def dataset_with_operations(fillna_col0_col1, fillna_col1_col4) -> Dataset:
"""
Create Dataset instance with not empty ``operations_history`` attribute.
Returns
-------
Dataset
Dataset instance containing FeatureOperation instances
in the `operations_history` attribute
"""
dataset = Dataset(df_object=DataFrameMock.df_generic(10))
dataset.track_history(fillna_col0_col1)
dataset.track_history(fillna_col1_col4)
return dataset
def it_knows_how_to_track_history(self, request, metadata_cols,
derived_columns, expected_metadata_cols):
operations_list_iadd_ = method_mock(request, OperationsList,
"__iadd__")
expected_df = DataFrameMock.df_generic(10)
get_df_from_csv_ = function_mock(request,
"trousse.dataset.get_df_from_csv")
get_df_from_csv_.return_value = expected_df
dataset = Dataset(data_file="fake/path", metadata_cols=metadata_cols)
feat_op = fop.FillNA(columns=["metadata_num_col"],
derived_columns=derived_columns,
value=0)
dataset.track_history(feat_op)
assert dataset.metadata_cols == expected_metadata_cols
operations_list_iadd_.assert_called_once_with(ANY, feat_op)
def test_track_history_with_no_derived_columns(
self,
request,
metadata_columns,
original_columns,
expected_metadata_cols,
):
df = DataFrameMock.df_generic(10)
dataset = Dataset(
df_object=df,
metadata_cols=metadata_columns,
)
feat_op = fop.FillNA(columns=original_columns,
derived_columns=None,
value=0)
dataset.track_history(feat_op)
for column in original_columns:
# Check if the operation is added to each column
assert feat_op in dataset.operations_history[column]
assert dataset.metadata_cols == expected_metadata_cols
