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_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_csv_dataset_reader(path_type, split, features, keep_in_memory,
csv_path, tmp_path):
if issubclass(path_type, str):
path = csv_path
elif issubclass(path_type, list):
path = [csv_path]
cache_dir = tmp_path / "cache"
expected_split = str(split) if split else "train"
# CSV file loses col_1 string dtype information: default now is "int64" instead of "string"
default_expected_features = {
"col_1": "int64",
"col_2": "int64",
"col_3": "float64"
}
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 = CsvDatasetReader(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 == 3
assert dataset.column_names == ["col_1", "col_2", "col_3"]
assert dataset.split == expected_split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
def test_datasetdict_from_csv(split, features, keep_in_memory, csv_path,
tmp_path):
if split:
path = {split: csv_path}
else:
split = "train"
path = {"train": csv_path, "test": csv_path}
cache_dir = tmp_path / "cache"
# CSV file loses col_1 string dtype information: default now is "int64" instead of "string"
default_expected_features = {
"col_1": "int64",
"col_2": "int64",
"col_3": "float64"
}
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 = DatasetDict.from_csv(path,
features=features,
cache_dir=cache_dir,
keep_in_memory=keep_in_memory)
assert isinstance(dataset, DatasetDict)
dataset = dataset[split]
assert dataset.num_rows == 4
assert dataset.num_columns == 3
assert dataset.column_names == ["col_1", "col_2", "col_3"]
assert dataset.split == split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
def test_datasetdict_from_json(
split,
features,
keep_in_memory,
jsonl_path,
tmp_path,
):
file_path = jsonl_path
field = None
if split:
path = {split: file_path}
else:
split = "train"
path = {"train": file_path, "test": file_path}
cache_dir = tmp_path / "cache"
default_expected_features = {"col_1": "string", "col_2": "int64", "col_3": "float64"}
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 = DatasetDict.from_json(
path, features=features, cache_dir=cache_dir, keep_in_memory=keep_in_memory, field=field
)
assert isinstance(dataset, DatasetDict)
dataset = dataset[split]
assert dataset.num_rows == 4
assert dataset.num_columns == 3
assert dataset.column_names == ["col_1", "col_2", "col_3"]
assert dataset.split == split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
def test_json_dataset_reader(
path_type,
split,
features,
keep_in_memory,
jsonl_path,
tmp_path,
):
file_path = jsonl_path
field = None
if issubclass(path_type, str):
path = file_path
elif issubclass(path_type, list):
path = [file_path]
cache_dir = tmp_path / "cache"
expected_split = str(split) if split else "train"
default_expected_features = {
"col_1": "string",
"col_2": "int64",
"col_3": "float64"
}
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 = JsonDatasetReader(path,
split=split,
features=features,
cache_dir=cache_dir,
keep_in_memory=keep_in_memory,
field=field).read()
assert isinstance(dataset, Dataset)
assert dataset.num_rows == 4
assert dataset.num_columns == 3
assert dataset.column_names == ["col_1", "col_2", "col_3"]
assert dataset.split == expected_split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
def test_csv_datasetdict_reader(split, features, keep_in_memory, csv_path,
tmp_path):
if split:
path = {split: csv_path}
else:
split = "train"
path = {"train": csv_path, "test": csv_path}
cache_dir = tmp_path / "cache"
# CSV file loses col_1 string dtype information: default now is "int64" instead of "string"
default_expected_features = {
"col_1": "int64",
"col_2": "int64",
"col_3": "float64"
}
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
previous_allocated_memory = pa.total_allocated_bytes()
dataset = CsvDatasetReader(path,
features=features,
cache_dir=cache_dir,
keep_in_memory=keep_in_memory).read()
increased_allocated_memory = (pa.total_allocated_bytes() -
previous_allocated_memory) > 0
assert isinstance(dataset, DatasetDict)
dataset = dataset[split]
assert dataset.num_rows == 4
assert dataset.num_columns == 3
assert dataset.column_names == ["col_1", "col_2", "col_3"]
assert dataset.split == split
for feature, expected_dtype in expected_features.items():
assert dataset.features[feature].dtype == expected_dtype
assert increased_allocated_memory == keep_in_memory
