codeprep

View on PyPIReverse Dependencies (0)

1.0.5 codeprep-1.0.5-py3-none-any.whl

Wheel Details

Project: codeprep
Version: 1.0.5
Filename: codeprep-1.0.5-py3-none-any.whl
Download: [link]
Size: 266418
MD5: 3bee7ed88c2ce4df797ed1b4fd8f2fc1
SHA256: 00e45aab633c708cf97fe0d47c8a9ffe5e838dfd5620f8665f760cf8e7f22379
Uploaded: 2021-04-21 18:12:05 +0000

dist-info

METADATA

Metadata-Version: 2.1
Name: codeprep
Version: 1.0.5
Summary: A toolkit for pre-processing large source code corpora
Author: Hlib Babii
Author-Email: hlibbabii[at]gmail.com
Home-Page: http://github.com/giganticode/codeprep
License: Apache-2.0
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 :: Apache Software 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 (<2,>=1.4)
Requires-Dist: dill (<0.4,>=0.3.1.1)
Requires-Dist: docopt (<0.7,>=0.6.2)
Requires-Dist: docopt-subcommands (<4,>=3.0.0)
Requires-Dist: jsons (<2,>=1.0)
Requires-Dist: nltk (<4,>=3.4.5)
Requires-Dist: Pygments (<3,>=2.5.2)
Requires-Dist: PyYAML (<6,>=5.1)
Requires-Dist: regex (<=2020.5.14,>=2019.11.1)
Requires-Dist: tqdm (<5,>=4.39)
Description-Content-Type: text/markdown
[Description omitted; length: 12075 characters]

WHEEL

Wheel-Version: 1.0
Generator: bdist_wheel (0.36.2)
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
codeprep/VERSION sha256=jFS_q38a6b0acUjq5B57Co9K03JuDKxw-COi1F255gw 6
codeprep/__init__.py sha256=NpaRhbqNiDBPMYXvlhvLmwkQJQ-IdSIobTRbFAF_VOU 686
codeprep/__main__.py sha256=cEFL-lStiDag7CPwCi9MlbXSvZDycz04SrpuN8FoVmY 246
codeprep/config.py sha256=XAzFBj74vhFyHeyarnp0asABbxIxqnyBCR8ijpigT_c 1510
codeprep/dirutils.py sha256=oIuItrukF3CQ6xsfcBoBLnoomYgudg_PkKX-zFtC5yc 3422
codeprep/fileutils.py sha256=A5X9wg2SZCT14ome4ggvTWTXKJENu1TbJtTo0kOSvQs 1350
codeprep/logging.yaml sha256=8-ZVpmUKRLQGT3jDle75ubNby0CpKL6jowt3vF4GHaE 671
codeprep/noneng.py sha256=DRiYLsu5m6W0alE6CBNAJCaT3qR3pZn5GnJFCmS55QE 1416
codeprep/prepconfig.py sha256=iLMCfZHB6fO346yrn6JNnpnG4JctuLJNceYwM6NXRT8 8146
codeprep/stemming.py sha256=GM7mvEP9MYj41KWoKI20pjZjSxV0Q4PuubmqphDuRAo 412
codeprep/subtokens.py sha256=c5F1ztCWZO38WhY7MRQNTuEs908M4aKKkzvzVXEIwZ8 5368
codeprep/util.py sha256=DXA91amh4T6IrDDtAR5VwvhilLQpiRKTrv2IDfgRD0k 7098
codeprep/api/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
codeprep/api/common.py sha256=bH1SY8qoDAn8F90dOnJ3z_NBQsRQqYsMeEAiKU165Ss 2266
codeprep/api/corpus.py sha256=1Oh3OWCnmgfjXcTUBRpGAyCQTso5e5F27FICq2h9ckI 13519
codeprep/api/text.py sha256=TuPVIAEbR9UiLt4-_vgM6O5g4SpAATSM4Dy9WRtsAhI 26509
codeprep/bpepkg/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
codeprep/bpepkg/bpe_config.py sha256=HzTnMYJ4UiM5kpeU5taDfjSOLS-NTffi5ai_hnXQDq8 4369
codeprep/bpepkg/bpe_encode.py sha256=Le_HKZmsBqVYcLlOeL4MVjnfqx3zPGBNRVuOq_wdgc4 5798
codeprep/bpepkg/bpe_learn.py sha256=Q4ZFlROst4717xtFhsnCv8Jy-C5hzys4-ZiOkPi7V98 5357
codeprep/bpepkg/cache.py sha256=Hxw8o2NqUFcoKlLSSyK6muQ4E7v-ItfWVN_9AfhC2Uk 1102
codeprep/bpepkg/merge.py sha256=cyZX_AlzldK8HWBaVRfa2arerctcMU878B2Y0fi_f0Q 5522
codeprep/bpepkg/wild_bpe.py sha256=UoxE9C2oHsf8psO1hNRGJlu9L5b07qDOUg3LscAPyWc 20064
codeprep/cli/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
codeprep/cli/impl.py sha256=qzIk3iFqhEpkBWNHoly2S_hgOUmR_XtekpaiC_FoAA8 5282
codeprep/cli/spec.py sha256=kS8uyXDEBNxB9YiodONbJGW5KDX51oxWJ1FmJqSifbA 11468
codeprep/cli/vocab.py sha256=CtB8JRzhMlk4ahzBrBY-DadMWxEXDA8sWDAWjCydm7c 738
codeprep/data/allamanis_dataset_metadata/small-train-projects.txt sha256=JEdIrdCkJ_5f2VgDRADjaNbA7tpu7cBndCDwfbh7G6c 1585
codeprep/data/bpe/10k/merges.txt sha256=U9xFW2X74JZIKLIBl7N8PyzsZK76Bft0EELMpe-nlTg 132354
codeprep/data/bpe/case/0/merges.txt sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
codeprep/data/bpe/case/10k/merges.txt sha256=U9xFW2X74JZIKLIBl7N8PyzsZK76Bft0EELMpe-nlTg 132354
codeprep/data/bpe/case/1k/merges.txt sha256=Crr9sZI8TPOyJI48KGx3_4mUSFGNtfhKmatY4xW6sv8 12133
codeprep/data/bpe/case/2k/merges.txt sha256=SpfcEZiRK3qZ97v3tI8VThuup0MoHlSiYs5FYF41RY0 25000
codeprep/data/bpe/case/5k/merges.txt sha256=tqIFLf_amQ7p756TykInMddsHduEhzrId5RoN5Gyf5I 63769
codeprep/data/bpe/nocase/0/merges.txt sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
codeprep/parse/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
codeprep/parse/core.py sha256=t4oSWUe9QRTzBuVnCanRnAKgrOuc74RT1lnr-qgM6gE 1619
codeprep/parse/matchers.py sha256=8hDo27ZfOkiZ_gwF_hwbamaQgIR97WMTg2UGhVXk-5k 4211
codeprep/parse/subtokens.py sha256=1ujpjZGpujvp88CiZ-ODGPFsgaczDljMLx_68yjQSE4 4004
codeprep/pipeline/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
codeprep/pipeline/bpelearner.py sha256=UJuIZfzHcpyPe1T-NVJuw4b3Sj2SPIAF0kDiG5IXqCg 4921
codeprep/pipeline/bperegistry.py sha256=W5YBCyqYeqOeOYpIyPJTTmaohFD_E56qXHCRDr-J_ts 8641
codeprep/pipeline/dataset.py sha256=yeXO371pH5O5p7HpqxCjUcpRoo9iO4m1q1Gr0rd8HoU 13182
codeprep/pipeline/parse_projects.py sha256=5Hq6L3I-I6YiOmK7-lI9O_8BaTgnC8ENedph-03K3GE 2817
codeprep/pipeline/stages.py sha256=cFBTF1H2RLEZD2hgbQszn1mzDmYK81bmQUD11c9i9_w 3049
codeprep/pipeline/to_repr.py sha256=9rElMfn1qx5MImi-aJXDivHERmE1s43f_Jd_ywX5cvs 7829
codeprep/pipeline/vocab.py sha256=3mi5WRaDygWmRpetrQwea6qwMSER4QP22egaRBJNw20 15673
codeprep/pipeline/vocabloader.py sha256=fpBG1_H05arh5-w-zgAqZ_JT53VSjBbiCCqSV53OW9Q 2015
codeprep/preprocess/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
codeprep/preprocess/core.py sha256=GDyfNzj5whWnFiB-AP9wEFLqIVOTJWWbAtQZWo98NSQ 1260
codeprep/preprocess/metadata.py sha256=yzjfzMY44VzlL9pD2-I23jJZgC5V3To5QjBMqJZ8qXM 4528
codeprep/preprocess/placeholders.py sha256=4iYGHhfy_ZK7zE6Vnufm3aKgkQ9A4zMCdENr9nwJqAY 492
codeprep/preprocess/reprconfig.py sha256=WGaCpKsxw69XJS4tRdXONc17u0LqT170bbplPlOFaYc 880
codeprep/tokens/__init__.py sha256=DFl8j6gSWW3jVzIFylJjO9erbzmTqnvOvNa47t9Yzaw 378
codeprep/tokens/containers.py sha256=OO_Gsl7ZD04se9cJ9XbOrjUVhx6t2S6B1-l52sgeRH0 6736
codeprep/tokens/noneng.py sha256=-_yT6QzLj1FCOCWF2qTrrDy2Z1oxREIZbshMYz0a0b4 1712
codeprep/tokens/numeric.py sha256=5PMw3ZXxYT-2JUiU-MtxJnqZEx-LniGWvHa3Vo1JUEI 1574
codeprep/tokens/rootclasses.py sha256=PBAInp-p-ncH7cjvQO1q_MdtRVBeHcKNsiqNl_1W_oI 707
codeprep/tokens/whitespace.py sha256=IpQnI3RrHZCA6Z_15X2ZNnk4VlhVJVIRxk6tjUV8_0Q 1982
codeprep/tokens/word.py sha256=sfcMF0kALgzYPz_W1TU3GYIK8rrEghnkNbAyV7ntNfQ 6083
tests/__init__.py sha256=yYWM1rhwfz_msHCse78vHMpNQM3oqeeVfQr5fDCgU_w 209
tests/test_corpus_b2b.py sha256=x2oBGg25wOYPleg1rfEgHRCaeaLchyayWyAdh_cytxc 1781
tests/test_subword_separation.py sha256=Pf5zBkRzshn5I87QEshN29gwN3z3CFUJDdqzJk3Xjzg 3553
tests/test_to_repr.py sha256=z60YpFmW2C5JTpKeqZU88HrjRpigxaJMFRBkGcB_Y9M 25850
tests/api/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
tests/api/test_corpus.py sha256=4S5o0Op_ZSelYja7CCFULIzVmO0RqVBeif_n4mDUMUc 2837
tests/bpepkg/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
tests/bpepkg/test_merge.py sha256=E9_VxGPgcn9MPM8rt4rsBchu1NmLMT6hNIJ0StEEQ5U 1360
tests/bpepkg/wild_bpe_performance.py sha256=Z_bG7P_C7PktVmI5NShaGj_f7C-DADDsqyYD1ZW8I5s 3404
tests/cli/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
tests/cli/test_spec.py sha256=fqhMX9EUXmzayfK8OdApeu1zSdTdRwj4WSCxYwx83aE 21087
tests/infrastructure/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
tests/infrastructure/test_bpelearner.py sha256=2HgKBrs8Y7Au6Odyau8wsVqeFCObAVisoftRc3ZlXvE 997
tests/infrastructure/test_bperegistry.py sha256=s6xmaSnbt9O1QPd3sNOEo9X4A2p-4vH8ynmCnBHfoGk 6079
tests/infrastructure/test_dataset.py sha256=7_BhQ8mrS1xHAuYrj4XcZ0UbKkN4TOttjZz3Z1mknm8 5476
tests/parse/__init__.py sha256=yrO7mv29TE9Wr5zWLgPkfZON7Qvxd8ZwPYZFhgYX1yg 103
tests/parse/test_core.py sha256=Sgk7i6ZnUKTtsSYkgVhUml6f9tRHwedbCglvKR55nP0 15460
tests/parse/test_subtokens.py sha256=3RSMbQgOEtxpJt1z5OAjQPdQ6MEHU_Qs7rc2sMaJ7p0 1422
codeprep-1.0.5.dist-info/METADATA sha256=K-_cD9mNflaPIxVWGLQlpRmC4WI2NQkxrPUmE9UKxOY 13393
codeprep-1.0.5.dist-info/WHEEL sha256=OqRkF0eY5GHssMorFjlbTIq072vpHpF60fIQA6lS9xA 92
codeprep-1.0.5.dist-info/entry_points.txt sha256=9ulPpELHzv70H6u11C0pqNDhhvAdpyeyfpEztRLBHto 53
codeprep-1.0.5.dist-info/top_level.txt sha256=-9ryrooJNIkkRC2N8R1U4XKL__gdkPNnsRQL2UlAW6g 15
codeprep-1.0.5.dist-info/RECORD

top_level.txt

codeprep
tests

entry_points.txt

codeprep = codeprep.__main__:main