>>> import fsspec
>>> fs = fsspec.filesystem("...")  # s3 / gcs / abfs / adl / oci / ...
>>> data_dir = "path/to/my/data/"
>>> pattern = "*.parquet"
>>> data_files = fs.glob(data_dir + pattern)
["path/to/my/data/0001.parquet", "path/to/my/data/0001.parquet", ...]

>>> from huggingface_hub import create_repo, upload_folder
>>> from tqdm.auto import tqdm
>>> destination_dataset = "username/my-dataset"
>>> create_repo(destination_dataset, repo_type="dataset")
>>> batch_size = 100
>>> for data_files in batched(tqdm(fs.glob(data_dir + pattern)), batch_size):
...     with TemporaryDirectory() as tmp_dir:
...         tmp_files = [os.path.join(tmp_dir, x[len(data_dir):]) for x in data_files]
...         fs.download(data_files, tmp_files)
...         upload_folder(
...             repo_id=destination_dataset,
...             folder_path=tmp_dir,
...             repo_type="dataset",
...         )

>>> from datasets import load_dataset
>>> ds = load_dataset("username/my-dataset")

>>> from huggingface_hub import create_bucket, sync_bucket
>>> from tqdm.auto import tqdm
>>> from itertools import batched
>>> from tempfile import TemporaryDirectory
>>> import os
>>> create_bucket("username/my-bucket")
>>> bucket_files_location = "hf://buckets/username/my-bucket/path/to/raw/files"
>>> batch_size = 100
>>> for data_files in batched(tqdm(fs.glob(data_dir + pattern)), batch_size):
...     with TemporaryDirectory() as tmp_dir:
...         tmp_files = [os.path.join(tmp_dir, x[len(data_dir):]) for x in data_files]
...         fs.download(data_files, tmp_files)
...         sync_bucket(tmp_dir, bucket_files_location)

>>> from datasets import load_dataset
>>> ds = load_dataset(bucket_files_location, streaming=True)
>>> ds = ds.map(...).filter(...)
>>> ds.push_to_hub("username/my-dataset", num_proc=4)
>>> # and later
>>> ds = load_dataset("username/my-dataset")

>>> from datasets import IterableDataset
>>> from huggingface_hub import hffs
>>> data_files = hffs.find(bucket_files_location)
>>> num_shards = 1024  # For parallelism. PS: every shard should fit in RAM
>>> ds = IterableDataset.from_dict({"data_file": data_files}, num_shards=num_shards)
>>> def parse_data_files(data_files):
...     ...
...     return {"col_1": [...], "col_2": [...]}
>>> ds = ds.map(parse_data_files, batched=True, input_column=["data_file"])
>>> ds.push_to_hub("username/my-dataset", num_proc=4)
>>> # and later
>>> ds = load_dataset("username/my-dataset")