giganticode-dataprep

View on PyPIReverse Dependencies (1)

1.0.0a12 giganticode_dataprep-1.0.0a12-py3-none-any.whl

Wheel Details

Project: giganticode-dataprep
Version: 1.0.0a12
Filename: giganticode_dataprep-1.0.0a12-py3-none-any.whl
Download: [link]
Size: 245970
MD5: 045368b55051956f15d2672d8582d3b5
SHA256: 0069e70e7da1d97d8253b8a340d83184b1bfffd4419efb1e17a01650071e7266
Uploaded: 2020-01-15 08:39:53 +0000

dist-info

METADATA

Metadata-Version: 2.1
Name: giganticode-dataprep
Version: 1.0.0a12
Summary: A toolkit for pre-processing large source code corpora
Author: giganticode
Author-Email: hlibbabii[at]gmail.com
Home-Page: http://github.com/giganticode/dataprep
License: MIT
Keywords: big large data source code corpus machine learning pre-processing nlp
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Classifier: Topic :: Software Development :: Pre-processors
Requires-Python: >=3.6
Requires-Dist: appdirs (==1.4.3)
Requires-Dist: dill (==0.3.1.1)
Requires-Dist: docopt (==0.6.2)
Requires-Dist: docopt-subcommands (==3.0.0)
Requires-Dist: jsons (==1.0.0)
Requires-Dist: nltk (==3.4.5)
Requires-Dist: Pygments (==2.5.2)
Requires-Dist: PyYAML (==5.1.2)
Requires-Dist: regex (==2019.11.1)
Requires-Dist: tqdm (==4.39.0)
Description-Content-Type: text/markdown
[Description omitted; length: 10852 characters]

WHEEL

Wheel-Version: 1.0
Generator: bdist_wheel (0.33.6)
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
dataprep/VERSION sha256=saMjrfmyWsb_g-yyrB9fL3mjJ-lzl3T6akK9pjpL--g 15
dataprep/__init__.py sha256=RASejiPmsywhyfeSu540C2f5r5u-Gc1WH_ekM6yU5E0 581
dataprep/__main__.py sha256=_40LllHC4pGQKZaZDVSzuSU7GwMnKenpq0vgVQ3wnlk 142
dataprep/config.py sha256=u2d1zGvbgWpwn_BpsEmIpIAD9QbpBrHsZKG6fQJ7Emk 1329
dataprep/dirutils.py sha256=NTZQrF1FLA_EiLKkGpcKIcnwwgi8VPPQKpObUBT-SMk 3320
dataprep/fileutils.py sha256=YOLAPYhGSzy215RRMLw0NMlFIQFIE2VgfNmBlE29nJM 1245
dataprep/logging.yaml sha256=PGYFZ19O_97YCxbVVElnQJhLzQEL79n-L9CrYLlAt9Y 671
dataprep/noneng.py sha256=USgtsYFpfCbpNY2A-6pY0qB0XpAfZnJEaXb5CFVOAHg 1312
dataprep/prepconfig.py sha256=djSTYazwyOprAwSnh9GEuxKzvzId8I3AxbzDFWeGWrs 8042
dataprep/stemming.py sha256=INjXT8V27AbU37pJG_b_MtpnshbARiByU21ja_zFSWA 307
dataprep/subtokens.py sha256=H8FCtNcWTD-_v40xxBIUVUcHLd-hN7JgpV-2OKg789A 5264
dataprep/util.py sha256=uSGb9Cgm7j8av56y-HGnk0p33cLC5BKU7-ngEPBcA_Q 6113
dataprep/api/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/api/common.py sha256=AyWO8GFL-s5BLk4fU1BshHY4BA92WCbRZIXD_FvYGyA 2162
dataprep/api/corpus.py sha256=ZTnJKhCpXfMmh5FNDJkr0Inwc0ZHyhyQj95cfSsx9Ko 11838
dataprep/api/text.py sha256=Xmoa6oULksUHOXPyn3cKG90mV2reFeOFsY14VqlHiIk 26405
dataprep/bpepkg/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/bpepkg/bpe_config.py sha256=lEb-lSYEoc6SwsMzFJdsn_ZNCst89cRRBTtSa53lKiw 4265
dataprep/bpepkg/bpe_encode.py sha256=bAVg7JwWhCxtUanh2k1g7gIMYcGBX-7W4twgmCegE7M 5694
dataprep/bpepkg/bpe_learn.py sha256=lnv18NVXvP7iB-F4OAPwveCjPLILojHTC6pepM-oaMA 5253
dataprep/bpepkg/cache.py sha256=lKRDYl5BGnRxgw2V_nT2VYPGn8LT2y1H9Gt84jS2HSU 998
dataprep/bpepkg/merge.py sha256=TyoW4CJo-xSc_l53yHLCgKDH7b6w9XQlvquoBR3WJuE 5273
dataprep/bpepkg/wild_bpe.py sha256=XbWAFEeaXC2q95VFJnpnml2CNPNA2sSywog_ECO5khA 19959
dataprep/cli/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/cli/impl.py sha256=WOlsfDXuKsacRbyAI-H6VGmYWU-XJBw5Yk6G4Fkg3aQ 5100
dataprep/cli/spec.py sha256=W7GPWqkGVvKRlfKeg2NI__cR5Y0CzSaxHtXFw9vogDg 9966
dataprep/cli/vocab.py sha256=37AXajbcZMw6HlI4FNZnHHPpmrlZk3Gwc9EtYXXlD84 634
dataprep/data/bpe/10k/merges.txt sha256=U9xFW2X74JZIKLIBl7N8PyzsZK76Bft0EELMpe-nlTg 132354
dataprep/data/bpe/case/0/merges.txt sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/data/bpe/case/10k/merges.txt sha256=U9xFW2X74JZIKLIBl7N8PyzsZK76Bft0EELMpe-nlTg 132354
dataprep/data/bpe/case/1k/merges.txt sha256=Crr9sZI8TPOyJI48KGx3_4mUSFGNtfhKmatY4xW6sv8 12133
dataprep/data/bpe/case/5k/merges.txt sha256=tqIFLf_amQ7p756TykInMddsHduEhzrId5RoN5Gyf5I 63769
dataprep/data/bpe/nocase/0/merges.txt sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/parse/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/parse/core.py sha256=vaAES1SR3kfNN6aSwdTMb0ShnqL-zc3R_I1lEoCjeMY 1484
dataprep/parse/matchers.py sha256=f102pqrvLwqxormLKLAdNfUw88xg6h8VNH2o7XNUyWo 4107
dataprep/parse/subtokens.py sha256=9gev4NOF2OMRGQ5l7yIjCEVAO2_tXif_P4u8PjgXclY 3900
dataprep/pipeline/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/pipeline/bpelearner.py sha256=J-edkYIQGhegd8PmDdTffnqA6pnQZdR-iix4AitzDHM 4817
dataprep/pipeline/bperegistry.py sha256=BRX1FGe8tODIkmEJ7ikcKK4Y6tgsJGZupFHKLfMPLHI 8536
dataprep/pipeline/dataset.py sha256=uxGP9AZj7oKLa4-ubG3qKURZ2aPMr_yLLDrrwcPX8pk 12725
dataprep/pipeline/parse_projects.py sha256=zTIt1N9yb9EIvTctYm5TWBYwgqQ2XQPiCy5x82EVRRQ 2672
dataprep/pipeline/stages.py sha256=21LoOf4dZeHGwyAIwr0944jWvHxhUrQcgR3PEVyW6Gw 2945
dataprep/pipeline/to_repr.py sha256=pCVJ0xLIOl0nFbkC917dpV4pEtSh6cOmCcYLhbgjtHQ 7088
dataprep/pipeline/vocab.py sha256=aL3ZRuk-oOtm0KqLLeGYjaOA6Vmoqq6CWySS9rE3PsM 15280
dataprep/pipeline/vocabloader.py sha256=vDzUilvSAw24niKuqrUHacuk6hq6eh3JwZdxL-oOUxU 1911
dataprep/preprocess/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
dataprep/preprocess/core.py sha256=G5T9iicgFrE6lFDywsh2u3CpB98cEg_URbLf-VGVsqU 1156
dataprep/preprocess/metadata.py sha256=oGX4nnnOWXnhJPfob2kTsPwu3aGi2369nfA79EkheAU 4423
dataprep/preprocess/placeholders.py sha256=nfjmUYA29qZ2CMoqa5bxZyl8hhEGBSlNqgI7EzErVxI 388
dataprep/preprocess/reprconfig.py sha256=ZUxZpWtGBmATI0_e9NMlk3K2O7vOVUUeRFoMWWgw4tg 775
dataprep/tokens/__init__.py sha256=gWBDbQ1QMKfTC_xStvafE1HKeoI2pCweXNxB9hXQtbw 273
dataprep/tokens/containers.py sha256=Vmbbjj4C8kz21VhkrplvV-vzF4ub_q4ev4DUGOUF5MY 6632
dataprep/tokens/noneng.py sha256=2ac_zc7vQCCtTTDdObioFMxzY_PYv9GQOicAxYgHq0c 1608
dataprep/tokens/numeric.py sha256=efEmp9ldtZ2Tzmu-2EmQHkqp-onQ64R_T3F8wSMm-PI 1469
dataprep/tokens/rootclasses.py sha256=ti0WGeRBeMqo4Wg5i-jRQsF2JPXMW_CRNCXciUbohBM 603
dataprep/tokens/whitespace.py sha256=9m9lXMx0bUsgcesBgC-rnVAPFnKQAvVp2OlEDvy3ppU 1878
dataprep/tokens/word.py sha256=Z9oi48t-_4S2F2cMURoc_QzEi34cQDxpE8j79ajtwDs 5979
tests/__init__.py sha256=LLi6a_Iy7QA5sRmDY_kVYr247bC5x_FLGqsls09Dx9E 104
tests/test_corpus_b2b.py sha256=spklf7_6lC9G5gX3xH_09En1ZW_KNxt1EGhEa1wujWc 955
tests/test_subword_separation.py sha256=EchWYH5IdgtoUtfoCiV08pCRZen9WjJMvjaxGgmLFoY 3449
tests/test_to_repr.py sha256=6kSg0Erkt1UMgOep_nafyCQO7NsOOARm1bmKY8QqNIw 25747
tests/api/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
tests/api/test_corpus.py sha256=5I6XZ5ARCDBTjH3Z_SrC2Fx4_rELdJ5gFgttEd2Mb_Q 3059
tests/bpepkg/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
tests/bpepkg/test_merge.py sha256=Rt1imd7x6Fb6Uph1H-Tij-U1G2V9hrgbOtl1Gh91nGQ 1256
tests/bpepkg/wild_bpe_performance.py sha256=cyPKp1LRzI4ktp3AL8-x4BjeavQlnpxcqhnOUC1fW-A 3299
tests/cli/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
tests/cli/test_spec.py sha256=_vsTx06cKmglZ7XlMtroYdjbUilTBxlP0Iw-qfaKx6Q 20051
tests/infrastructure/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
tests/infrastructure/test_bpelearner.py sha256=js_qAhXZbvXIW1evobGjDxXFkfV4U9zJ4UDzTLXJil0 893
tests/infrastructure/test_bperegistry.py sha256=T9katw9sdSX3p6aIyMwr2RNhMltQyAx4MGouLxlrg9w 5975
tests/infrastructure/test_dataset.py sha256=dz0viuDD4IGsHXanEK0Nu4fYVKc7cRuLydJrscxaaxw 5372
tests/parse/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
tests/parse/test_core.py sha256=7dbk4i69tQlKPXDaoJLwNBIJfW6a_cXqcvxape7TwX0 15356
tests/parse/test_subtokens.py sha256=uuoXAOsqjKJGlxUowVcwWyrfx64kWbMDQZCldpqhd_k 1318
giganticode_dataprep-1.0.0a12.dist-info/LICENSE sha256=mTCFcE4Y41dR0sP7hz-LXhCPApr-q3H2etVuCyNrjWo 1068
giganticode_dataprep-1.0.0a12.dist-info/METADATA sha256=7Y8kiQDkOVkcetEGnnNYI7bOEkLbYlVkT27TR2JdWRA 12132
giganticode_dataprep-1.0.0a12.dist-info/WHEEL sha256=p46_5Uhzqz6AzeSosiOnxK-zmFja1i22CrQCjmYe8ec 92
giganticode_dataprep-1.0.0a12.dist-info/entry_points.txt sha256=A-z4W7PBYuHGzCszP-PJe4GAC3VmkFa1EIjc0c-LV5Y 53
giganticode_dataprep-1.0.0a12.dist-info/top_level.txt sha256=LH1g_LSoBnug6XQ6yVx_iLPWBJahzkrdnbjB1xdYneI 15
giganticode_dataprep-1.0.0a12.dist-info/RECORD

top_level.txt

dataprep
tests

entry_points.txt

dataprep = dataprep.__main__:main