data-modori
View on PyPI — Reverse Dependencies (0)
0.1.5 | data_modori-0.1.5-py3-none-any.whl |
Wheel Details
Project: | data-modori |
Version: | 0.1.5 |
Filename: | data_modori-0.1.5-py3-none-any.whl |
Download: | [link] |
Size: | 119660 |
MD5: | afb9b8bbfb6f25ae09ee02081a952f39 |
SHA256: | 193d6cc450f92619198b06c0cf9875f0c7eb5bd9db95f362e2467c3d47b155db |
Uploaded: | 2023-12-14 17:40:26 +0000 |
dist-info
METADATA · WHEEL · RECORD · top_level.txt · entry_points.txt
METADATA
WHEEL
Wheel-Version: | 1.0 |
Generator: | bdist_wheel (0.41.2) |
Root-Is-Purelib: | true |
Tag: | py3-none-any |
RECORD
Path | Digest | Size |
---|---|---|
data_modori/__init__.py | sha256=CjpRE9sT1AfD9Ft__Fhhop9Bh9IBCVEmm9E9TX1aV2k | 21 |
data_modori/analysis/__init__.py | sha256=CJRFx62f1uCpAWZRhVRCCbk8Ab_FZYQVD-IGpVEGcRk | 99 |
data_modori/analysis/column_wise_analysis.py | sha256=e3TCHHLm-irhjGj3bbvb5e5eUP5xXzMdRX1lO5iVP4M | 10511 |
data_modori/analysis/diversity_analysis.py | sha256=Fzp0M8hYtXbHY6CXTS7gIqi4gxW8fwaCKmppgzPsg7E | 6107 |
data_modori/analysis/overall_analysis.py | sha256=fpDqTdgwF7TEr2FDpLsdSfpNnyQWXX16EnPa2YjiWKI | 1388 |
data_modori/config/__init__.py | sha256=y9w17TyxBnOnkuJn86xr1H2tWyYQ_xp82pY8EM6Uhnw | 41 |
data_modori/config/config.py | sha256=DyIHinV2y2Osm8mPVp7ZTwr0mhsKCkD_WmVKQLAoCGQ | 16300 |
data_modori/core/__init__.py | sha256=gnJL_9FL93W0NS1I28yTRs3whThx8vcjqna3HlpGP-A | 152 |
data_modori/core/analyser.py | sha256=Q2XlX_ZNmUcIQ7rsQxh0l7FKxywKrznM-G5UtseC7Lo | 5105 |
data_modori/core/data.py | sha256=n1LaAbm9JA3lAdlB8IotlPhy5Cg3gnefUTS2gAx91HI | 12389 |
data_modori/core/executor.py | sha256=yLsj3SdJPIo3sIo--o8AeAQDR8E7FEPzWEkf5R7S4I0 | 9344 |
data_modori/core/exporter.py | sha256=w8y5-4KcHHkwODY81oUrqi2bOK5rg8yWDJ1dwc-ZK5I | 8737 |
data_modori/core/ray_executor.py | sha256=s7dSZPLWkWi_oWo22EVNRLTWZ9fkSsAVH2LFObeDo4c | 3039 |
data_modori/core/tracer.py | sha256=4-BVz80f7Hf1hVdcASFyarZ0hOiW_Jv7-iNxoYpQoqU | 9063 |
data_modori/format/__init__.py | sha256=Me--0Z33F8NOHeskbuoEgu2Ajt4r-OUsEcrqWQlaRiM | 163 |
data_modori/format/csv_formatter.py | sha256=83kjrH-NjAz5qh0U7d4-DxryvDwu8mVdSv_myrDk7g0 | 726 |
data_modori/format/formatter.py | sha256=KB2qUE6cHQy2Ujl5J2qqvZtTJCGR7SV_-foaRGinZuk | 9374 |
data_modori/format/json_formatter.py | sha256=BqgiKV9qKsDfe3-3ke-rEv338NrV5arPtZu7_uUrIrc | 779 |
data_modori/format/load.py | sha256=FdUa6R62LT7GpkqpzIsfCrrpN21Rmsq4VjLNG-N0Q7E | 1050 |
data_modori/format/mixture_formatter.py | sha256=NWh72fgItlCZUXV-Bi5bfgmzXwl0axe-If4lh8qi1Gc | 3868 |
data_modori/format/parquet_formatter.py | sha256=mSCiC5lTSG8ZuneeTKZlLU5jqf_L27lt3mTfT5OxaDE | 746 |
data_modori/format/text_formatter.py | sha256=4LOeNXjmzw1PGkQRdea0i5hr1_8ILneAiDF8tj1Q68Q | 6190 |
data_modori/format/tsv_formatter.py | sha256=estI4SRpbW6tFMD4fibMss0WXpxwpIiLyWD77b15GBc | 778 |
data_modori/ops/__init__.py | sha256=vxsZh3si5CnP7Zgh4xDY6v5izoDMtYE7sTFWVd7K-7Y | 151 |
data_modori/ops/base_op.py | sha256=xlfByP5DYYJJE3hWrEHaPXztO3k18e2ejUIGvgGXt_0 | 3928 |
data_modori/ops/load.py | sha256=9kw-Yy7fDYEDwB4xJGBCkjkmDZNrnDrV7PvJd1At1lk | 706 |
data_modori/ops/op_fusion.py | sha256=QSeOPNTVEEPrzUe2G2dNBDhfleKhglWKlpQEfPMJgU8 | 5165 |
data_modori/ops/common/__init__.py | sha256=yuxCK9ypvYDOySxEjEu_r53fymELdYvO38iKzdab9KU | 412 |
data_modori/ops/common/aws_s3_downloader.py | sha256=yqmqbVda4aBHPd96QTitWXH53kG0X_CcaGgqE5nmnZk | 2141 |
data_modori/ops/common/helper_func.py | sha256=87JfJKSa0HiUFjCo3gs28FRX8OZr39anvgXtyuRdILk | 7733 |
data_modori/ops/common/special_characters.py | sha256=5DbPI7udvamO8QSoq89EZbwh7jHWSRyTEBiyyGgnuXI | 1390 |
data_modori/ops/deduplicator/__init__.py | sha256=r3l5CyoxjcGSjXQIVXUjKhEfFgMOooHRfPo57xGR_W4 | 115 |
data_modori/ops/deduplicator/document_deduplicator.py | sha256=kChGHYF2WkZc0jkpfhcfrRnAK_ubdlyUSnjD7EqqDRI | 3884 |
data_modori/ops/deduplicator/document_minhash_deduplicator.py | sha256=91txsWzZr8kaI9Bzi2ZFqY8YWGgK90TYjwtCixCwbOk | 11557 |
data_modori/ops/deduplicator/document_simhash_deduplicator.py | sha256=qQ5KkDtDuCfzV8Q3HTlIroEiMWn1wmgD3nHBTDklijQ | 9699 |
data_modori/ops/filter/__init__.py | sha256=ao93gyICtC0F54Lcac7NLgH-XM1g85nTxhgoJNV2RiQ | 473 |
data_modori/ops/filter/alphanumeric_filter.py | sha256=iRsIk3MGdn1r9EGKEhnyeEXpOIcJOngXkaHcIRA5gq0 | 3170 |
data_modori/ops/filter/average_line_length_filter.py | sha256=xzfoHK31fiT9y_iK3nDJaDfvrzPLOmExbxE6-HsbuTE | 2043 |
data_modori/ops/filter/character_repetition_filter.py | sha256=mh-xKEgvfdDqfvVuXohupS62kC8ym2M8MSe22dVBsZ4 | 2850 |
data_modori/ops/filter/flagged_words_filter.py | sha256=QvL72V_56kGQA8gRgXm-oWNScn5guJnXhR_u1WoaWz4 | 9084 |
data_modori/ops/filter/language_id_score_filter.py | sha256=OI7r22IxuPzEyS2_Hj6HQgpnQ2Su5UpY8YgX-HXmV4k | 2181 |
data_modori/ops/filter/maximum_line_length_filter.py | sha256=HPppR1Y2T5LaxD1M9an2lrLxyBm65_6R7HNr2eZjx98 | 2048 |
data_modori/ops/filter/perplexity_filter.py | sha256=jCVFggmCGjxTa3insd7w9BX7IeiSaaOEUu_46zBF47A | 2965 |
data_modori/ops/filter/special_characters_filter.py | sha256=1asOZjNQ73RDWW-Im9Vk-hJSzQdbWtgJaUKJt_etGQs | 1987 |
data_modori/ops/filter/specified_field_filter.py | sha256=bQVjdFaoaLIgcoaFmBpKCvj0_BbEyxyiCkWHMAg4u3c | 1804 |
data_modori/ops/filter/specified_numeric_field_filter.py | sha256=Rs9UVYYW92uKe5947q_J_SiUorhd_ZqTD-9dgO4rp6o | 2158 |
data_modori/ops/filter/stopwords_filter.py | sha256=E2o8x_ytWFSKl0UAed5GBJONxu5q7bKg9TFgkiwMqfs | 4903 |
data_modori/ops/filter/suffix_filter.py | sha256=p0Zu215yVWUNU_Q9H-upxJcnrIw2ADi5MR9SVY5WISw | 1168 |
data_modori/ops/filter/text_length_filter.py | sha256=hM1-mRk-qgUZAxZPy-dC-8ux15WjWnSYpEVI4JlYFTc | 1493 |
data_modori/ops/filter/token_num_filter.py | sha256=4CPe3zKBVo8jVVRogY2gGib20x5zYRHJ7L4vBaIo1zE | 2136 |
data_modori/ops/filter/word_num_filter.py | sha256=wBiIM_ouSGvaZVDFJ0SB9RZX4NrFpjmc9vk0vHp7Q-Q | 2723 |
data_modori/ops/filter/word_repetition_filter.py | sha256=FcOkwin7hSdJrp3JAgw4oavt_pGMEWK1qOvKNxvR3qg | 4322 |
data_modori/ops/mapper/__init__.py | sha256=DyM4D1evF3eUgPZRSKYsGM1OlFMmWxu7Z-L-L3thYrc | 601 |
data_modori/ops/mapper/clean_copyright_mapper.py | sha256=EbdDSDRjNuB42tkNLZV_tdzsCuS6La5W619jQzZDbSM | 1755 |
data_modori/ops/mapper/clean_email_mapper.py | sha256=WNblzBkOX4Kr9bvcx6grP-HLZtewNHA-i95ZThIDIi8 | 862 |
data_modori/ops/mapper/clean_html_mapper.py | sha256=Sxr_yP5ERl5mIKCT-rfKkZXVBKXPoIQR6ebN3JhyK-I | 1026 |
data_modori/ops/mapper/clean_ip_mapper.py | sha256=iVdsqDNA_9gp4OFgevMfAH9IcP9EVGD7zWO5UnGXXdM | 1147 |
data_modori/ops/mapper/clean_links_mapper.py | sha256=i-5QR4n_v4coGmV43ocT2SN3bWuLL2FnAT_TJDzWyGU | 1404 |
data_modori/ops/mapper/expand_macro_mapper.py | sha256=BSrKlCneO5kJhLM0h8RFRQUEZCjVi3VYyXReJ0QrAUs | 3158 |
data_modori/ops/mapper/fix_unicode_mapper.py | sha256=LY6ox28O40l2Id3ssJ0R9JAaRUH0axb6HU1FGrJSTA0 | 521 |
data_modori/ops/mapper/nlpaug_en_mapper.py | sha256=K5NkBOyBbRFhkoiR4XliByUpakglCP6jOiiQxRHWwtQ | 6310 |
data_modori/ops/mapper/punctuation_normalization_mapper.py | sha256=6n_trRmpxM58l5n3wdccNFIXaeuL6s2h2MkTbUrbunc | 1664 |
data_modori/ops/mapper/remove_bibliography_mapper.py | sha256=FSvleqWKDg7z_0FLnSKcLoDpIhQqzB8DOb0qd2sUUtE | 1169 |
data_modori/ops/mapper/remove_comments_mapper.py | sha256=8mmKituD-AZsIUTa8n0zul_Pb6KJUTjZG6N-YxJA5Bs | 1835 |
data_modori/ops/mapper/remove_header_mapper.py | sha256=mOloYDSpvB2LpYqpOEW5xjuQrq3Riq_5nR5tkz0tQrA | 1784 |
data_modori/ops/mapper/remove_long_words_mapper.py | sha256=xfO7yP_aQ5uZPUIQr9USvjIniaLUOjJOPtj1Bkebz_U | 1910 |
data_modori/ops/mapper/remove_specific_chars_mapper.py | sha256=uB4RdXWEHyxC9mxOwQV1YRDIjZt5WeOQk54Grm4Xnao | 1206 |
data_modori/ops/mapper/remove_table_text_mapper.py | sha256=uBDxF8p4tWMdlU8iyQ8mAPhh7uoSjhb6HOttnWB_Thc | 1392 |
data_modori/ops/mapper/remove_words_with_incorrect_substrings_mapper.py | sha256=MOfwLcww2Qn3ixyxATDX2jWems6oBT8ClWBpotwUaqU | 2741 |
data_modori/ops/mapper/sentence_split_mapper.py | sha256=r_HkjGscPkEs90jWDvlYd8dBtZLp6A3mcuzH-lSj3dQ | 981 |
data_modori/ops/mapper/whitespace_normalization_mapper.py | sha256=S0PVIMdmz1LgaJjsR9dx7XBtCBgsW3KN9Ohcvvo3BHQ | 1158 |
data_modori/ops/selector/__init__.py | sha256=ozLhYXkJ4tmb_xP9-ddB4oww4ITCkwObIqFTjp5BMtM | 80 |
data_modori/ops/selector/frequency_specified_field_selector.py | sha256=dTKsDj5zSBLWX5Xn5I2G2zY46nKdfSFgnHdbn-t6QwY | 3430 |
data_modori/ops/selector/topk_specified_field_selector.py | sha256=A5Iw_fIkqUW2QglD09xN8pwvWr4uEEkHfMGbcfQEyDo | 3562 |
data_modori/tools/__init__.py | sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU | 0 |
data_modori/tools/analyze_data.py | sha256=FjFFPihTukGnWHGgw52MXJDGXlbickj0KyLJTsCZ7Qk | 177 |
data_modori/tools/process_data.py | sha256=6CiZHOJQ8ZVATPIb1z21pJTCVZ7ayCVL4wH0QnxMtXI | 427 |
data_modori/utils/__init__.py | sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU | 0 |
data_modori/utils/asset_utils.py | sha256=GBXBFOz5SVciEbXoV8AErlu0buGkG6uibPfUIL9MuT0 | 2115 |
data_modori/utils/cache_utils.py | sha256=gMYqslL4YLn0SNVJDfe5dQ2zI7EQf1glqTbsmC3F2JI | 974 |
data_modori/utils/ckpt_utils.py | sha256=DkBaIfOl2GM2rWEpXU96Ep8-6y_NypOG4HGrRJ6aNFU | 4492 |
data_modori/utils/compress.py | sha256=9kfzXyH529X5j6xdggaRfd3XZbCWh9k2otsihaArZgw | 17211 |
data_modori/utils/constant.py | sha256=slhiZ64d_RZEaiEsEAel6LpIkYuxffTnNriGuMjLWXk | 1105 |
data_modori/utils/file_utils.py | sha256=NV8JltxM6nwX4VLegExzg5TM7gK7RxhVg55OcBH0Yno | 1979 |
data_modori/utils/fingerprint_utils.py | sha256=OKsh0pBDCYH0wzsuPDL64fCMkm7u0pOrI7qNqa71V1M | 6023 |
data_modori/utils/logger_utils.py | sha256=6ULUKKryAML8iC_UP2nohpmp0ir8rMg0q8ZMJWWHMAo | 4622 |
data_modori/utils/mm_utils.py | sha256=yypguEgORyhTDtf2jyhrftLJ5ZFBUKKcZ3r9bvvsxzM | 3022 |
data_modori/utils/model_utils.py | sha256=__yGXJAieMQoA39266bZf5QzpeefW9MrTktfzG_kBkQ | 10113 |
data_modori/utils/registry.py | sha256=m1OBz3rnuD0fr_QyEgkDXfN_e9WUcSb8xa5ndHVqzRE | 4390 |
data_modori-0.1.5.dist-info/LICENSE | sha256=8u49RROqcHXDrH_NFOGAbwj7z4q1UFpkPa9TA-EgIsc | 21634 |
data_modori-0.1.5.dist-info/METADATA | sha256=F5zDMCiQDI_tiVirtlxNEPW-YyeDXJuZ3UK4JcIWDvo | 15651 |
data_modori-0.1.5.dist-info/WHEEL | sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A | 92 |
data_modori-0.1.5.dist-info/entry_points.txt | sha256=v_UWUtyhyx1ZG4Biu7W_NVOxGS5Zj3LLFUc6OPs3h2I | 116 |
data_modori-0.1.5.dist-info/top_level.txt | sha256=dtUlUxmLfr3jXcv-xZOZpKHdhLP3FeHALZXsB_r9ZdM | 12 |
data_modori-0.1.5.dist-info/RECORD | — | — |
top_level.txt
data_modori
entry_points.txt
dm-analyze = data_modori.tools.analyze_data:main
dm-process = data_modori.tools.process_data:main