cleaning up

tests/data/scripts/create_test_data.py

@@ -28,26 +28,6 @@ def write_test_sample(reader: csv.reader, writer: csv.writer, property_test_case
             if has_prop:
                 break
 
-def get_test_sample(src_data: pd.DataFrame, property_test_cases: List[str]) -> pd.DataFrame:
-    # check that all test cases exist at least once in data set
-    assert len(src_data) > 0
-    contains_test_cases = []
-    for p in property_test_cases:
-        has_related_name = src_data['Property Name'].map(lambda x: True if p in str(x) else False)
-        contains_test_cases.append(np.any(has_related_name))
-    assert np.all(contains_test_cases)
-    test_cases = src_data['Property Name'].str.contains('|'.join(property_test_cases), na=False)
-    return src_data[test_cases]
-
-def copy_test_data_sample(
-        test_data: pd.DataFrame, 
-        test_data_file_path: pathlib.Path
-    ) -> pathlib.Path:
-    if not os.path.exists(test_data_file_path):
-        os.makedirs(os.path.dirname(test_data_file_path), exist_ok=True)
-        test_data.to_csv(test_data_file_path, index=False)
-    return test_data_file_path
-
 def main():
     # the first console argument is technically the python script so we skip that
     src_arg = sys.argv[1]
@@ -56,8 +36,6 @@ def main():
     src_path = curr_path / src_arg
     target_path = curr_path / target_arg
 
-    # src_data = get_and_clean_csv(src_path)
-    # test_data = get_test_sample(src_data, property_test_cases)
     csvfile = open(get_src_file_path(src_path), 'r')
     src_csv = csv.reader(csvfile)