def it_can_apply_ordinal_encoder(
self,
request,
columns,
derived_columns,
expected_new_columns,
):
df = DataFrameMock.df_generic(sample_size=100)
get_df_from_csv_ = function_mock(request,
"trousse.dataset.get_df_from_csv")
get_df_from_csv_.return_value = df
dataset = Dataset(data_file="fake/path0")
sk_fit_transform_ = method_mock(request, sk_preproc.OrdinalEncoder,
"fit_transform")
sk_fit_transform_.return_value = pd.Series(range(100))
ordinal_encoder = fop.OrdinalEncoder(
columns=columns,
derived_columns=derived_columns,
)
encoded_dataset = ordinal_encoder._apply(dataset)
assert encoded_dataset is not None
assert encoded_dataset is not dataset
assert isinstance(encoded_dataset, Dataset)
for col in expected_new_columns:
assert col in encoded_dataset.data.columns
get_df_from_csv_.assert_called_once_with("fake/path0")
assert len(sk_fit_transform_.call_args_list) == len(columns)
pd.testing.assert_frame_equal(
sk_fit_transform_.call_args_list[0][0][1], df[[columns[0]]])
def it_knows_its_encoder(self):
ordinal_encoder = fop.OrdinalEncoder(columns=["col0"],
derived_columns=["col1"])
encoder_attr = ordinal_encoder.encoder
assert isinstance(encoder_attr, sk_preproc.OrdinalEncoder)
def test_ordinal_encoder(csv, columns, derived_columns, expected_csv):
dataset = Dataset(data_file=csv)
expected_df = load_expectation(expected_csv, type_="csv")
ordinal_encoder = fop.OrdinalEncoder(columns=columns,
derived_columns=derived_columns)
encoded_dataset = ordinal_encoder(dataset)
pd.testing.assert_frame_equal(encoded_dataset.data, expected_df)
def it_knows_if_equal(self, other, expected_equal):
feat_op = fop.OrdinalEncoder(
columns=["exam_num_col_0"],
derived_columns=["encoded_exam_num_col_0"],
)
equal = feat_op == other
assert type(equal) == bool
assert equal == expected_equal
def it_construct_from_args(self, request):
_init_ = initializer_mock(request, fop.OrdinalEncoder)
ordinal_encoder = fop.OrdinalEncoder(columns=["col0"],
derived_columns=["col1"])
_init_.assert_called_once_with(
ANY,
columns=["col0"],
derived_columns=["col1"],
)
assert isinstance(ordinal_encoder, fop.OrdinalEncoder)
def and_it_validates_its_arguments(self, request):
validate_columns_ = method_mock(request, fop.OrdinalEncoder,
"_validate_single_element_columns")
validate_derived_columns_ = method_mock(
request, fop.OrdinalEncoder,
"_validate_single_element_derived_columns")
ordinal_encoder = fop.OrdinalEncoder(columns=["col0"],
derived_columns=["col1"])
validate_columns_.assert_called_once_with(ordinal_encoder, ["col0"])
validate_derived_columns_.assert_called_once_with(
ordinal_encoder, ["col1"])
def it_can_encode_with_template_call(self, request):
_apply_ = method_mock(request, fop.OrdinalEncoder, "_apply")
track_history_ = method_mock(request, Dataset, "track_history")
df = DataFrameMock.df_generic(sample_size=100)
get_df_from_csv_ = function_mock(request,
"trousse.dataset.get_df_from_csv")
get_df_from_csv_.return_value = df
dataset_in = Dataset(data_file="fake/path0")
dataset_out = Dataset(data_file="fake/path0")
_apply_.return_value = dataset_out
ordinal_encoder = fop.OrdinalEncoder(
columns=["exam_num_col_0"],
derived_columns=["exam_str_col_0"],
)
replaced_dataset = ordinal_encoder(dataset_in)
_apply_.assert_called_once_with(ordinal_encoder, dataset_in)
track_history_.assert_called_once_with(replaced_dataset,
ordinal_encoder)
assert replaced_dataset is dataset_out
class DescribeOrdinalEncoder:
def it_construct_from_args(self, request):
_init_ = initializer_mock(request, fop.OrdinalEncoder)
ordinal_encoder = fop.OrdinalEncoder(columns=["col0"],
derived_columns=["col1"])
_init_.assert_called_once_with(
ANY,
columns=["col0"],
derived_columns=["col1"],
)
assert isinstance(ordinal_encoder, fop.OrdinalEncoder)
def and_it_validates_its_arguments(self, request):
validate_columns_ = method_mock(request, fop.OrdinalEncoder,
"_validate_single_element_columns")
validate_derived_columns_ = method_mock(
request, fop.OrdinalEncoder,
"_validate_single_element_derived_columns")
ordinal_encoder = fop.OrdinalEncoder(columns=["col0"],
derived_columns=["col1"])
validate_columns_.assert_called_once_with(ordinal_encoder, ["col0"])
validate_derived_columns_.assert_called_once_with(
ordinal_encoder, ["col1"])
def it_knows_its_encoder(self):
ordinal_encoder = fop.OrdinalEncoder(columns=["col0"],
derived_columns=["col1"])
encoder_attr = ordinal_encoder.encoder
assert isinstance(encoder_attr, sk_preproc.OrdinalEncoder)
@pytest.mark.parametrize(
"columns, derived_columns, expected_new_columns",
[
(
["exam_str_col_0"],
["col1"],
["col1"],
),
(
["exam_str_col_0"],
None,
[],
),
],
)
def it_can_apply_ordinal_encoder(
self,
request,
columns,
derived_columns,
expected_new_columns,
):
df = DataFrameMock.df_generic(sample_size=100)
get_df_from_csv_ = function_mock(request,
"trousse.dataset.get_df_from_csv")
get_df_from_csv_.return_value = df
dataset = Dataset(data_file="fake/path0")
sk_fit_transform_ = method_mock(request, sk_preproc.OrdinalEncoder,
"fit_transform")
sk_fit_transform_.return_value = pd.Series(range(100))
ordinal_encoder = fop.OrdinalEncoder(
columns=columns,
derived_columns=derived_columns,
)
encoded_dataset = ordinal_encoder._apply(dataset)
assert encoded_dataset is not None
assert encoded_dataset is not dataset
assert isinstance(encoded_dataset, Dataset)
for col in expected_new_columns:
assert col in encoded_dataset.data.columns
get_df_from_csv_.assert_called_once_with("fake/path0")
assert len(sk_fit_transform_.call_args_list) == len(columns)
pd.testing.assert_frame_equal(
sk_fit_transform_.call_args_list[0][0][1], df[[columns[0]]])
def it_can_encode_with_template_call(self, request):
_apply_ = method_mock(request, fop.OrdinalEncoder, "_apply")
track_history_ = method_mock(request, Dataset, "track_history")
df = DataFrameMock.df_generic(sample_size=100)
get_df_from_csv_ = function_mock(request,
"trousse.dataset.get_df_from_csv")
get_df_from_csv_.return_value = df
dataset_in = Dataset(data_file="fake/path0")
dataset_out = Dataset(data_file="fake/path0")
_apply_.return_value = dataset_out
ordinal_encoder = fop.OrdinalEncoder(
columns=["exam_num_col_0"],
derived_columns=["exam_str_col_0"],
)
replaced_dataset = ordinal_encoder(dataset_in)
_apply_.assert_called_once_with(ordinal_encoder, dataset_in)
track_history_.assert_called_once_with(replaced_dataset,
ordinal_encoder)
assert replaced_dataset is dataset_out
@pytest.mark.parametrize(
"other, expected_equal",
[
(
fop.OrdinalEncoder(
columns=["exam_num_col_0"],
derived_columns=["encoded_exam_num_col_0"],
),
True,
),
(
fop.OrdinalEncoder(
columns=["exam_num_col_1"],
derived_columns=["encoded_exam_num_col_0"],
),
False,
),
(
fop.OrdinalEncoder(
columns=["exam_num_col_0"],
derived_columns=["encoded_exam_num_col_1"],
),
False,
),
(
fop.OrdinalEncoder(
columns=["exam_num_col_1"],
derived_columns=["encoded_exam_num_col_1"],
),
False,
),
(dict(), False),
],
)
def it_knows_if_equal(self, other, expected_equal):
feat_op = fop.OrdinalEncoder(
columns=["exam_num_col_0"],
derived_columns=["encoded_exam_num_col_0"],
)
equal = feat_op == other
assert type(equal) == bool
assert equal == expected_equal