duplicated block id: 1
size: 137 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1774:1920)
 - src/datasets/dataset_dict.py (2590:2736)

duplicated block id: 2
size: 56 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1440:1506)
 - src/datasets/builder.py (1695:1761)

duplicated block id: 3
size: 42 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1619:1756)
 - src/datasets/dataset_dict.py (2445:2572)

duplicated block id: 4
size: 38 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (240:290)
 - src/datasets/features/pdf.py (207:257)

duplicated block id: 5
size: 38 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1882:1920)
 - src/datasets/iterable_dataset.py (4225:4263)

duplicated block id: 6
size: 38 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2698:2736)
 - src/datasets/iterable_dataset.py (4225:4263)

duplicated block id: 7
size: 36 cleaned lines of code
in 2 files:
 - src/datasets/features/image.py (196:253)
 - src/datasets/features/video.py (224:281)

duplicated block id: 8
size: 28 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (250:290)
 - src/datasets/features/image.py (253:293)

duplicated block id: 9
size: 28 cleaned lines of code
in 2 files:
 - src/datasets/features/image.py (253:293)
 - src/datasets/features/pdf.py (217:257)

duplicated block id: 10
size: 25 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1409:1437)
 - src/datasets/builder.py (1666:1694)

duplicated block id: 11
size: 25 cleaned lines of code
in 2 files:
 - src/datasets/features/pdf.py (173:216)
 - src/datasets/features/video.py (228:271)

duplicated block id: 12
size: 25 cleaned lines of code
in 2 files:
 - src/datasets/download/streaming_download_manager.py (15:44)
 - src/datasets/streaming.py (7:35)

duplicated block id: 13
size: 25 cleaned lines of code
in 2 files:
 - src/datasets/features/image.py (200:243)
 - src/datasets/features/pdf.py (173:216)

duplicated block id: 14
size: 24 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (39:66)
 - src/datasets/io/text.py (33:60)

duplicated block id: 15
size: 23 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/text/text.py (31:62)
 - src/datasets/packaged_modules/xml/xml.py (27:58)

duplicated block id: 16
size: 22 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (16:37)
 - src/datasets/io/text.py (10:31)

duplicated block id: 17
size: 22 cleaned lines of code
in 2 files:
 - src/datasets/io/parquet.py (18:39)
 - src/datasets/io/text.py (10:31)

duplicated block id: 18
size: 22 cleaned lines of code
in 2 files:
 - src/datasets/combine.py (124:145)
 - src/datasets/combine.py (190:211)

duplicated block id: 19
size: 22 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (16:37)
 - src/datasets/io/parquet.py (18:39)

duplicated block id: 20
size: 21 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (45:69)
 - src/datasets/io/text.py (36:60)

duplicated block id: 21
size: 21 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (42:66)
 - src/datasets/io/json.py (45:69)

duplicated block id: 22
size: 21 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (42:66)
 - src/datasets/io/parquet.py (46:70)

duplicated block id: 23
size: 21 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (273:293)
 - src/datasets/utils/_dill.py (442:462)

duplicated block id: 24
size: 21 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (45:69)
 - src/datasets/io/parquet.py (46:70)

duplicated block id: 25
size: 21 cleaned lines of code
in 2 files:
 - src/datasets/io/parquet.py (46:70)
 - src/datasets/io/text.py (36:60)

duplicated block id: 26
size: 20 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1589:1612)
 - src/datasets/iterable_dataset.py (1713:1736)

duplicated block id: 27
size: 18 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py (314:333)
 - src/datasets/packaged_modules/json/json.py (135:154)

duplicated block id: 28
size: 18 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (323:341)
 - src/datasets/iterable_dataset.py (395:413)

duplicated block id: 29
size: 18 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (148:168)
 - src/datasets/packaged_modules/text/text.py (31:55)

duplicated block id: 30
size: 18 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (279:296)
 - src/datasets/utils/_dill.py (430:447)

duplicated block id: 31
size: 18 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (148:168)
 - src/datasets/packaged_modules/xml/xml.py (27:51)

duplicated block id: 32
size: 17 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (361:377)
 - src/datasets/utils/_dill.py (385:401)

duplicated block id: 33
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2659:2674)
 - src/datasets/iterable_dataset.py (4192:4207)

duplicated block id: 34
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/json/json.py (71:88)
 - src/datasets/packaged_modules/text/text.py (32:53)

duplicated block id: 35
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/json/json.py (71:88)
 - src/datasets/packaged_modules/xml/xml.py (28:49)

duplicated block id: 36
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1843:1858)
 - src/datasets/iterable_dataset.py (4192:4207)

duplicated block id: 37
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (430:444)
 - src/datasets/utils/_dill.py (448:462)

duplicated block id: 38
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1588:1603)
 - src/datasets/builder.py (1840:1855)

duplicated block id: 39
size: 15 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (149:166)
 - src/datasets/packaged_modules/json/json.py (71:88)

duplicated block id: 40
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (361:374)
 - src/datasets/utils/_dill.py (407:420)

duplicated block id: 41
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2912:2925)
 - src/datasets/iterable_dataset.py (2992:3005)

duplicated block id: 42
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/arrow/arrow.py (28:45)
 - src/datasets/packaged_modules/parquet/parquet.py (42:59)

duplicated block id: 43
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2679:2693)
 - src/datasets/iterable_dataset.py (4209:4223)

duplicated block id: 44
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (297:310)
 - src/datasets/utils/_dill.py (431:444)

duplicated block id: 45
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (297:310)
 - src/datasets/utils/_dill.py (449:462)

duplicated block id: 46
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (258:271)
 - src/datasets/utils/_dill.py (427:440)

duplicated block id: 47
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1863:1877)
 - src/datasets/iterable_dataset.py (4209:4223)

duplicated block id: 48
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (385:398)
 - src/datasets/utils/_dill.py (407:420)

duplicated block id: 49
size: 14 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (280:293)
 - src/datasets/utils/_dill.py (297:310)

duplicated block id: 50
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (259:271)
 - src/datasets/utils/_dill.py (409:421)

duplicated block id: 51
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (50:63)
 - src/datasets/io/generator.py (43:56)

duplicated block id: 52
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/formatting/tf_formatter.py (96:111)
 - src/datasets/formatting/torch_formatter.py (97:112)

duplicated block id: 53
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (141:156)
 - src/datasets/formatting/tf_formatter.py (96:111)

duplicated block id: 54
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (43:56)
 - src/datasets/io/json.py (53:66)

duplicated block id: 55
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (580:592)
 - src/datasets/data_files.py (739:751)

duplicated block id: 56
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (43:56)
 - src/datasets/io/parquet.py (54:67)

duplicated block id: 57
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (141:156)
 - src/datasets/formatting/torch_formatter.py (97:112)

duplicated block id: 58
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (24:36)
 - src/datasets/io/json.py (25:37)

duplicated block id: 59
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (25:37)
 - src/datasets/io/text.py (18:30)

duplicated block id: 60
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (43:56)
 - src/datasets/io/text.py (44:57)

duplicated block id: 61
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (409:421)
 - src/datasets/utils/_dill.py (428:440)

duplicated block id: 62
size: 13 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (25:37)
 - src/datasets/io/parquet.py (26:38)

duplicated block id: 63
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (344:355)
 - src/datasets/iterable_dataset.py (420:431)

duplicated block id: 64
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (259:270)
 - src/datasets/utils/_dill.py (363:374)

duplicated block id: 65
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (259:270)
 - src/datasets/utils/_dill.py (387:398)

duplicated block id: 66
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1727:1741)
 - src/datasets/iterable_dataset.py (4039:4053)

duplicated block id: 67
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/arrow/arrow.py (27:41)
 - src/datasets/packaged_modules/text/text.py (31:48)

duplicated block id: 68
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/formatting/np_formatter.py (105:117)
 - src/datasets/formatting/tf_formatter.py (114:126)

duplicated block id: 69
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/arrow/arrow.py (27:41)
 - src/datasets/packaged_modules/csv/csv.py (148:161)

duplicated block id: 70
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2543:2557)
 - src/datasets/iterable_dataset.py (4039:4053)

duplicated block id: 71
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1524:1538)
 - src/datasets/builder.py (1779:1793)

duplicated block id: 72
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/formatting/tf_formatter.py (114:126)
 - src/datasets/formatting/torch_formatter.py (115:127)

duplicated block id: 73
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (159:171)
 - src/datasets/formatting/tf_formatter.py (114:126)

duplicated block id: 74
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1606:1617)
 - src/datasets/dataset_dict.py (2432:2443)

duplicated block id: 75
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (159:171)
 - src/datasets/formatting/np_formatter.py (105:117)

duplicated block id: 76
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (387:398)
 - src/datasets/utils/_dill.py (428:439)

duplicated block id: 77
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (159:171)
 - src/datasets/formatting/torch_formatter.py (115:127)

duplicated block id: 78
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/arrow/arrow.py (27:41)
 - src/datasets/packaged_modules/xml/xml.py (27:44)

duplicated block id: 79
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/formatting/np_formatter.py (105:117)
 - src/datasets/formatting/torch_formatter.py (115:127)

duplicated block id: 80
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1380:1391)
 - src/datasets/iterable_dataset.py (1397:1408)

duplicated block id: 81
size: 12 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (363:374)
 - src/datasets/utils/_dill.py (428:439)

duplicated block id: 82
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/parquet/parquet.py (42:55)
 - src/datasets/packaged_modules/text/text.py (32:48)

duplicated block id: 83
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/load.py (472:483)
 - src/datasets/load.py (680:691)

duplicated block id: 84
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/json/json.py (71:83)
 - src/datasets/packaged_modules/parquet/parquet.py (42:55)

duplicated block id: 85
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/load.py (697:707)
 - src/datasets/load.py (771:781)

duplicated block id: 86
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1549:1560)
 - src/datasets/builder.py (1798:1809)

duplicated block id: 87
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1569:1579)
 - src/datasets/builder.py (1816:1826)

duplicated block id: 88
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/load.py (968:978)
 - src/datasets/load.py (1005:1015)

duplicated block id: 89
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (149:161)
 - src/datasets/packaged_modules/parquet/parquet.py (42:55)

duplicated block id: 90
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (632:642)
 - src/datasets/data_files.py (678:688)

duplicated block id: 91
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (261:271)
 - src/datasets/utils/_dill.py (448:458)

duplicated block id: 92
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (244:254)
 - src/datasets/utils/_dill.py (343:353)

duplicated block id: 93
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/load.py (443:453)
 - src/datasets/load.py (642:652)

duplicated block id: 94
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (261:271)
 - src/datasets/utils/_dill.py (279:289)

duplicated block id: 95
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/parquet/parquet.py (42:55)
 - src/datasets/packaged_modules/xml/xml.py (28:44)

duplicated block id: 96
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/utils/tf_utils.py (266:276)
 - src/datasets/utils/tf_utils.py (504:514)

duplicated block id: 97
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (279:289)
 - src/datasets/utils/_dill.py (411:421)

duplicated block id: 98
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/arrow/arrow.py (28:41)
 - src/datasets/packaged_modules/json/json.py (71:83)

duplicated block id: 99
size: 11 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (411:421)
 - src/datasets/utils/_dill.py (448:458)

duplicated block id: 100
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (589:601)
 - src/datasets/iterable_dataset.py (631:643)

duplicated block id: 101
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (365:374)
 - src/datasets/utils/_dill.py (448:457)

duplicated block id: 102
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (262:271)
 - src/datasets/utils/_dill.py (297:306)

duplicated block id: 103
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (389:398)
 - src/datasets/utils/_dill.py (448:457)

duplicated block id: 104
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/load.py (454:463)
 - src/datasets/load.py (654:663)

duplicated block id: 105
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/formatting/formatting.py (241:250)
 - src/datasets/formatting/polars_formatter.py (73:82)

duplicated block id: 106
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (297:306)
 - src/datasets/utils/_dill.py (412:421)

duplicated block id: 107
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (240:249)
 - src/datasets/features/video.py (262:271)

duplicated block id: 108
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (279:288)
 - src/datasets/utils/_dill.py (389:398)

duplicated block id: 109
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (279:288)
 - src/datasets/utils/_dill.py (365:374)

duplicated block id: 110
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3300:3309)
 - src/datasets/iterable_dataset.py (3424:3433)

duplicated block id: 111
size: 10 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (240:249)
 - src/datasets/features/image.py (234:243)

duplicated block id: 112
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/pandas/pandas.py (45:55)
 - src/datasets/packaged_modules/text/text.py (44:53)

duplicated block id: 113
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2997:3005)
 - src/datasets/iterable_dataset.py (3406:3414)

duplicated block id: 114
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (785:795)
 - src/datasets/iterable_dataset.py (873:884)

duplicated block id: 115
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2252:2260)
 - src/datasets/iterable_dataset.py (2351:2359)

duplicated block id: 116
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/io/parquet.py (55:64)
 - src/datasets/io/sql.py (37:46)

duplicated block id: 117
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (161:169)
 - src/datasets/inspect.py (220:228)

duplicated block id: 118
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2917:2925)
 - src/datasets/iterable_dataset.py (3054:3062)

duplicated block id: 119
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/utils/tf_utils.py (119:127)
 - src/datasets/utils/tf_utils.py (266:274)

duplicated block id: 120
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2997:3005)
 - src/datasets/iterable_dataset.py (3054:3062)

duplicated block id: 121
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (2102:2110)
 - src/datasets/features/features.py (2128:2136)

duplicated block id: 122
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3254:3262)
 - src/datasets/iterable_dataset.py (3301:3309)

duplicated block id: 123
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2917:2925)
 - src/datasets/iterable_dataset.py (3406:3414)

duplicated block id: 124
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/json/json.py (79:88)
 - src/datasets/packaged_modules/pandas/pandas.py (45:55)

duplicated block id: 125
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (157:166)
 - src/datasets/packaged_modules/pandas/pandas.py (45:55)

duplicated block id: 126
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3254:3262)
 - src/datasets/iterable_dataset.py (3425:3433)

duplicated block id: 127
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (297:305)
 - src/datasets/utils/_dill.py (390:398)

duplicated block id: 128
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (297:305)
 - src/datasets/utils/_dill.py (366:374)

duplicated block id: 129
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (44:53)
 - src/datasets/io/sql.py (37:46)

duplicated block id: 130
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (634:642)
 - src/datasets/data_files.py (657:665)

duplicated block id: 131
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/io/sql.py (37:46)
 - src/datasets/io/text.py (45:54)

duplicated block id: 132
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3054:3062)
 - src/datasets/iterable_dataset.py (3406:3414)

duplicated block id: 133
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (54:63)
 - src/datasets/io/sql.py (37:46)

duplicated block id: 134
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (657:665)
 - src/datasets/data_files.py (680:688)

duplicated block id: 135
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/utils/tf_utils.py (119:127)
 - src/datasets/utils/tf_utils.py (504:512)

duplicated block id: 136
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (104:118)
 - src/datasets/formatting/tf_formatter.py (68:82)

duplicated block id: 137
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (447:455)
 - src/datasets/builder.py (494:502)

duplicated block id: 138
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (78:87)
 - src/datasets/io/json.py (81:90)

duplicated block id: 139
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/pandas/pandas.py (45:55)
 - src/datasets/packaged_modules/xml/xml.py (40:49)

duplicated block id: 140
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (177:186)
 - src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py (282:291)

duplicated block id: 141
size: 9 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (51:60)
 - src/datasets/io/sql.py (37:46)

duplicated block id: 142
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (81:94)
 - src/datasets/formatting/torch_formatter.py (47:59)

duplicated block id: 143
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1625:1632)
 - src/datasets/iterable_dataset.py (1750:1757)

duplicated block id: 144
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1490:1497)
 - src/datasets/iterable_dataset.py (1503:1510)

duplicated block id: 145
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/search.py (458:465)
 - src/datasets/search.py (499:506)

duplicated block id: 146
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (147:156)
 - src/datasets/formatting/np_formatter.py (93:102)

duplicated block id: 147
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (238:245)
 - src/datasets/inspect.py (299:306)

duplicated block id: 148
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (12:19)
 - src/datasets/io/parquet.py (21:28)

duplicated block id: 149
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (16:23)
 - src/datasets/io/parquet.py (18:25)

duplicated block id: 150
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (451:461)
 - src/datasets/iterable_dataset.py (587:597)

duplicated block id: 151
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1791:1798)
 - src/datasets/iterable_dataset.py (4082:4089)

duplicated block id: 152
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (97:104)
 - src/datasets/inspect.py (345:352)

duplicated block id: 153
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/utils/track.py (28:36)
 - src/datasets/utils/track.py (50:58)

duplicated block id: 154
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/load.py (491:498)
 - src/datasets/load.py (774:781)

duplicated block id: 155
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/load.py (491:498)
 - src/datasets/load.py (700:707)

duplicated block id: 156
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (631:640)
 - src/datasets/iterable_dataset.py (1525:1534)

duplicated block id: 157
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (416:423)
 - src/datasets/dataset_dict.py (2275:2282)

duplicated block id: 158
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (12:19)
 - src/datasets/io/csv.py (19:26)

duplicated block id: 159
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (453:462)
 - src/datasets/iterable_dataset.py (1603:1612)

duplicated block id: 160
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1192:1199)
 - src/datasets/dataset_dict.py (1275:1282)

duplicated block id: 161
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2124:2131)
 - src/datasets/iterable_dataset.py (2727:2734)

duplicated block id: 162
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/formatting/np_formatter.py (93:102)
 - src/datasets/formatting/tf_formatter.py (102:111)

duplicated block id: 163
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (589:598)
 - src/datasets/iterable_dataset.py (1525:1534)

duplicated block id: 164
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/csv/csv.py (165:174)
 - src/datasets/packaged_modules/sql/sql.py (100:109)

duplicated block id: 165
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2607:2614)
 - src/datasets/iterable_dataset.py (4082:4089)

duplicated block id: 166
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (16:23)
 - src/datasets/io/json.py (16:23)

duplicated block id: 167
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/features/image.py (111:120)
 - src/datasets/features/video.py (123:132)

duplicated block id: 168
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (244:251)
 - src/datasets/iterable_dataset.py (287:294)

duplicated block id: 169
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (453:462)
 - src/datasets/iterable_dataset.py (1727:1736)

duplicated block id: 170
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/io/json.py (16:23)
 - src/datasets/io/text.py (10:17)

duplicated block id: 171
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2109:2116)
 - src/datasets/iterable_dataset.py (2704:2711)

duplicated block id: 172
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1032:1039)
 - src/datasets/iterable_dataset.py (1443:1450)

duplicated block id: 173
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (12:19)
 - src/datasets/io/text.py (13:20)

duplicated block id: 174
size: 8 cleaned lines of code
in 2 files:
 - src/datasets/formatting/np_formatter.py (93:102)
 - src/datasets/formatting/torch_formatter.py (103:112)

duplicated block id: 175
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1806:1812)
 - src/datasets/iterable_dataset.py (4096:4102)

duplicated block id: 176
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (644:650)
 - src/datasets/data_files.py (690:696)

duplicated block id: 177
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (631:639)
 - src/datasets/iterable_dataset.py (1603:1611)

duplicated block id: 178
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1525:1533)
 - src/datasets/iterable_dataset.py (1727:1735)

duplicated block id: 179
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (37:43)
 - src/datasets/io/text.py (14:20)

duplicated block id: 180
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2244:2250)
 - src/datasets/iterable_dataset.py (2330:2337)

duplicated block id: 181
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (631:639)
 - src/datasets/iterable_dataset.py (1727:1735)

duplicated block id: 182
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (186:193)
 - src/datasets/features/pdf.py (235:241)

duplicated block id: 183
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (453:461)
 - src/datasets/iterable_dataset.py (1525:1533)

duplicated block id: 184
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (453:461)
 - src/datasets/iterable_dataset.py (631:639)

duplicated block id: 185
size: 7 cleaned lines of code
in 2 files:
 - benchmarks/benchmark_getitem_100B.py (68:77)
 - benchmarks/benchmark_indices_mapping.py (50:59)

duplicated block id: 186
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (558:564)
 - src/datasets/data_files.py (571:577)

duplicated block id: 187
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1611:1617)
 - src/datasets/iterable_dataset.py (3915:3921)

duplicated block id: 188
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (186:193)
 - src/datasets/features/image.py (271:277)

duplicated block id: 189
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (941:948)
 - src/datasets/dataset_dict.py (2103:2110)

duplicated block id: 190
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (1676:1682)
 - src/datasets/features/features.py (1694:1700)

duplicated block id: 191
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (281:287)
 - src/datasets/iterable_dataset.py (414:420)

duplicated block id: 192
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (37:43)
 - src/datasets/io/csv.py (20:26)

duplicated block id: 193
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2719:2725)
 - src/datasets/iterable_dataset.py (3427:3433)

duplicated block id: 194
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (391:397)
 - src/datasets/iterable_dataset.py (416:422)

duplicated block id: 195
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (98:104)
 - src/datasets/inspect.py (271:277)

duplicated block id: 196
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/videofolder/videofolder.py (27:33)
 - src/datasets/packaged_modules/webdataset/webdataset.py (272:278)

duplicated block id: 197
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (645:652)
 - src/datasets/data_files.py (669:676)

duplicated block id: 198
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (1379:1385)
 - src/datasets/features/features.py (1391:1397)

duplicated block id: 199
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (30:36)
 - src/datasets/io/generator.py (22:28)

duplicated block id: 200
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (22:29)
 - src/datasets/io/abc.py (44:51)

duplicated block id: 201
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (273:282)
 - src/datasets/iterable_dataset.py (380:389)

duplicated block id: 202
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (271:277)
 - src/datasets/inspect.py (346:352)

duplicated block id: 203
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2719:2725)
 - src/datasets/iterable_dataset.py (3303:3309)

duplicated block id: 204
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2805:2811)
 - src/datasets/iterable_dataset.py (2962:2968)

duplicated block id: 205
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2719:2725)
 - src/datasets/iterable_dataset.py (3256:3262)

duplicated block id: 206
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (533:554)
 - src/datasets/dataset_dict.py (572:613)

duplicated block id: 207
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (589:597)
 - src/datasets/iterable_dataset.py (1603:1611)

duplicated block id: 208
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (684:692)
 - src/datasets/iterable_dataset.py (948:956)

duplicated block id: 209
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (22:28)
 - src/datasets/io/text.py (24:30)

duplicated block id: 210
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/features/image.py (172:178)
 - src/datasets/features/pdf.py (148:154)

duplicated block id: 211
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/csv.py (70:76)
 - src/datasets/io/json.py (73:79)

duplicated block id: 212
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (22:28)
 - src/datasets/io/parquet.py (32:38)

duplicated block id: 213
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (13:19)
 - src/datasets/io/abc.py (37:43)

duplicated block id: 214
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (186:193)
 - src/datasets/features/audio.py (268:274)

duplicated block id: 215
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1454:1461)
 - src/datasets/dataset_dict.py (1497:1504)

duplicated block id: 216
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1525:1533)
 - src/datasets/iterable_dataset.py (1603:1611)

duplicated block id: 217
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1766:1772)
 - src/datasets/dataset_dict.py (2582:2588)

duplicated block id: 218
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (589:597)
 - src/datasets/iterable_dataset.py (1727:1735)

duplicated block id: 219
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/abc.py (37:43)
 - src/datasets/io/parquet.py (22:28)

duplicated block id: 220
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1559:1565)
 - src/datasets/builder.py (1578:1584)

duplicated block id: 221
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2437:2443)
 - src/datasets/iterable_dataset.py (3915:3921)

duplicated block id: 222
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2622:2628)
 - src/datasets/iterable_dataset.py (4096:4102)

duplicated block id: 223
size: 7 cleaned lines of code
in 2 files:
 - src/datasets/io/generator.py (22:28)
 - src/datasets/io/json.py (31:37)

duplicated block id: 224
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/utils/py_utils.py (409:414)
 - src/datasets/utils/py_utils.py (546:551)

duplicated block id: 225
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2963:2968)
 - src/datasets/iterable_dataset.py (3257:3262)

duplicated block id: 226
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2963:2968)
 - src/datasets/iterable_dataset.py (3304:3309)

duplicated block id: 227
size: 6 cleaned lines of code
in 2 files:
 - benchmarks/benchmark_iterating.py (45:50)
 - benchmarks/benchmark_iterating.py (59:64)

duplicated block id: 228
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2720:2725)
 - src/datasets/iterable_dataset.py (3409:3414)

duplicated block id: 229
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3057:3062)
 - src/datasets/iterable_dataset.py (3304:3309)

duplicated block id: 230
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3057:3062)
 - src/datasets/iterable_dataset.py (3257:3262)

duplicated block id: 231
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3257:3262)
 - src/datasets/iterable_dataset.py (3409:3414)

duplicated block id: 232
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3057:3062)
 - src/datasets/iterable_dataset.py (3428:3433)

duplicated block id: 233
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/builder.py (1808:1813)
 - src/datasets/builder.py (1825:1830)

duplicated block id: 234
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (2920:2925)

duplicated block id: 235
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (232:237)
 - src/datasets/features/video.py (256:261)

duplicated block id: 236
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1497:1502)
 - src/datasets/dataset_dict.py (1589:1594)

duplicated block id: 237
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (3000:3005)

duplicated block id: 238
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (3057:3062)

duplicated block id: 239
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2920:2925)
 - src/datasets/iterable_dataset.py (3304:3309)

duplicated block id: 240
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2920:2925)
 - src/datasets/iterable_dataset.py (3257:3262)

duplicated block id: 241
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (313:318)
 - src/datasets/features/features.py (364:369)

duplicated block id: 242
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (313:318)
 - src/datasets/features/features.py (349:354)

duplicated block id: 243
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (110:115)
 - src/datasets/inspect.py (176:181)

duplicated block id: 244
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (17:22)
 - src/datasets/hub.py (5:10)

duplicated block id: 245
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/formatting/np_formatter.py (66:75)
 - src/datasets/formatting/torch_formatter.py (79:88)

duplicated block id: 246
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2920:2925)
 - src/datasets/iterable_dataset.py (3428:3433)

duplicated block id: 247
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/inspect.py (45:50)
 - src/datasets/inspect.py (302:307)

duplicated block id: 248
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (967:972)
 - src/datasets/iterable_dataset.py (978:983)

duplicated block id: 249
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (704:709)
 - src/datasets/iterable_dataset.py (989:994)

duplicated block id: 250
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py (272:277)
 - src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py (390:395)

duplicated block id: 251
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (109:118)
 - src/datasets/formatting/torch_formatter.py (79:88)

duplicated block id: 252
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (313:318)
 - src/datasets/features/features.py (334:339)

duplicated block id: 253
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2963:2968)
 - src/datasets/iterable_dataset.py (3057:3062)

duplicated block id: 254
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1890:1895)
 - src/datasets/dataset_dict.py (2725:2730)

duplicated block id: 255
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2963:2968)
 - src/datasets/iterable_dataset.py (3000:3005)

duplicated block id: 256
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/formatting/jax_formatter.py (109:118)
 - src/datasets/formatting/np_formatter.py (66:75)

duplicated block id: 257
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2725:2730)
 - src/datasets/iterable_dataset.py (4233:4238)

duplicated block id: 258
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1890:1895)
 - src/datasets/dataset_dict.py (1909:1914)

duplicated block id: 259
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3409:3414)
 - src/datasets/iterable_dataset.py (3428:3433)

duplicated block id: 260
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/utils/_dill.py (273:278)
 - src/datasets/utils/_dill.py (291:296)

duplicated block id: 261
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (4233:4238)
 - src/datasets/iterable_dataset.py (4252:4257)

duplicated block id: 262
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2679:2684)
 - src/datasets/iterable_dataset.py (2695:2700)

duplicated block id: 263
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (3409:3414)

duplicated block id: 264
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (3428:3433)

duplicated block id: 265
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3756:3761)
 - src/datasets/iterable_dataset.py (3825:3830)

duplicated block id: 266
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/data_files.py (669:674)
 - src/datasets/data_files.py (691:696)

duplicated block id: 267
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3304:3309)
 - src/datasets/iterable_dataset.py (3409:3414)

duplicated block id: 268
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1334:1339)
 - src/datasets/dataset_dict.py (1711:1716)

duplicated block id: 269
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2706:2711)
 - src/datasets/dataset_dict.py (2725:2730)

duplicated block id: 270
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/spark/spark.py (239:244)
 - src/datasets/packaged_modules/spark/spark.py (257:262)

duplicated block id: 271
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (1650:1655)
 - src/datasets/iterable_dataset.py (1775:1780)

duplicated block id: 272
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/video.py (197:202)
 - src/datasets/features/video.py (206:211)

duplicated block id: 273
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (349:354)
 - src/datasets/features/features.py (364:369)

duplicated block id: 274
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/arrow/arrow.py (53:62)
 - src/datasets/packaged_modules/parquet/parquet.py (67:76)

duplicated block id: 275
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1463:1468)
 - src/datasets/dataset_dict.py (1555:1560)

duplicated block id: 276
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3000:3005)
 - src/datasets/iterable_dataset.py (3428:3433)

duplicated block id: 277
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py (307:313)
 - src/datasets/packaged_modules/json/json.py (124:130)

duplicated block id: 278
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (334:339)
 - src/datasets/features/features.py (349:354)

duplicated block id: 279
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (878:884)
 - src/datasets/iterable_dataset.py (948:954)

duplicated block id: 280
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/formatting/np_formatter.py (66:75)
 - src/datasets/formatting/tf_formatter.py (73:82)

duplicated block id: 281
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (947:952)
 - src/datasets/dataset_dict.py (1064:1069)

duplicated block id: 282
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1454:1459)
 - src/datasets/dataset_dict.py (1589:1594)

duplicated block id: 283
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3000:3005)
 - src/datasets/iterable_dataset.py (3257:3262)

duplicated block id: 284
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (3000:3005)
 - src/datasets/iterable_dataset.py (3304:3309)

duplicated block id: 285
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/formatting/tf_formatter.py (73:82)
 - src/datasets/formatting/torch_formatter.py (79:88)

duplicated block id: 286
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1890:1895)
 - src/datasets/iterable_dataset.py (4252:4257)

duplicated block id: 287
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1759:1764)
 - src/datasets/dataset_dict.py (2575:2580)

duplicated block id: 288
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2720:2725)
 - src/datasets/iterable_dataset.py (2806:2811)

duplicated block id: 289
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1909:1914)
 - src/datasets/iterable_dataset.py (4233:4238)

duplicated block id: 290
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1420:1425)
 - src/datasets/dataset_dict.py (1555:1560)

duplicated block id: 291
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (232:237)
 - src/datasets/features/pdf.py (201:206)

duplicated block id: 292
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2703:2708)
 - src/datasets/iterable_dataset.py (2794:2799)

duplicated block id: 293
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/load.py (570:575)
 - src/datasets/load.py (741:746)

duplicated block id: 294
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2720:2725)
 - src/datasets/iterable_dataset.py (2920:2925)

duplicated block id: 295
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2720:2725)
 - src/datasets/iterable_dataset.py (2963:2968)

duplicated block id: 296
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (789:795)
 - src/datasets/iterable_dataset.py (948:954)

duplicated block id: 297
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1420:1425)
 - src/datasets/dataset_dict.py (1463:1468)

duplicated block id: 298
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2720:2725)
 - src/datasets/iterable_dataset.py (3000:3005)

duplicated block id: 299
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2720:2725)
 - src/datasets/iterable_dataset.py (3057:3062)

duplicated block id: 300
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/video.py (196:201)
 - src/datasets/features/video.py (214:219)

duplicated block id: 301
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (987:1062)
 - src/datasets/dataset_dict.py (1091:1120)

duplicated block id: 302
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/search.py (110:115)
 - src/datasets/search.py (589:594)

duplicated block id: 303
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (615:620)
 - src/datasets/dataset_dict.py (752:757)

duplicated block id: 304
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2176:2181)
 - src/datasets/iterable_dataset.py (2795:2800)

duplicated block id: 305
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1334:1339)
 - src/datasets/dataset_dict.py (2527:2532)

duplicated block id: 306
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (684:690)
 - src/datasets/iterable_dataset.py (878:884)

duplicated block id: 307
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/formatting/formatting.py (255:260)
 - src/datasets/formatting/polars_formatter.py (87:92)

duplicated block id: 308
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2963:2968)
 - src/datasets/iterable_dataset.py (3428:3433)

duplicated block id: 309
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (3257:3262)

duplicated block id: 310
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/image.py (124:131)
 - src/datasets/features/pdf.py (100:107)

duplicated block id: 311
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2806:2811)
 - src/datasets/iterable_dataset.py (3304:3309)

duplicated block id: 312
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2963:2968)
 - src/datasets/iterable_dataset.py (3409:3414)

duplicated block id: 313
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/features.py (334:339)
 - src/datasets/features/features.py (364:369)

duplicated block id: 314
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (2706:2711)
 - src/datasets/iterable_dataset.py (4252:4257)

duplicated block id: 315
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/features/audio.py (232:237)
 - src/datasets/features/image.py (228:233)

duplicated block id: 316
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/download/download_manager.py (74:79)
 - src/datasets/download/streaming_download_manager.py (57:62)

duplicated block id: 317
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (2920:2925)
 - src/datasets/iterable_dataset.py (2963:2968)

duplicated block id: 318
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1909:1914)
 - src/datasets/dataset_dict.py (2706:2711)

duplicated block id: 319
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/load.py (418:423)
 - src/datasets/load.py (595:600)

duplicated block id: 320
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1196:1202)
 - src/datasets/dataset_dict.py (2182:2188)

duplicated block id: 321
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/fingerprint.py (238:243)
 - src/datasets/fingerprint.py (260:265)

duplicated block id: 322
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py (65:72)
 - src/datasets/packaged_modules/parquet/parquet.py (41:48)

duplicated block id: 323
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/iterable_dataset.py (684:690)
 - src/datasets/iterable_dataset.py (789:795)

duplicated block id: 324
size: 6 cleaned lines of code
in 2 files:
 - src/datasets/dataset_dict.py (1139:1183)
 - src/datasets/dataset_dict.py (1206:1258)