def test_datasetdict_from_text(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 = DatasetDict.from_text(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 == 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_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 = DatasetDict.from_text({"train": text_path}, cache_dir=cache_dir, keep_in_memory=keep_in_memory) _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 = DatasetDict.from_text(path, cache_dir=cache_dir) _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_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 = DatasetDict.from_text({"train": text_path}, features=features, cache_dir=cache_dir) _check_text_datasetdict(dataset, expected_features)