def test_from_json(resources_data_path):
json_path = str(resources_data_path / "dataset_sequence.jsonl")
ds = Dataset.from_json(paths=json_path)
ds2 = Dataset.from_json(paths=[json_path, json_path])
assert len(ds) == 4
assert len(ds2) == 8
json_path = str(resources_data_path / "dataset_sequence.json")
ds = Dataset.from_json(paths=json_path, field="data")
assert len(ds) == 4
def test_flatten_json(resources_data_path):
"""Showcases the behavior of Dataset.flatten_"""
file_path = str(resources_data_path / "to-be-flattened.jsonl")
dataset_flatten_source = Dataset.from_json(paths=file_path)
dataset_flatten_source.flatten_()
for c in ["complexData.a", "complexData.b"]:
assert c in dataset_flatten_source.column_names
file_path = str(resources_data_path / "nested-list.jsonl")
dataset_nested_list = Dataset.from_json(paths=file_path)
dataset_nested_list.flatten_()
assert len(dataset_nested_list) == 1
assert dataset_nested_list.column_names == ["classification"]
def dataset_from_path(path: str) -> Dataset:
file_extension = Path(path).suffix
if file_extension in [".csv"]:
return Dataset.from_csv(path)
elif file_extension in [".json", ".jsonl"]:
return Dataset.from_json(path)
else:
raise ValueError(
f"Could not create a Dataset from '{path}'. "
f"We only support following formats: [csv, json, jsonl]"
)
def dataset_from_path(path: str) -> Dataset:
file_extension = Path(path).suffix
if file_extension in [".csv"]:
return Dataset.from_csv(path)
elif file_extension in [".json", ".jsonl"]:
return Dataset.from_json(path)
# yaml files are used for elasticsearch data
elif file_extension in [".yaml", ".yml"]:
from_es_kwargs = yaml_to_dict(path)
client = Elasticsearch(**from_es_kwargs["client"])
return Dataset.from_elasticsearch(
client=client,
index=from_es_kwargs["index"],
query=from_es_kwargs.get("query"),
)
else:
raise ValueError(f"Could not create a Dataset from '{path}'")
