{ "info": { "author": "chenghaomou", "author_email": "chengham@isi.edu", "bugtrack_url": null, "classifiers": [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "License :: OSI Approved :: MIT License", "Programming Language :: Python :: 3.7" ], "description": "# Dependencies\n\n```bash\nunidecode\nemoji\n*kenlm\nfuzzy\nscikit-learn\npyxdameraulevenshtein \npygtrie\nnumpy \n```\n\n*Install kenlm wrapper from github:\n\n```bash\npip install https://github.com/kpu/kenlm/archive/master.zip\n```\n\n# Usage\n\n```python\n\n # Load english dictionary\n english_vocab = load_english_vocab(...)\n english_vocab.update(load_english_vocab(...))\n \n # Load bilingual lexicon dictionary\n foreign_dict = load_lexicon_norm(...)\n \n # Load target language model\n lm = kenlm.Model(...)\n\n # Train a ngram model if needed\n # ngram_train(foreign_dict, 'hin-tfidf-ngram_algo')\n\n # Ulf's romanizer\n romanizer = partial(romanize,\n romanization_path=...,\n language_code=\"hin\")\n\n soundex_inst = fuzzy.DMetaphone()\n soundex_algo = lambda x: soundex_inst(x)[0].decode('utf-8') if soundex_inst(x)[0] is not None else x\n english_encoded_vocab = {e: soundex_algo(e) for e in english_vocab if e}\n\n # load the ngram model\n ngram_algo = pickle.loads(open(..., \"rb\").read())\n\n soundex_model = partial(soundex_similarity,\n encoded_english_vocab=english_encoded_vocab,\n romanizer=romanizer,\n soundex=soundex_algo)\n\n lev_model = partial(lev_similarity, backup=soundex_model)\n ngram_model = partial(ngram_similarity, model=ngram_algo, backup=lev_model)\n final_model = partial(exact_similarity, backup=ngram_model)\n\n for line in open(...):\n source, target = line.strip('\\n').split('\\t')\n oovs = extract_oov(target, source, english_vocab=english_vocab, romanization=True)\n best, mods = translate_oov(target, oovs, foreign_dict, final_model, lm.score)\n\n if best != target:\n\n for oov in oovs:\n alt = list(mods[oov].keys())[0]\n trans = mods[oov][alt]\n debug.debug(f\"{romanizer(oov)} -> {romanizer(alt)} : {list(trans)}\")\n\n debug.debug(best)\n debug.debug(\"*\"*100)\n```\n\nor \n\n```shell\npython -m elisa_patch --help\n```", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/ChenghaoMou/elisa-patch", "keywords": "", "license": "", "maintainer": "", "maintainer_email": "", "name": "elisa-patch", "package_url": "https://pypi.org/project/elisa-patch/", "platform": "", "project_url": "https://pypi.org/project/elisa-patch/", "project_urls": { "Homepage": "https://github.com/ChenghaoMou/elisa-patch" }, "release_url": "https://pypi.org/project/elisa-patch/0.3.7/", "requires_dist": null, "requires_python": "", "summary": "Dictionary incorporation for machine translation", "version": "0.3.7" }, "last_serial": 5431993, "releases": { "0.2.3": [ { "comment_text": "", "digests": { "md5": "7d02771fe9ebe593036359a700956733", "sha256": "f9d0361abaa7f7a9150e6862e1f57547f018d5328b7fac4c5dee3351ab5098f8" }, "downloads": -1, "filename": "elisa-patch-0.2.3.tar.gz", "has_sig": false, "md5_digest": "7d02771fe9ebe593036359a700956733", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 5305, "upload_time": "2019-06-07T01:21:34", "url": "https://files.pythonhosted.org/packages/0d/0a/3f2ae2cbc91e711a58ad03d5cc76f19bfae7b6d9e678bb23ae56d5d6f363/elisa-patch-0.2.3.tar.gz" } ], "0.2.4": [ { "comment_text": "", "digests": { "md5": "bbbb4c59b5023696aef7acfca5d6d560", "sha256": "debe357f12c3c86873059571ca41a9c3d961511dc1fc2e2a3cd95064c5151d03" }, "downloads": -1, "filename": "elisa-patch-0.2.4.tar.gz", "has_sig": false, "md5_digest": "bbbb4c59b5023696aef7acfca5d6d560", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6177, "upload_time": "2019-06-10T23:09:01", "url": "https://files.pythonhosted.org/packages/eb/b4/69feae065852bb69ff7c702d6843af118a2721669f6866bf118c384c7d91/elisa-patch-0.2.4.tar.gz" } ], "0.2.5": [ { "comment_text": "", "digests": { "md5": "4d362aa31eea44c51fb52ed556dc478b", "sha256": "2011f44f729081b3106bfbc66c3c1d9643aa2d23af3e9629a2a9044fa2309f79" }, "downloads": -1, "filename": "elisa-patch-0.2.5.tar.gz", "has_sig": false, "md5_digest": "4d362aa31eea44c51fb52ed556dc478b", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6175, "upload_time": "2019-06-10T23:11:44", "url": "https://files.pythonhosted.org/packages/18/1d/a61178dd3497f0cf17a758d2fba7c1d3d50bfdf8777260a9f78acd22051c/elisa-patch-0.2.5.tar.gz" } ], "0.2.6": [ { "comment_text": "", "digests": { "md5": "20be162fe36969a89d910a75a612914f", "sha256": "33b3b5e765f84b45e0f8debcf730f1260b67300d389d9eb7cfe2ba38ca04ff6c" }, "downloads": -1, "filename": "elisa-patch-0.2.6.tar.gz", "has_sig": false, "md5_digest": "20be162fe36969a89d910a75a612914f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6229, "upload_time": "2019-06-10T23:49:27", "url": "https://files.pythonhosted.org/packages/a0/70/d0264f23c4b1af4ff2b390f571071d2f7cda25fb0c681846864540113249/elisa-patch-0.2.6.tar.gz" } ], "0.2.7": [ { "comment_text": "", "digests": { "md5": "b61cae0707e09845028e0e844a66b1d3", "sha256": "6f1dc48df902adf782996ea23a9274ba59aec3adda7f53086d3f3ae2c792bab0" }, "downloads": -1, "filename": "elisa-patch-0.2.7.tar.gz", "has_sig": false, "md5_digest": "b61cae0707e09845028e0e844a66b1d3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6233, "upload_time": "2019-06-11T16:56:37", "url": "https://files.pythonhosted.org/packages/5d/3e/78b9a4e1fa5e51991fa1a3c61b5331b823f870e5fed47bb165171256c602/elisa-patch-0.2.7.tar.gz" } ], "0.2.8": [ { "comment_text": "", "digests": { "md5": "1f9990037d9b4191883a6bc6b5b8dcc2", "sha256": "53b7d700c552c1aec83b87e3b39814dde73648a9cf2339f075c236e454755534" }, "downloads": -1, "filename": "elisa-patch-0.2.8.tar.gz", "has_sig": false, "md5_digest": "1f9990037d9b4191883a6bc6b5b8dcc2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6247, "upload_time": "2019-06-11T17:04:40", "url": "https://files.pythonhosted.org/packages/f1/a5/e85cf44bc03337d85576c5969e329d85d65ba2d6e0c9dab6357a21760a7c/elisa-patch-0.2.8.tar.gz" } ], "0.2.9": [ { "comment_text": "", "digests": { "md5": "a120a2603aebda0a79e10273b8fb19ef", "sha256": "64934895f6012b37127bc4061547c121babb2be6d8783296ad8df47a9c161a0b" }, "downloads": -1, "filename": "elisa-patch-0.2.9.tar.gz", "has_sig": false, "md5_digest": "a120a2603aebda0a79e10273b8fb19ef", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6244, "upload_time": "2019-06-11T17:07:35", "url": "https://files.pythonhosted.org/packages/a8/53/cf7def49923c1d0f9644774844d3a1aa276cf9f552091e7fe64bef902848/elisa-patch-0.2.9.tar.gz" } ], "0.3.0": [ { "comment_text": "", "digests": { "md5": "c52af045a87d723c21f8de30bacbf7d2", "sha256": "7b2e81cda31e53c27eb340b61aedb4bb7ab1aa6d665ed2b0f81228307db679bb" }, "downloads": -1, "filename": "elisa-patch-0.3.0.tar.gz", "has_sig": false, "md5_digest": "c52af045a87d723c21f8de30bacbf7d2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6299, "upload_time": "2019-06-11T17:23:10", "url": "https://files.pythonhosted.org/packages/06/b3/1f9db56d6cd105cf3e5421280aaad6111f44f0664c2b04834e12a045353c/elisa-patch-0.3.0.tar.gz" } ], "0.3.1": [ { "comment_text": "", "digests": { "md5": "386ff32d23517003baa2c8cb850201ad", "sha256": "af8fd408d029c3ddcb083715e5040f61b7d02d9125677e4ce8d71f8240992176" }, "downloads": -1, "filename": "elisa-patch-0.3.1.tar.gz", "has_sig": false, "md5_digest": "386ff32d23517003baa2c8cb850201ad", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6587, "upload_time": "2019-06-14T17:32:20", "url": "https://files.pythonhosted.org/packages/49/c0/c3e1d064bedd8202b5cc9e78f4dff43c6226b27833990f231c924f280c08/elisa-patch-0.3.1.tar.gz" } ], "0.3.2": [ { "comment_text": "", "digests": { "md5": "61b0eff9d395244d4d6224cf8bcef95a", "sha256": "4a8682cf285aa1993bb959b804bfd7ec6d8a2287b62c18ae59f80bc36cdcbddd" }, "downloads": -1, "filename": "elisa-patch-0.3.2.tar.gz", "has_sig": false, "md5_digest": "61b0eff9d395244d4d6224cf8bcef95a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6612, "upload_time": "2019-06-14T17:40:19", "url": "https://files.pythonhosted.org/packages/72/fd/b0bd5d3219bf086edfb23650d8fa08d425b7f81211ea5f3cabffd56d0393/elisa-patch-0.3.2.tar.gz" } ], "0.3.5": [ { "comment_text": "", "digests": { "md5": "5a802d41ce9cdd3330b22a81fa3cd84f", "sha256": "ab94a1c2544cb09dfca1adcc02638994b7f9016b08e1e86aedb993f1dcd41cbf" }, "downloads": -1, "filename": "elisa-patch-0.3.5.tar.gz", "has_sig": false, "md5_digest": "5a802d41ce9cdd3330b22a81fa3cd84f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6634, "upload_time": "2019-06-21T17:19:37", "url": "https://files.pythonhosted.org/packages/0b/26/23e0bd11d8aea239a904b895d8b93220fc232cc51e097c196a9c51b57934/elisa-patch-0.3.5.tar.gz" } ], "0.3.7": [ { "comment_text": "", "digests": { "md5": "162b47e68bad3c88cc0968353d536330", "sha256": "5e27cc7da606f4f2c17b70bca4647f2a2336e5bdd44ca24b13cc101c387c655d" }, "downloads": -1, "filename": "elisa-patch-0.3.7.tar.gz", "has_sig": false, "md5_digest": "162b47e68bad3c88cc0968353d536330", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6630, "upload_time": "2019-06-21T17:27:00", "url": "https://files.pythonhosted.org/packages/8a/e1/29d93e1d6c9f65d90c3f8957e9168c923ea886297c1336474346df748178/elisa-patch-0.3.7.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "162b47e68bad3c88cc0968353d536330", "sha256": "5e27cc7da606f4f2c17b70bca4647f2a2336e5bdd44ca24b13cc101c387c655d" }, "downloads": -1, "filename": "elisa-patch-0.3.7.tar.gz", "has_sig": false, "md5_digest": "162b47e68bad3c88cc0968353d536330", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 6630, "upload_time": "2019-06-21T17:27:00", "url": "https://files.pythonhosted.org/packages/8a/e1/29d93e1d6c9f65d90c3f8957e9168c923ea886297c1336474346df748178/elisa-patch-0.3.7.tar.gz" } ] }