data-prep-toolkit-transforms
View on PyPI — Reverse Dependencies (1)
0.2.1.dev3 | data_prep_toolkit_transforms-0.2.1.dev3-py3-none-any.whl |
Wheel Details
Project: | data-prep-toolkit-transforms |
Version: | 0.2.1.dev3 |
Filename: | data_prep_toolkit_transforms-0.2.1.dev3-py3-none-any.whl |
Download: | [link] |
Size: | 115220 |
MD5: | 691fb641b9ffce40ec6f80497c2da2b3 |
SHA256: | 877437589aa28645f3a042b71599d076f36cf736b571ba0e682798be2dbd3bbb |
Uploaded: | 2024-09-11 19:17:07 +0000 |
dist-info
METADATA · WHEEL · RECORD · top_level.txt
METADATA
WHEEL
Wheel-Version: | 1.0 |
Generator: | setuptools (74.1.2) |
Root-Is-Purelib: | true |
Tag: | py3-none-any |
RECORD
Path | Digest | Size |
---|---|---|
cc_net_prepro.py | sha256=B9lt_2ZFVsORqXHdepNQ3B-wd3CT_9wNrC41Qcedtg0 | 4929 |
code2parquet_local.py | sha256=lpc4oesF2F-6cq3kOlUoteNNytRLhI3fUcVlKXCFP9M | 2140 |
code2parquet_local_python.py | sha256=X0IyCfonb4G1X2rjuhT0bpdYRz1exORg_UVRG9NyI9s | 2326 |
code2parquet_s3_python.py | sha256=3lV3rWxY_iCceCuKUoguztDsNp--nOU2E21Jad3dje0 | 2330 |
code2parquet_transform.py | sha256=Rk1wKMMDvmE7ORqg59AVFCniDlkvNKGiWt5TBJaaZNQ | 10512 |
code2parquet_transform_python.py | sha256=dnaECaTrQtqsJjDHfXTD4AjTTzEFL0rSyPD_kqCpAQA | 1539 |
code_quality_local.py | sha256=cVjqwZwDDLs6Dee72XNbBRxExWvskwGSv14RPUR9WS8 | 1495 |
code_quality_local_python.py | sha256=jBKu4a0cv0LwsVvq74eJ67Zvc8cZdajptlGHcSfgsB4 | 1933 |
code_quality_transform.py | sha256=tBGjqBnym9cqbx16Tu5e0nivQOmAct2heSZe-Om70HQ | 11283 |
code_quality_transform_python.py | sha256=lcGBN2Oky9XuoY4kC5Huof5zHg09jmHCLE7zp_XpP3c | 1140 |
doc_Gopher_statistics.py | sha256=KxZpWjXKX5l9FkQnyLzwDb3fmdG-8awoGbKWnleFtPI | 6530 |
doc_c4_statistics.py | sha256=gZBossXPPswmJ1sujXMNcV7giup8VKZy9OYbnIMLLUM | 6048 |
doc_chunk_chunkers.py | sha256=9VsEXCuk5Nvs1QLpSfdCnt0XLS21Cru6q36G7eWhQJo | 2695 |
doc_chunk_local.py | sha256=AtuaTktcJ4D2qca_0NCkRCHzBVYcQ0cVI00K03YU7U8 | 1471 |
doc_chunk_local_python.py | sha256=HTIpnhqql61imSrNFgjzNKf56hoGEaVFHS_ZyZ0GXy8 | 2148 |
doc_chunk_transform.py | sha256=7qE14srWEHVf164lAxp6cY95GUmIdAsM4Qda_n-nT1s | 8234 |
doc_chunk_transform_python.py | sha256=LPSxi9yTeSR04AnSgPjwsHfuPBqLGmHLS5HuEFaNHes | 1730 |
doc_id_local.py | sha256=FdKnmtPVeCnaooZkxOzpi7R6b8lHKtD16AE3U--7wQU | 2389 |
doc_id_local_python.py | sha256=5clxS6OVatTMk2IjAAskmHirjqjRQNVeo8hud_Q5rcQ | 2328 |
doc_id_transform_base.py | sha256=qKzBLkatF79MoVan9RXEhviJyXRgn0FhaPOuQe4rNbs | 6697 |
doc_id_transform_python.py | sha256=iT6Ub4MKGE62IC-FwYnqKNQcPXKH3wuMKDkgw0nONDY | 4801 |
doc_quality_local.py | sha256=NgzYtfZuixRb674upFaqG2av2NDCup0ZXuhmx11M22E | 1729 |
doc_quality_local_python.py | sha256=G0kCMYy7Xv3RpI1SIOlEECK2WvooH6pCW9TNPgmTk5s | 2398 |
doc_quality_transform.py | sha256=g3JAHZMXkx77I3IT6sgUFLwUnHjTlj-dl_QVyyP7O0g | 10872 |
doc_quality_transform_python.py | sha256=5zBVvG_xHIXa-iuu6kgJ7kAJNM7eJPMC4Beo5oI-hrM | 1720 |
doc_quality_utils.py | sha256=n8vHmiLLAtO45_7S8lnseH4sUmyPrhBNIPuUEOhCqfI | 2264 |
ededup_local.py | sha256=Z8TjQ9c_ONspihEd9_Xv3TgQlHsRyOAZ0gfNV96D6wU | 2027 |
ededup_local_python.py | sha256=QgdYIsL05bEh_eHrv-8mCv4x-DR8NvrdOdCmTMbfRcY | 1915 |
ededup_local_python_incremental.py | sha256=ujumN2zto-JLtfWaealiH5ILMqJgKCYAYWLFXxEso44 | 2085 |
ededup_transform_base.py | sha256=STehVD7DL1b3vmx-IQY3tEGtN1LYTcII2VPVhvNNl5w | 9147 |
ededup_transform_python.py | sha256=08KIvJK3psfQrTD3IlAGxvRIGaiAIFNF3vbGD63sOZs | 6128 |
filter_local.py | sha256=p6yuEnaxUgceU8IzExb34sQNXMv56o3VSYAfBMmrigI | 2189 |
filter_local_python.py | sha256=b7UwEG_AvPMkH6bppqG4hZToM3giFq2p08i4zqR8XpI | 2388 |
filter_test_support.py | sha256=zV1ZzP0fIAVXgV-bKfGBCTO3nLs45U8NOS-7e0hWGdY | 5684 |
filter_transform.py | sha256=TFzfNnWceUhxsRp89oQHH-qKz97wh_Y1xUAks8xZEUk | 8260 |
filter_transform_python.py | sha256=7xeCdI5gdri0JKT_jxg1BPBAnSRqMt3AoZ0fmuHZ8WY | 1326 |
flair_recognizer.py | sha256=r5NeTRFyalrUkkhUzzRmMjKu-hJgGDTh5Fc2Yj1kUDs | 5218 |
header_cleanser_local.py | sha256=8DwEfmjKXLHoUC2B18S6leZwcNhOkheFwyweR1H0IL4 | 1944 |
header_cleanser_local_python.py | sha256=lmn57Cws6A2bKhgM9ucatJ1X-7frDGvNhww6Ol_uCxs | 2077 |
header_cleanser_test_support.py | sha256=EO8mk8rSzPNYVjkW7WqUaCZCO_CJqEQ_gidZYDURLh4 | 3460 |
header_cleanser_transform.py | sha256=e8aLlSY9nPdv2unpXdZQOFhmvUPowDtGRODJF5O_tFI | 7967 |
header_cleanser_transform_python.py | sha256=N08Goq8rsot2lsFNtK7XjdERbSEYUmeL4KzTqKAJkM8 | 1390 |
lang_id_local.py | sha256=wX69bfpLo28VLLgBzXJWQMP9dkAyWZCPW766iu5qphE | 1929 |
lang_id_local_python.py | sha256=PhDhwXbuKNDaIvvBS-3G-oTh-SGc0W0O_Z-Q8E5P7BU | 2314 |
lang_id_transform.py | sha256=Y9XBp3RQJrH1lcsZIuRa7fGn6Jlz_TwM18XRw6gUvrE | 6679 |
lang_id_transform_python.py | sha256=i9VnbkbOLrc5BjNUji_7hM0v2bJ5-XGflMvBm0QnM2w | 1758 |
lang_models.py | sha256=ZniqCjUwVKiL5DSY--Z7NfFcMEf0cWHUGyR745i9Hl8 | 1891 |
nlp.py | sha256=yzujQyKYG8PUT3cTmwhoJAgioGL4sLZsr2dn2uqkWkA | 1875 |
pdf2parquet_local.py | sha256=9kDOJFhVbA4pvvGXY2zXRdz-GtCOQh_ztO7gwXw79-w | 1609 |
pdf2parquet_local_python.py | sha256=uioZvdLp6U2TQ--qpGX-FeDDdTLUyd8mrcf8IjB4bgg | 2214 |
pdf2parquet_transform.py | sha256=zlZVVPkSRXtbagd6oFIR0-X2TK2Y08tb2rFBhNjPlBU | 13566 |
pdf2parquet_transform_python.py | sha256=xSp6c4QwUQFg9kHNtICIbqxn-C8lYykogB1Xn9MTnj8 | 1610 |
pii_analyzer.py | sha256=eOSaES5hJj2mIWuzhZZxzcMpO8VEHLv_2-DG__odQxo | 2714 |
pii_anonymizer.py | sha256=AlrXuyWg_RWzERPAMTsL3N8F_8EWFPmhv7KaPUs7GAU | 929 |
pii_redactor_local.py | sha256=FFaCOcGO9O56zCC0kOQso8Bw8t6te4BMbNPeaY6TTMA | 1508 |
pii_redactor_local_python.py | sha256=Pzar75Fo1RBFlC3F-ZQAoyPXbeW-KfGohXPVjjo4SB0 | 1694 |
pii_redactor_transform.py | sha256=Q02Nk2PZOhi1_QPGyipGSrsjVph4MQbxA0sAYkmE4O4 | 6141 |
pii_redactor_transform_python.py | sha256=Yo-VwNPozcv304537YYOpSLKCUyBxODTHsVtCMK1WMs | 1467 |
proglang_select_local.py | sha256=nwuE7htJpbkzLNcQpdH6Z3XElNh6Lsv5K1fWFZ9IHnY | 2056 |
proglang_select_local_python.py | sha256=BB33ejzoZeNxa02djjVHj1LhU3V8zv1sax1obfjm2kU | 2351 |
proglang_select_transform.py | sha256=MzoZqIAEvnHL7fN1TFRMJAgG3aBUcM-UTc90rDpwzB4 | 7675 |
proglang_select_transform_python.py | sha256=wv1wAEcZf02b_frbaAJ0XrJC_V_sRBISkn2M7ej_-IQ | 1247 |
resize_local.py | sha256=VgwxoStQu_CuYdAkh0UuuwkMEFsztO_cmyaM85EHppE | 1688 |
resize_local_python.py | sha256=_MdQljbaUrWc_eeFWWkvG_le6SX58bLGYF4ZZIN-rVI | 1869 |
resize_transform.py | sha256=QUxt7DOfL-v4Lm_Qie05Ml_0TUcU8dgotIhmqTf6A2w | 8946 |
resize_transform_python.py | sha256=uAZtKGsLRWZoyJ-QLTyFCEE8-IlRr3-cGQH1zghT_f0 | 1496 |
text_encoder_local.py | sha256=qs73_LTeBLtZXzB1aqv-xAlr0ysxtzmAguaTpGvRK4Q | 1907 |
text_encoder_local_python.py | sha256=fUXC2OfMFv5WLhMKw8PIDyiCxhGqCPXHSK0vei2SPyQ | 1895 |
text_encoder_transform.py | sha256=pWekXVfQ7Spq3hWiP27hJGnOMaHD2HDwb33kVNKxOFc | 5146 |
text_encoder_transform_python.py | sha256=mTNWldGvTwcGbydhNhcFWca5w8FHB0Lx7vgZQbqbSG4 | 1729 |
tokenization_local_long_doc_python.py | sha256=kt6F1wRvWkp449npFpLhb3FJNZBjNU6qNAfeQROsv-I | 2148 |
tokenization_local_python.py | sha256=XQT69Odcw7fKhnU8C9fSl1Cqu0KQe9DOo-zMAfKiCqA | 1681 |
tokenization_s3_long_doc_python.py | sha256=n7iaMVZ6CjOvVXlLuGOvpvXiRcDKg8xbzfRbK0cMMAU | 2149 |
tokenization_transform.py | sha256=GkjfgxwEO_poPa1vsVJ2ghGNjTki3Jz155Pfq_8Z0iQ | 10702 |
tokenization_transform_python.py | sha256=J7E79ZAHIBwuLt65WHuVgQdIug8DGchX0fBQwwrKVrI | 1158 |
tokenization_utils.py | sha256=uJuozmA3hIGQHIFol3w_hT6Dw5J3dMu71or9bK0Pk6c | 5475 |
data_prep_toolkit_transforms-0.2.1.dev3.dist-info/METADATA | sha256=oVz7kFFzTllG_aLWscmT2Q9_DwsI-bWccvoJzzV36L0 | 3222 |
data_prep_toolkit_transforms-0.2.1.dev3.dist-info/WHEEL | sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY | 91 |
data_prep_toolkit_transforms-0.2.1.dev3.dist-info/top_level.txt | sha256=O5EV8IKN2kg7d0OMLaErKlXd6odRg42enENi0plXxrM | 1691 |
data_prep_toolkit_transforms-0.2.1.dev3.dist-info/RECORD | — | — |
top_level.txt
cc_net_prepro
code2parquet_local
code2parquet_local_python
code2parquet_s3_python
code2parquet_transform
code2parquet_transform_python
code_quality_local
code_quality_local_python
code_quality_transform
code_quality_transform_python
doc_Gopher_statistics
doc_c4_statistics
doc_chunk_chunkers
doc_chunk_local
doc_chunk_local_python
doc_chunk_transform
doc_chunk_transform_python
doc_id_local
doc_id_local_python
doc_id_transform_base
doc_id_transform_python
doc_quality_local
doc_quality_local_python
doc_quality_transform
doc_quality_transform_python
doc_quality_utils
ededup_local
ededup_local_python
ededup_local_python_incremental
ededup_transform_base
ededup_transform_python
filter_local
filter_local_python
filter_test_support
filter_transform
filter_transform_python
flair_recognizer
header_cleanser_local
header_cleanser_local_python
header_cleanser_test_support
header_cleanser_transform
header_cleanser_transform_python
lang_id_local
lang_id_local_python
lang_id_transform
lang_id_transform_python
lang_models
nlp
pdf2parquet_local
pdf2parquet_local_python
pdf2parquet_transform
pdf2parquet_transform_python
pii_analyzer
pii_anonymizer
pii_redactor_local
pii_redactor_local_python
pii_redactor_transform
pii_redactor_transform_python
proglang_select_local
proglang_select_local_python
proglang_select_transform
proglang_select_transform_python
resize_local
resize_local_python
resize_transform
resize_transform_python
text_encoder_local
text_encoder_local_python
text_encoder_transform
text_encoder_transform_python
tokenization_local_long_doc_python
tokenization_local_python
tokenization_s3_long_doc_python
tokenization_transform
tokenization_transform_python
tokenization_utils