def load_dataset(dataset, datasets_path=None, bucket=None):
dataset_path = _get_dataset_path(dataset, datasets_path, bucket)
metadata = Metadata(str(dataset_path / 'metadata.json'))
tables = metadata.get_tables()
if not hasattr(metadata, 'modality'):
if len(tables) > 1:
modality = 'multi-table'
else:
table = metadata.get_table_meta(tables[0])
if any(table.get(field) for field in TIMESERIES_FIELDS):
modality = 'timeseries'
else:
modality = 'single-table'
metadata._metadata['modality'] = modality
metadata.modality = modality
if not hasattr(metadata, 'name'):
metadata._metadata['name'] = dataset_path.name
metadata.name = dataset_path.name
return metadata
def load_dataset(dataset,
datasets_path=None,
bucket=None,
aws_key=None,
aws_secret=None,
max_columns=None):
dataset_path = _get_dataset_path(dataset, datasets_path, bucket, aws_key,
aws_secret)
with open(dataset_path / 'metadata.json') as metadata_file:
metadata_content = json.load(metadata_file)
if max_columns:
if len(metadata_content['tables']) > 1:
raise ValueError(
'max_columns is not supported for multi-table datasets')
_apply_max_columns_to_metadata(metadata_content, max_columns)
metadata = Metadata(metadata_content, dataset_path)
tables = metadata.get_tables()
if not hasattr(metadata, 'modality'):
if len(tables) > 1:
modality = 'multi-table'
else:
table = metadata.get_table_meta(tables[0])
if any(table.get(field) for field in TIMESERIES_FIELDS):
modality = 'timeseries'
else:
modality = 'single-table'
metadata._metadata['modality'] = modality
metadata.modality = modality
if not hasattr(metadata, 'name'):
metadata._metadata['name'] = dataset_path.name
metadata.name = dataset_path.name
return metadata