path	# lines of code	# active days	days since first update	days since last update	# commits	# contributors	first updated	last updated	first contributor	last contributor
utils/release.py	62	3	1478	726	3	3	2021-06-14	2023-07-06	8515462+albertvillanova@users.noreply.github.com	mariosasko777@gmail.com
benchmarks/benchmark_indices_mapping.py	41	4	1769	1478	5	2	2020-08-27	2021-06-14	thomwolf@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
benchmarks/benchmark_iterating.py	79	3	1769	1478	4	2	2020-08-27	2021-06-14	thomwolf@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
benchmarks/benchmark_map_filter.py	42	3	1768	1478	4	2	2020-08-28	2021-06-14	thomwolf@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
benchmarks/benchmark_getitem_100B.py	53	2	1547	1478	2	2	2021-04-06	2021-06-14	42851186+lhoestq@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
benchmarks/format.py	34	6	1769	868	6	4	2020-08-27	2023-02-14	thomwolf@users.noreply.github.com	mariosasko777@gmail.com
benchmarks/utils.py	47	5	1769	1208	6	4	2020-08-27	2022-03-11	thomwolf@users.noreply.github.com	mariosasko777@gmail.com
benchmarks/benchmark_array_xd.py	108	4	1769	1478	5	2	2020-08-27	2021-06-14	thomwolf@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/iterable_dataset.py	2750	96	1469	6	105	37	2021-06-23	2025-06-25	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/io/abc.py	46	5	1572	797	5	5	2021-03-12	2023-04-26	8515462+albertvillanova@users.noreply.github.com	maddie.dawson@databricks.com
src/datasets/io/__init__.py	1	1	1572	1572	1	1	2021-03-12	2021-03-12	8515462+albertvillanova@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/io/csv.py	122	19	1572	476	19	8	2021-03-12	2024-03-12	8515462+albertvillanova@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/io/generator.py	52	8	1019	340	8	6	2022-09-16	2024-07-26	mariosasko777@gmail.com	piercus@users.noreply.github.com
src/datasets/io/text.py	53	6	1566	476	6	4	2021-03-18	2024-03-12	8515462+albertvillanova@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/io/parquet.py	103	19	1462	246	19	11	2021-06-30	2024-10-28	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/io/sql.py	101	8	1002	476	8	3	2022-10-03	2024-03-12	frederic.branchaud.charron@gmail.com	mariosasko777@gmail.com
src/datasets/io/json.py	148	25	1566	225	25	12	2021-03-18	2024-11-18	8515462+albertvillanova@users.noreply.github.com	varadhbhatnagar@rediffmail.com
src/datasets/io/spark.py	46	3	797	768	3	1	2023-04-26	2023-05-25	maddie.dawson@databricks.com	maddie.dawson@databricks.com
src/datasets/fingerprint.py	258	31	1755	118	32	15	2020-09-10	2025-03-05	thomwolf@users.noreply.github.com	cyyever@outlook.com
src/datasets/utils/_dataset_viewer.py	70	4	449	118	4	3	2024-04-08	2025-03-05	sylvain.lesage@huggingface.co	cyyever@outlook.com
src/datasets/utils/file_utils.py	807	105	1755	22	121	26	2020-09-10	2025-06-09	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/utils/extract.py	253	19	1454	118	21	8	2021-07-08	2025-03-05	8515462+albertvillanova@users.noreply.github.com	cyyever@outlook.com
src/datasets/utils/info_utils.py	67	9	1755	386	9	5	2020-09-10	2024-06-10	thomwolf@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/utils/__init__.py	11	21	1755	392	22	7	2020-09-10	2024-06-04	thomwolf@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/utils/resources/__init__.py	1	1	1527	1527	1	1	2021-04-26	2021-04-26	theo-m@users.noreply.github.com	theo-m@users.noreply.github.com
src/datasets/utils/resources/readme_structure.yaml	116	2	1513	1509	2	1	2021-05-10	2021-05-14	chhablani.gunjan@gmail.com	chhablani.gunjan@gmail.com
src/datasets/utils/stratify.py	46	3	1133	173	3	2	2022-05-25	2025-01-09	48522685+nandwalritik@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/utils/hub.py	9	9	965	315	9	4	2022-11-09	2024-08-20	8515462+albertvillanova@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/utils/typing.py	6	3	1572	118	3	2	2021-03-12	2025-03-05	8515462+albertvillanova@users.noreply.github.com	cyyever@outlook.com
src/datasets/utils/track.py	45	3	560	118	3	2	2023-12-19	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/utils/deprecation_utils.py	70	7	1588	970	7	5	2021-02-24	2022-11-04	33657802+sbrandeis@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/utils/py_utils.py	402	75	1755	22	79	19	2020-09-10	2025-06-09	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/utils/doc_utils.py	6	1	1495	1495	1	1	2021-05-28	2021-05-28	lewis.c.tunstall@gmail.com	lewis.c.tunstall@gmail.com
src/datasets/utils/filelock.py	8	17	1688	581	18	8	2020-11-16	2023-11-28	42851186+lhoestq@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/utils/_dill.py	334	7	581	15	8	4	2023-11-28	2025-06-16	mariosasko777@gmail.com	45557362+qgallouedec@users.noreply.github.com
src/datasets/utils/sharding.py	56	4	965	118	4	4	2022-11-09	2025-03-05	teven.lescao@gmail.com	cyyever@outlook.com
src/datasets/utils/experimental.py	12	2	748	487	2	2	2023-06-14	2024-03-01	ying.chen@databricks.com	42851186+lhoestq@users.noreply.github.com
src/datasets/utils/version.py	52	11	1755	935	11	8	2020-09-10	2022-12-09	thomwolf@users.noreply.github.com	59462357+stevhliu@users.noreply.github.com
src/datasets/utils/tqdm.py	40	2	587	487	2	2	2023-11-22	2024-03-01	mariosasko777@gmail.com	42851186+lhoestq@users.noreply.github.com
src/datasets/utils/logging.py	69	20	1755	22	21	7	2020-09-10	2025-06-09	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/utils/patching.py	65	9	1449	588	9	5	2021-07-13	2023-11-21	8515462+albertvillanova@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/utils/tf_utils.py	390	9	1121	118	9	6	2022-06-06	2025-03-05	rocketknight1@users.noreply.github.com	cyyever@outlook.com
src/datasets/utils/_filelock.py	30	4	586	118	4	3	2023-11-23	2025-03-05	mariosasko777@gmail.com	cyyever@outlook.com
src/datasets/utils/metadata.py	180	40	1527	118	44	16	2021-04-26	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/__init__.py	32	128	1755	14	215	13	2020-09-10	2025-06-17	lhoest.q@gmail.com	42851186+lhoestq@users.noreply.github.com
src/datasets/info.py	254	42	1755	6	45	16	2020-09-10	2025-06-25	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/search.py	393	41	1755	6	42	25	2020-09-10	2025-06-25	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/splits.py	260	30	1755	118	32	13	2020-09-10	2025-03-05	thomwolf@users.noreply.github.com	cyyever@outlook.com
src/datasets/exceptions.py	61	7	630	118	7	3	2023-10-10	2025-03-05	8515462+albertvillanova@users.noreply.github.com	cyyever@outlook.com
src/datasets/dataset_dict.py	1075	134	1755	6	151	42	2020-09-10	2025-06-25	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/commands/__init__.py	10	2	1755	1513	2	2	2020-09-10	2021-05-10	thomwolf@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/commands/delete_from_hub.py	35	1	427	427	1	1	2024-04-30	2024-04-30	8515462+albertvillanova@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/commands/datasets_cli.py	25	8	1586	22	8	3	2021-02-26	2025-06-09	mariosasko777@gmail.com	42851186+lhoestq@users.noreply.github.com
src/datasets/commands/env.py	31	7	1755	614	7	5	2020-09-10	2023-10-26	thomwolf@users.noreply.github.com	mariosasko777@gmail.com
src/datasets/builder.py	1185	144	1755	6	165	33	2020-09-10	2025-06-25	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/formatting/__init__.py	84	17	1607	64	17	8	2021-02-05	2025-04-28	42851186+lhoestq@users.noreply.github.com	35225576+afuetterer@users.noreply.github.com
src/datasets/formatting/np_formatter.py	79	8	995	12	9	5	2022-10-10	2025-06-19	42851186+lhoestq@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/formatting/tf_formatter.py	83	14	1607	12	14	7	2021-02-05	2025-06-19	42851186+lhoestq@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/formatting/torch_formatter.py	82	14	1607	12	14	8	2021-02-05	2025-06-19	42851186+lhoestq@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/formatting/jax_formatter.py	116	13	1471	12	14	8	2021-06-21	2025-06-19	42851186+lhoestq@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/formatting/formatting.py	464	39	1607	22	39	14	2021-02-05	2025-06-09	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/formatting/polars_formatter.py	88	2	480	152	2	2	2024-03-08	2025-01-30	psmyth1994@gmail.com	42851186+lhoestq@users.noreply.github.com
src/datasets/hub.py	100	4	427	22	4	2	2024-04-30	2025-06-09	8515462+albertvillanova@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/combine.py	90	23	1469	118	24	12	2021-06-23	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/streaming.py	83	37	1469	22	41	7	2021-06-23	2025-06-09	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/features/audio.py	163	43	1357	12	44	12	2021-10-13	2025-06-19	8515462+albertvillanova@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/features/__init__.py	24	10	1357	6	10	5	2021-10-13	2025-06-25	8515462+albertvillanova@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/features/pdf.py	141	6	105	14	7	4	2025-03-18	2025-06-17	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/features/features.py	1354	91	1357	6	107	32	2021-10-13	2025-06-25	8515462+albertvillanova@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/features/translation.py	52	14	1357	6	14	9	2021-10-13	2025-06-25	8515462+albertvillanova@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/features/video.py	186	8	250	12	11	5	2024-10-24	2025-06-19	42851186+lhoestq@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/features/_torchcodec.py	13	1	12	12	1	1	2025-06-19	2025-06-19	49127578+tytodd@users.noreply.github.com	49127578+tytodd@users.noreply.github.com
src/datasets/features/image.py	250	33	1303	12	34	10	2021-12-06	2025-06-19	mario@huggingface.co	49127578+tytodd@users.noreply.github.com
src/datasets/inspect.py	149	45	1755	22	51	14	2020-09-10	2025-06-09	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/data_files.py	470	58	1359	50	63	17	2021-10-11	2025-05-12	42851186+lhoestq@users.noreply.github.com	matthew@protopia.ai
src/datasets/config.py	176	69	1602	6	76	20	2021-02-10	2025-06-25	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/arrow_writer.py	469	72	1755	64	75	26	2020-09-10	2025-04-28	thomwolf@users.noreply.github.com	35225576+afuetterer@users.noreply.github.com
src/datasets/keyhash.py	38	5	1513	55	5	5	2021-05-10	2025-05-07	nikhilbartwal1234@gmail.com	73196164+giraffacarp@users.noreply.github.com
src/datasets/naming.py	47	11	1755	487	11	8	2020-09-10	2024-03-01	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/parallel/parallel.py	65	2	748	442	2	2	2023-06-14	2024-04-15	ying.chen@databricks.com	42851186+lhoestq@users.noreply.github.com
src/datasets/parallel/__init__.py	1	2	748	392	2	2	2023-06-14	2024-06-04	ying.chen@databricks.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/arrow_reader.py	309	34	1755	95	34	16	2020-09-10	2025-03-28	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/csv/__init__.py	1	1	1624	1624	1	1	2021-01-19	2021-01-19	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/csv/csv.py	164	27	1624	118	28	10	2021-01-19	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/packaged_modules/arrow/__init__.py	1	1	749	749	1	1	2023-06-13	2023-06-13	mariusz.jachimowicz.83@gmail.com	mariusz.jachimowicz.83@gmail.com
src/datasets/packaged_modules/arrow/arrow.py	56	6	749	173	6	5	2023-06-13	2025-01-09	mariusz.jachimowicz.83@gmail.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/sql/__init__.py	1	1	1002	1002	1	1	2022-10-03	2022-10-03	frederic.branchaud.charron@gmail.com	frederic.branchaud.charron@gmail.com
src/datasets/packaged_modules/sql/sql.py	92	5	1002	118	5	5	2022-10-03	2025-03-05	frederic.branchaud.charron@gmail.com	cyyever@outlook.com
src/datasets/packaged_modules/generator/__init__.py	1	1	1019	1019	1	1	2022-09-16	2022-09-16	mariosasko777@gmail.com	mariosasko777@gmail.com
src/datasets/packaged_modules/generator/generator.py	23	5	1019	118	5	5	2022-09-16	2025-03-05	mariosasko777@gmail.com	cyyever@outlook.com
src/datasets/packaged_modules/pandas/pandas.py	47	9	1624	390	9	5	2021-01-19	2024-06-06	42851186+lhoestq@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/packaged_modules/pandas/__init__.py	1	1	1624	1624	1	1	2021-01-19	2021-01-19	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/text/__init__.py	1	1	1624	1624	1	1	2021-01-19	2021-01-19	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/text/text.py	83	19	1624	314	19	5	2021-01-19	2024-08-21	42851186+lhoestq@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/packaged_modules/__init__.py	85	28	1624	105	30	13	2021-01-19	2025-03-18	42851186+lhoestq@users.noreply.github.com	yabran.muvdi@gmail.com
src/datasets/packaged_modules/webdataset/webdataset.py	263	12	581	118	13	4	2023-11-28	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/packaged_modules/webdataset/__init__.py	1	1	581	581	1	1	2023-11-28	2023-11-28	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/webdataset/_tenbin.py	167	1	581	581	1	1	2023-11-28	2023-11-28	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/spark/__init__.py	1	1	797	797	1	1	2023-04-26	2023-04-26	maddie.dawson@databricks.com	maddie.dawson@databricks.com
src/datasets/packaged_modules/spark/spark.py	289	9	797	118	10	5	2023-04-26	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/packaged_modules/json/__init__.py	1	1	1624	1624	1	1	2021-01-19	2021-01-19	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/json/json.py	141	31	1624	377	32	7	2021-01-19	2024-06-19	42851186+lhoestq@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/packaged_modules/videofolder/__init__.py	1	1	250	250	1	1	2024-10-24	2024-10-24	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/videofolder/videofolder.py	21	2	250	118	2	2	2024-10-24	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/packaged_modules/audiofolder/__init__.py	1	1	1044	1044	1	1	2022-08-22	2022-08-22	polina@huggingface.co	polina@huggingface.co
src/datasets/packaged_modules/audiofolder/audiofolder.py	61	8	1044	12	8	5	2022-08-22	2025-06-19	polina@huggingface.co	49127578+tytodd@users.noreply.github.com
src/datasets/packaged_modules/pdffolder/pdffolder.py	13	1	105	105	1	1	2025-03-18	2025-03-18	yabran.muvdi@gmail.com	yabran.muvdi@gmail.com
src/datasets/packaged_modules/pdffolder/__init__.py	1	1	105	105	1	1	2025-03-18	2025-03-18	yabran.muvdi@gmail.com	yabran.muvdi@gmail.com
src/datasets/packaged_modules/imagefolder/__init__.py	1	1	1218	1218	1	1	2022-03-01	2022-03-01	nxr9266@g.rit.edu	nxr9266@g.rit.edu
src/datasets/packaged_modules/imagefolder/imagefolder.py	77	13	1218	118	14	6	2022-03-01	2025-03-05	nxr9266@g.rit.edu	cyyever@outlook.com
src/datasets/packaged_modules/xml/__init__.py	1	1	250	250	1	1	2024-10-24	2024-10-24	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/xml/xml.py	46	1	250	250	1	1	2024-10-24	2024-10-24	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/parquet/__init__.py	1	2	1462	1446	2	2	2021-06-30	2021-07-16	42851186+lhoestq@users.noreply.github.com	stevhliu@gmail.com
src/datasets/packaged_modules/parquet/parquet.py	86	19	1462	118	19	8	2021-06-30	2025-03-05	42851186+lhoestq@users.noreply.github.com	cyyever@outlook.com
src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py	347	19	1044	6	20	8	2022-08-22	2025-06-25	polina@huggingface.co	42851186+lhoestq@users.noreply.github.com
src/datasets/packaged_modules/folder_based_builder/__init__.py	1	1	1044	1044	1	1	2022-08-22	2022-08-22	polina@huggingface.co	polina@huggingface.co
src/datasets/table.py	942	63	1558	6	72	21	2021-03-26	2025-06-25	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/distributed.py	9	2	897	249	2	1	2023-01-16	2024-10-25	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/download/download_manager.py	172	23	1133	118	24	7	2022-05-25	2025-03-05	8515462+albertvillanova@users.noreply.github.com	cyyever@outlook.com
src/datasets/download/__init__.py	9	1	1133	1133	1	1	2022-05-25	2022-05-25	8515462+albertvillanova@users.noreply.github.com	8515462+albertvillanova@users.noreply.github.com
src/datasets/download/streaming_download_manager.py	106	36	1133	118	42	9	2022-05-25	2025-03-05	8515462+albertvillanova@users.noreply.github.com	cyyever@outlook.com
src/datasets/download/download_config.py	33	15	1133	64	17	9	2022-05-25	2025-04-28	8515462+albertvillanova@users.noreply.github.com	35225576+afuetterer@users.noreply.github.com
src/datasets/filesystems/__init__.py	26	18	1617	118	18	12	2021-01-26	2025-03-05	32632186+philschmid@users.noreply.github.com	cyyever@outlook.com
src/datasets/filesystems/compression.py	80	9	1408	414	9	5	2021-08-23	2024-05-13	42851186+lhoestq@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
src/datasets/load.py	952	181	1755	6	217	46	2020-09-10	2025-06-25	thomwolf@users.noreply.github.com	42851186+lhoestq@users.noreply.github.com
pyproject.toml	23	9	988	368	9	5	2022-10-17	2024-06-28	mariosasko777@gmail.com	8515462+albertvillanova@users.noreply.github.com
setup.py	131	278	1904	12	437	57	2020-04-14	2025-06-19	thomwolf@users.noreply.github.com	49127578+tytodd@users.noreply.github.com