_df_1(), expected_df_2())
+ h.index_preserved_params(d.create_df_1(), expected_df_2()),
)
def test_non_specified_values_unchanged(self, df, expected):
"""Test that values not specified in mappings are left unchanged in transform."""
mapping = {"a": {1: "aa", 2: "bb", 3: "cc"}}
x = CrossColumnMappingTransformer(mappings=mapping, adjust_column="b")
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag="expected output from cross column mapping transformer",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_df_7(), expected_df_3())
+ h.index_preserved_params(d.create_df_7(), expected_df_3()),
)
def test_multiple_mappings_ordered_dict(self, df, expected):
"""Test that mappings by multiple columns using an ordered dict gives the expected output in transform"""
mapping = OrderedDict()
mapping["a"] = {1: "aa", 2: "bb"}
mapping["b"] = {"x": "cc", "z": "dd"}
x = CrossColumnMappingTransformer(mappings=mapping, adjust_column="c")
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag="expected output from cross column mapping transformer",
)
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",
)
class TestTransform(object):
"""Tests for SeriesStrMethodTransformer.transform()."""
def expected_df_1():
"""Expected output of test_expected_output_no_overwrite."""
df = d.create_df_7()
df["b_new"] = df["b"].str.find(sub="a")
return df
def expected_df_2():
"""Expected output of test_expected_output_overwrite."""
df = d.create_df_7()
df["b"] = df["b"].str.pad(width=10)
return df
def test_arguments(self):
"""Test that transform has expected arguments."""
h.test_function_arguments(func=SeriesStrMethodTransformer.transform,
expected_arguments=["self", "X"])
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_df_7()
x = SeriesStrMethodTransformer(new_column_name="cc",
pd_method_name="find",
columns=["c"])
expected_call_args = {0: {"args": (d.create_df_7(), ), "kwargs": {}}}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_df_7(), expected_df_1()) +
h.index_preserved_params(d.create_df_7(), expected_df_1()),
)
def test_expected_output_no_overwrite(self, df, expected):
"""Test a single column output from transform gives expected results, when not overwriting the original column."""
x = SeriesStrMethodTransformer(
new_column_name="b_new",
pd_method_name="find",
columns=["b"],
pd_method_kwargs={"sub": "a"},
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag=
"Unexpected values in SeriesStrMethodTransformer.transform with find, not overwriting original column",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_df_7(), expected_df_2()) +
h.index_preserved_params(d.create_df_7(), expected_df_2()),
)
def test_expected_output_overwrite(self, df, expected):
"""Test a single column output from transform gives expected results, when overwriting the original column."""
x = SeriesStrMethodTransformer(
new_column_name="b",
pd_method_name="pad",
columns=["b"],
pd_method_kwargs={"width": 10},
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag=
"Unexpected values in SeriesStrMethodTransformer.transform with pad, overwriting original column",
)
@pytest.mark.parametrize(
"df, new_column_name, pd_method_name, columns, pd_method_kwargs",
[
(d.create_df_7(), "b_new", "find", ["b"], {
"sub": "a"
}),
(
d.create_df_7(),
"c_slice",
"slice",
["c"],
{
"start": 0,
"stop": 1,
"step": 1
},
),
(d.create_df_7(), "b_upper", "upper", ["b"], {}),
],
)
def test_pandas_method_called(self, mocker, df, new_column_name,
pd_method_name, columns, pd_method_kwargs):
"""Test that the pandas.Series.str method is called as expected (with kwargs passed) during transform."""
spy = mocker.spy(pd.Series.str, pd_method_name)
x = SeriesStrMethodTransformer(
new_column_name=new_column_name,
pd_method_name=pd_method_name,
columns=columns,
pd_method_kwargs=pd_method_kwargs,
)
x.transform(df)
# pull out positional and keyword args to target the call
call_args = spy.call_args_list[0]
call_kwargs = call_args[1]
# test keyword are as expected
h.assert_dict_equal_msg(
actual=call_kwargs,
expected=pd_method_kwargs,
msg_tag=f"""Keyword arg assert for {pd_method_name}""",
)
def test_attributes_unchanged_by_transform(self):
"""Test that attributes set in init are unchanged by the transform method."""
df = d.create_df_7()
x = SeriesStrMethodTransformer(
new_column_name="b",
pd_method_name="pad",
columns=["b"],
pd_method_kwargs={"width": 10},
)
x2 = SeriesStrMethodTransformer(
new_column_name="b",
pd_method_name="pad",
columns=["b"],
pd_method_kwargs={"width": 10},
)
x.transform(df)
assert (
x.new_column_name == x2.new_column_name
), "new_column_name changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_name == x2.pd_method_name
), "pd_method_name changed by SeriesDtMethodTransformer.transform"
assert (x.columns == x2.columns
), "columns changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_kwargs == x2.pd_method_kwargs
), "pd_method_kwargs changed by SeriesDtMethodTransformer.transform"
class TestTransform(object):
"""Tests for OneHotEncodingTransformer.transform()."""
def expected_df_1():
"""Expected output for test_expected_output."""
df = pd.DataFrame(
{
"a": [4, 2, 2, 1, 3],
"b": ["x", "z", "y", "x", "x"],
"c": ["c", "a", "a", "c", "b"],
}
)
df["c"] = df["c"].astype("category")
df["b_x"] = [1.0, 0.0, 0.0, 1.0, 1.0]
df["b_y"] = [0.0, 0.0, 1.0, 0.0, 0.0]
df["b_z"] = [0.0, 1.0, 0.0, 0.0, 0.0]
return df
def expected_df_2():
"""Expected output for test_unseen_categories_encoded_as_all_zeroes."""
df = pd.DataFrame(
{
"a": [1, 5, 2, 3, 3],
"b": ["w", "w", "z", "y", "x"],
"c": ["a", "a", "c", "b", "a"],
},
index=[10, 15, 200, 251, 59],
)
df["c"] = df["c"].astype("category")
df["a_1"] = [1.0, 0.0, 0.0, 0.0, 0.0]
df["a_2"] = [0.0, 0.0, 1.0, 0.0, 0.0]
df["a_3"] = [0.0, 0.0, 0.0, 1.0, 1.0]
df["a_4"] = [0.0, 0.0, 0.0, 0.0, 0.0]
df["b_x"] = [0.0, 0.0, 0.0, 0.0, 1.0]
df["b_y"] = [0.0, 0.0, 0.0, 1.0, 0.0]
df["b_z"] = [0.0, 0.0, 1.0, 0.0, 0.0]
df["c_a"] = [1.0, 1.0, 0.0, 0.0, 1.0]
df["c_b"] = [0.0, 0.0, 0.0, 1.0, 0.0]
df["c_c"] = [0.0, 0.0, 1.0, 0.0, 0.0]
return df
def test_arguments(self):
"""Test that transform has expected arguments."""
h.test_function_arguments(
func=OneHotEncodingTransformer.transform, expected_arguments=["self", "X"]
)
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_check_is_fitted_first_call(self, mocker):
"""Test the calls to BaseTransformer check_is_fitted."""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
x.fit(df)
expected_call_args = {
0: {"args": (["separator"],), "kwargs": {}},
1: {"args": (["drop_original"],), "kwargs": {}},
}
with h.assert_function_call(
mocker, tubular.base.BaseTransformer, "check_is_fitted", expected_call_args
):
x.transform(df)
def test_non_numeric_column_error_1(self):
"""Test that transform will raise an error if a column to transform has nulls."""
df_train = d.create_df_1()
df_test = d.create_df_2()
x = OneHotEncodingTransformer(columns=["b"])
x.fit(df_train)
with pytest.raises(
ValueError, match="column b has nulls - replace before proceeding"
):
x.transform(df_test)
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_one_hot_encoder_transform_called(self, mocker):
"""Test that OneHotEncoder.transform called."""
df = d.create_df_1()
x = OneHotEncodingTransformer(columns="b")
x.fit(df)
mocker.patch("sklearn.preprocessing.OneHotEncoder.transform")
x.transform(df)
assert (
sklearn.preprocessing.OneHotEncoder.transform.call_count == 1
), f"Not enough calls to OneHotEncoder.transform -\n Expected: 1\n Actual: {sklearn.preprocessing.OneHotEncoder.transform.call_count}"
call_args = sklearn.preprocessing.OneHotEncoder.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 OneHotEncodingTransformer.transform in BaseTransformer.init",
)
assert (
len(call_pos_args) == 2
), f"Unepxected number of positional args in OneHotEncodingTransformer.transform call -\n Expected: 2\n Actual: {len(call_pos_args)}"
assert (
call_pos_args[0] is x
), f"Unexpected positional arg (self, index 1) in OneHotEncodingTransformer.transform call -\n Expected: self\n Actual: {call_pos_args[0]}"
h.assert_frame_equal_msg(
expected=d.create_df_1()[["b"]],
actual=call_pos_args[1],
msg_tag="X positional arg in OneHotEncodingTransformer.transform call",
)
@pytest.mark.parametrize(
"df_test, expected",
h.row_by_row_params(d.create_df_7(), expected_df_1())
+ h.index_preserved_params(d.create_df_7(), expected_df_1()),
)
def test_expected_output(self, df_test, expected):
"""Test that OneHotEncodingTransformer.transform encodes the feature correctly.
Also tests that OneHotEncodingTransformer.transform does not modify unrelated columns.
"""
# 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="b")
x.fit(df_train)
df_transformed = x.transform(df_test)
h.assert_frame_equal_msg(
expected=expected,
actual=df_transformed,
msg_tag="Unspecified columns changed in transform",
)
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_renaming_feature_works_as_expected(self):
"""Test OneHotEncodingTransformer.transform() is renaming features correctly."""
df = d.create_df_7()
df = df[["b", "c"]]
x = OneHotEncodingTransformer(
columns=["b", "c"], separator="|", drop_original=True
)
x.fit(df)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=["b|x", "b|y", "b|z", "c|a", "c|b", "c|c"],
actual=list(df_transformed.columns.values),
msg="renaming columns feature in OneHotEncodingTransformer.transform",
)
def test_warning_generated_by_unseen_categories(self):
"""Test OneHotEncodingTransformer.transform triggers a warning for unseen categories."""
df_train = d.create_df_7()
df_test = d.create_df_8()
x = OneHotEncodingTransformer(verbose=True)
x.fit(df_train)
with pytest.warns(Warning):
x.transform(df_test)
@pytest.mark.parametrize(
"df_test, expected",
h.row_by_row_params(d.create_df_8(), expected_df_2())
+ h.index_preserved_params(d.create_df_8(), expected_df_2()),
)
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_original_columns_dropped_when_specified(self):
"""Test OneHotEncodingTransformer.transform drops original columns get when specified."""
df = d.create_df_7()
x = OneHotEncodingTransformer(columns=["a", "b", "c"], drop_original=True)
x.fit(df)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=["a", "b", "c"],
actual=[
x for x in df.columns.values if x not in df_transformed.columns.values
],
msg="original columns not dropped",
)
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",
)
