def test_text_datasetdict_reader(split, features, keep_in_memory, text_path,
tmp_path):
if split:
path = {split: text_path}
else:
split = "train"
path = {"train": text_path, "test": text_path}
cache_dir = tmp_path / "cache"
default_expected_features = {"text": "string"}
expected_features = features.copy(
) if features else default_expected_features
features = Features(
{feature: Value(dtype)
for feature, dtype in features.items()}) if features else None
with assert_arrow_memory_increases(
) if keep_in_memory else assert_arrow_memory_doesnt_increase():
dataset = TextDatasetReader(path,
features=features,
cache_dir=cache_dir,
keep_in_memory=keep_in_memory).read()
assert isinstance(dataset, DatasetDict)
dataset = dataset[split]
assert dataset.num_rows == 4
assert dataset.num_columns == 1
assert dataset.column_names == ["text"]
assert dataset.split == split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
def test_text_dataset_reader(path_type, split, features, keep_in_memory,
text_path, tmp_path):
if issubclass(path_type, str):
path = text_path
elif issubclass(path_type, list):
path = [text_path]
cache_dir = tmp_path / "cache"
expected_split = str(split) if split else "train"
default_expected_features = {"text": "string"}
expected_features = features.copy(
) if features else default_expected_features
features = Features(
{feature: Value(dtype)
for feature, dtype in features.items()}) if features else None
with assert_arrow_memory_increases(
) if keep_in_memory else assert_arrow_memory_doesnt_increase():
dataset = TextDatasetReader(path,
split=split,
features=features,
cache_dir=cache_dir,
keep_in_memory=keep_in_memory).read()
assert isinstance(dataset, Dataset)
assert dataset.num_rows == 4
assert dataset.num_columns == 1
assert dataset.column_names == ["text"]
assert dataset.split == expected_split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
def test_dataset_from_text_path_type(path_type, text_path, tmp_path):
if issubclass(path_type, str):
path = text_path
elif issubclass(path_type, list):
path = [text_path]
cache_dir = tmp_path / "cache"
expected_features = {"text": "string"}
dataset = TextDatasetReader(path, cache_dir=cache_dir).read()
_check_text_dataset(dataset, expected_features)
def test_dataset_from_text_features(features, text_path, tmp_path):
cache_dir = tmp_path / "cache"
default_expected_features = {"text": "string"}
expected_features = features.copy() if features else default_expected_features
features = (
Features({feature: Value(dtype) for feature, dtype in features.items()}) if features is not None else None
)
dataset = TextDatasetReader(text_path, features=features, cache_dir=cache_dir).read()
_check_text_dataset(dataset, expected_features)
def test_datasetdict_from_text_features(features, text_path, tmp_path):
cache_dir = tmp_path / "cache"
# CSV file loses col_1 string dtype information: default now is "int64" instead of "string"
default_expected_features = {"text": "string"}
expected_features = features.copy() if features else default_expected_features
features = (
Features({feature: Value(dtype) for feature, dtype in features.items()}) if features is not None else None
)
dataset = TextDatasetReader({"train": text_path}, features=features, cache_dir=cache_dir).read()
_check_text_datasetdict(dataset, expected_features)
def test_datasetdict_from_text_split(split, text_path, tmp_path):
if split:
path = {split: text_path}
else:
split = "train"
path = {"train": text_path, "test": text_path}
cache_dir = tmp_path / "cache"
expected_features = {"text": "string"}
dataset = TextDatasetReader(path, cache_dir=cache_dir).read()
_check_text_datasetdict(dataset, expected_features, splits=list(path.keys()))
assert all(dataset[split].split == split for split in path.keys())
def test_datasetdict_from_text_keep_in_memory(keep_in_memory, text_path, tmp_path):
cache_dir = tmp_path / "cache"
expected_features = {"text": "string"}
with assert_arrow_memory_increases() if keep_in_memory else assert_arrow_memory_doesnt_increase():
dataset = TextDatasetReader({"train": text_path}, cache_dir=cache_dir, keep_in_memory=keep_in_memory).read()
_check_text_datasetdict(dataset, expected_features)
def test_dataset_from_text_split(split, text_path, tmp_path):
cache_dir = tmp_path / "cache"
expected_features = {"text": "string"}
dataset = TextDatasetReader(text_path, cache_dir=cache_dir, split=split).read()
_check_text_dataset(dataset, expected_features)
assert dataset.split == str(split) if split else "train"