def test_integration_user_define_tag_separator_fn(self):
def internal_conversion_of_list_to_comma_separated_list(tags):
return str(tags).replace("[", "").replace("]", "").replace("'", "")
number_of_data_points = 4
create_csv_file(
self.a_data_container_path,
number_of_data_points=number_of_data_points,
reformat_list_fn=
internal_conversion_of_list_to_comma_separated_list,
)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path,
column_names=default_csv_column_name,
tag_seperator_reformat_fn=comma_separated_list_reformat,
)
self._test_integration(number_of_data_points, csv_dataset_container)
number_of_data_points = 5
create_csv_file(
self.a_data_container_path,
number_of_data_points=number_of_data_points,
reformat_list_fn=
internal_conversion_of_list_to_comma_separated_list,
)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path,
column_names=default_csv_column_name,
tag_seperator_reformat_fn=comma_separated_list_reformat,
)
self._test_integration(number_of_data_points, csv_dataset_container)
def test_givenACSVDatasetContainer_whenGetOneItem_thenReturnTheCorrectItem(
self):
create_csv_file(self.a_data_container_path)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path, column_names=default_csv_column_name)
# first data point
idx = 0
expected_address = base_string.format(idx)
expected_tags_idx = a_tags_sequence
actual_address, actual_tags_idx = csv_dataset_container[idx]
self.assertEqual(expected_address, actual_address)
self.assertListEqual(expected_tags_idx, actual_tags_idx)
# second data point
idx = 1
expected_address = base_string.format(idx)
expected_tags_idx = a_tags_sequence
actual_address, actual_tags_idx = csv_dataset_container[idx]
self.assertEqual(expected_address, actual_address)
self.assertListEqual(expected_tags_idx, actual_tags_idx)
# third data point
idx = 2
expected_address = base_string.format(idx)
expected_tags_idx = a_tags_sequence
actual_address, actual_tags_idx = csv_dataset_container[idx]
self.assertEqual(expected_address, actual_address)
self.assertListEqual(expected_tags_idx, actual_tags_idx)
def test_integration_user_define_column_names(self):
user_define_column_names = ["a_name", "Another_name"]
number_of_data_points = 4
create_csv_file(
self.a_data_container_path,
number_of_data_points=number_of_data_points,
column_names=user_define_column_names,
)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path, column_names=user_define_column_names)
self._test_integration(number_of_data_points, csv_dataset_container)
number_of_data_points = 5
create_csv_file(
self.a_data_container_path,
number_of_data_points=number_of_data_points,
column_names=user_define_column_names,
)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path, column_names=user_define_column_names)
self._test_integration(number_of_data_points, csv_dataset_container)
def test_integration_user_define_separator(self):
separator = ";"
number_of_data_points = 4
create_csv_file(self.a_data_container_path,
number_of_data_points=number_of_data_points,
separator=separator)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path,
column_names=default_csv_column_name,
separator=separator)
self._test_integration(number_of_data_points, csv_dataset_container)
number_of_data_points = 5
create_csv_file(self.a_data_container_path,
number_of_data_points=number_of_data_points,
separator=separator)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path,
column_names=default_csv_column_name,
separator=separator)
self._test_integration(number_of_data_points, csv_dataset_container)
def test_ifIsNotSupportedExportFile_raiseValueError(self):
create_csv_file(self.fake_data_path_csv, predict_container=True)
with self.assertRaises(ValueError):
parse.main([
self.a_fasttext_model_type,
self.fake_data_path_csv,
self.a_unsupported_data_path,
"--device",
self.cpu_device,
])
def test_ifIsCSVFile_noColumnName_raiseValueError(self):
create_csv_file(self.fake_data_path_csv, predict_container=True)
with self.assertRaises(ValueError):
parse.main([
self.a_fasttext_model_type,
self.fake_data_path_csv,
self.csv_export_filename,
"--device",
self.cpu_device,
])
def test_integration_csv(self):
create_csv_file(self.fake_data_path_csv, predict_container=True)
parse.main([
self.a_fasttext_att_model_type,
self.fake_data_path_csv,
self.csv_export_filename,
"--device",
self.cpu_device,
"--csv_column_name",
"Address",
])
export_path = generate_export_path(self.fake_data_path_csv,
self.csv_export_filename)
self.assertTrue(os.path.isfile(export_path))
def test_integration(self):
number_of_data_points = 4
create_csv_file(
self.a_data_container_path,
number_of_data_points=number_of_data_points,
)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path, column_names=default_csv_column_name)
self._test_integration(number_of_data_points, csv_dataset_container)
number_of_data_points = 5
create_csv_file(
self.a_data_container_path,
number_of_data_points=number_of_data_points,
)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path, column_names=default_csv_column_name)
self._test_integration(number_of_data_points, csv_dataset_container)
def test_integration_predict_container(self):
number_of_data_points = 4
create_csv_file(self.a_data_container_path,
number_of_data_points=number_of_data_points,
predict_container=False)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path,
column_names=["Address"],
is_training_container=False)
self._test_integration(number_of_data_points, csv_dataset_container)
number_of_data_points = 5
create_csv_file(self.a_data_container_path,
number_of_data_points=number_of_data_points,
predict_container=False)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path,
column_names=["Address"],
is_training_container=False)
self._test_integration(number_of_data_points, csv_dataset_container)
def test_givenAPickleDatasetContainer_whenGetSlice_thenReturnTheCorrectItems(
self):
create_csv_file(self.a_data_container_path)
csv_dataset_container = CSVDatasetContainer(
self.a_data_container_path, column_names=default_csv_column_name)
start_idx = 0
end_idx = 2
expected_addresses = [
base_string.format(idx) for idx in range(start_idx, end_idx)
]
expected_tags_idxs = [a_tags_sequence] * (end_idx - start_idx)
sliced_addresses = csv_dataset_container[start_idx:end_idx]
self.assertIsInstance(sliced_addresses, list)
for actual_address_tuple, expected_address, expected_tags_idx in zip(
sliced_addresses, expected_addresses, expected_tags_idxs):
actual_address, actual_tags_idx = actual_address_tuple[
0], actual_address_tuple[1]
self.assertEqual(expected_address, actual_address)
self.assertListEqual(expected_tags_idx, actual_tags_idx)
start_idx = 2
end_idx = 4
expected_addresses = [
base_string.format(idx) for idx in range(start_idx, end_idx)
]
expected_tags_idxs = [a_tags_sequence] * (end_idx - start_idx)
sliced_addresses = csv_dataset_container[start_idx:end_idx]
self.assertIsInstance(sliced_addresses, list)
for actual_address_tuple, expected_address, expected_tags_idx in zip(
sliced_addresses, expected_addresses, expected_tags_idxs):
actual_address, actual_tags_idx = actual_address_tuple[
0], actual_address_tuple[1]
self.assertEqual(expected_address, actual_address)
self.assertListEqual(expected_tags_idx, actual_tags_idx)