{ "info": { "author": "Jonathan Raiman", "author_email": "jraiman at mit dot edu", "bugtrack_url": null, "classifiers": [ "Intended Audience :: Science/Research", "Operating System :: OS Independent", "Programming Language :: Python :: 3.3", "Topic :: Text Processing :: Linguistic" ], "description": "Wikipedia NER\n-------------\n\nTool to train and obtain named entity recognition labeled examples\nfrom Wikipedia dumps.\n\nUsage in [IPython notebook](http://nbviewer.ipython.org/github/JonathanRaiman/wikipedia_ner/blob/master/Wikipedia%20to%20Named%20Entity%20Recognition.ipynb) (*nbviewer* link).\n\n## Usage\n\nHere is an example usage with the first 200 articles from the english wikipedia dump (dated lated 2013):\n\n\tparseresult = wikipedia_ner.parse_dump(\"enwiki.bz2\",\n max_articles = 200)\n most_common_category = wikipedia_ner.ParsedPage.categories_counter.most_common(1)[0][0]\n\n most_common_category_children = [\n\t\t\tparseresult.index2target[child] for child in list(wikipedia_ner.ParsedPage.categories[most_common_category].children)\n\t\t\t]\n\t\n\t\"In '%s' the children are %r\" % (\n\t\tmost_common_category,\n\t\t\", \".join(most_common_category_children)\n\t\t)\n\n\t#=> \"In 'Category : Member states of the United Nations' the children are 'Afghanistan, Algeria, Andorra, Antigua and Barbuda, Azerbaijan, Angola, Albania'\"", "description_content_type": null, "docs_url": null, "download_url": "https://github.com/JonathanRaiman/wikipedia_ner", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/JonathanRaiman/wikipedia_ner", "keywords": "XML,epub,tokenization,NLP", "license": "MIT", "maintainer": null, "maintainer_email": null, "name": "wikipedia-ner", "package_url": "https://pypi.org/project/wikipedia-ner/", "platform": "any", "project_url": "https://pypi.org/project/wikipedia-ner/", "project_urls": { "Download": "https://github.com/JonathanRaiman/wikipedia_ner", "Homepage": "https://github.com/JonathanRaiman/wikipedia_ner" }, "release_url": "https://pypi.org/project/wikipedia-ner/0.0.24/", "requires_dist": null, "requires_python": null, "summary": "Python package for creating labeled examples from wiki dumps", "version": "0.0.24" }, "last_serial": 1472469, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "3f3b3aeb91551a98ab17944925a6a01f", "sha256": "4a0538d424c439ec9e05b3a13de6c9d9e642ccb911e10cea48cfcbb100929634" }, "downloads": -1, "filename": "wikipedia-ner-0.0.1.tar.gz", "has_sig": false, "md5_digest": "3f3b3aeb91551a98ab17944925a6a01f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4184, "upload_time": "2014-10-27T18:28:05", "url": "https://files.pythonhosted.org/packages/45/06/b5e729768a62807192769a2303895b95622d114e6896f6fb4912d71c6d83/wikipedia-ner-0.0.1.tar.gz" } ], "0.0.10": [ { "comment_text": "", "digests": { "md5": "c68850b6853a0368a0cd455b59df4a40", "sha256": "e137b32ef9e14909dc83547b3389d83eff2c2c24bac8d9aea43fa503d7c5acda" }, "downloads": -1, "filename": "wikipedia-ner-0.0.10.tar.gz", "has_sig": false, "md5_digest": "c68850b6853a0368a0cd455b59df4a40", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74652, "upload_time": "2014-12-22T16:09:55", "url": "https://files.pythonhosted.org/packages/40/3b/ff77c3aa3fdbc97cdb1ff27a87b22a28ad13e034fd2caa1d0d37d5c6e972/wikipedia-ner-0.0.10.tar.gz" } ], "0.0.11": [ { "comment_text": "", "digests": { "md5": "497d117af7f92870186c641995848c76", "sha256": "c88fa365e06628a1ca15a72080e057d03f241718410e92ce3d8c1e22eb2c2f2a" }, "downloads": -1, "filename": "wikipedia-ner-0.0.11.tar.gz", "has_sig": false, "md5_digest": "497d117af7f92870186c641995848c76", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74764, "upload_time": "2014-12-22T16:35:07", "url": "https://files.pythonhosted.org/packages/fd/04/df9cae0eeadb19386efc51905160097f698e57698a01631163273a5d10a0/wikipedia-ner-0.0.11.tar.gz" } ], "0.0.12": [ { "comment_text": "", "digests": { "md5": "62de4e9d14284ed923fa9d4c2f247ab5", "sha256": "5e3a53852629263dd781c4b8ae69d8396d6531e26f4f10fdf3b7877959b8a232" }, "downloads": -1, "filename": "wikipedia-ner-0.0.12.tar.gz", "has_sig": false, "md5_digest": "62de4e9d14284ed923fa9d4c2f247ab5", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74772, "upload_time": "2014-12-22T16:45:27", "url": "https://files.pythonhosted.org/packages/c7/1a/295cc3ca17f412bf81b9d86145b4517723777817d49edf0b519551932441/wikipedia-ner-0.0.12.tar.gz" } ], "0.0.13": [ { "comment_text": "", "digests": { "md5": "f58f45420155cecf2aba73c21a14880a", "sha256": "e19f2e89a7a16b0f244ea7146eae68c12e6f180bc1ed823bc074191d2331b3f8" }, "downloads": -1, "filename": "wikipedia-ner-0.0.13.tar.gz", "has_sig": false, "md5_digest": "f58f45420155cecf2aba73c21a14880a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74771, "upload_time": "2014-12-22T16:51:09", "url": "https://files.pythonhosted.org/packages/76/41/4a21fbc5275f369f4cad2f13d00e00bd017e8e2705ed37dfeca952c24363/wikipedia-ner-0.0.13.tar.gz" } ], "0.0.14": [ { "comment_text": "", "digests": { "md5": "7fa1e04959c73238fbb5773f186e3241", "sha256": "e6117364408eee4faf03df34e5955af9925dc6efab67d05e40508eb18891820c" }, "downloads": -1, "filename": "wikipedia-ner-0.0.14.tar.gz", "has_sig": false, "md5_digest": "7fa1e04959c73238fbb5773f186e3241", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74773, "upload_time": "2014-12-22T16:52:16", "url": "https://files.pythonhosted.org/packages/13/2d/e32199076c56eeee2c1666b732ff822a3179122d52293ceeba063fd08499/wikipedia-ner-0.0.14.tar.gz" } ], "0.0.15": [ { "comment_text": "", "digests": { "md5": "30fa60d8e8b91684bde970d90c249cd2", "sha256": "ed6ddbf1d772164815cac4f2717c392bbcdd1f91825dd2319f5b9fea12dde5f7" }, "downloads": -1, "filename": "wikipedia-ner-0.0.15.tar.gz", "has_sig": false, "md5_digest": "30fa60d8e8b91684bde970d90c249cd2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74767, "upload_time": "2014-12-22T16:53:34", "url": "https://files.pythonhosted.org/packages/ce/e8/9b50709202516437d745308e8d24f4f1f456aee59679e5075d6dbd709af6/wikipedia-ner-0.0.15.tar.gz" } ], "0.0.16": [ { "comment_text": "", "digests": { "md5": "8985732fa02831d502ad671506aa71ec", "sha256": "24f794188dcb22fdeb30d6d9878f2a0449a24918b5d71501d257e566e72e2cbf" }, "downloads": -1, "filename": "wikipedia-ner-0.0.16.tar.gz", "has_sig": false, "md5_digest": "8985732fa02831d502ad671506aa71ec", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74762, "upload_time": "2014-12-22T16:54:56", "url": "https://files.pythonhosted.org/packages/69/b9/f1f0eafcadf35fae3d51023b2e469860f4dfd3c01ece5124765f5d351478/wikipedia-ner-0.0.16.tar.gz" } ], "0.0.17": [ { "comment_text": "", "digests": { "md5": "2813caa2a849f29f981b433725f2d44d", "sha256": "19737bbbfa31736975deb5835efc55fdad3693823bedd7db1a7d8dce93e2a0e2" }, "downloads": -1, "filename": "wikipedia-ner-0.0.17.tar.gz", "has_sig": false, "md5_digest": "2813caa2a849f29f981b433725f2d44d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74797, "upload_time": "2014-12-23T01:12:44", "url": "https://files.pythonhosted.org/packages/74/b7/761c13ce4304cc890a9997e4e1019c38762766e90489a9896c1fc2e28c7f/wikipedia-ner-0.0.17.tar.gz" } ], "0.0.18": [ { "comment_text": "", "digests": { "md5": "52716bd8d97732ecddfeafe185d3304b", "sha256": "fa57248f0c3460ef98a90aee0879bf88730c70106144e00b93adaaf243a2ad33" }, "downloads": -1, "filename": "wikipedia-ner-0.0.18.tar.gz", "has_sig": false, "md5_digest": "52716bd8d97732ecddfeafe185d3304b", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74808, "upload_time": "2014-12-24T06:01:37", "url": "https://files.pythonhosted.org/packages/5a/36/e9a1d980cee616c08a029834132efce4ce8e21ed866420f2cc0e240be2f8/wikipedia-ner-0.0.18.tar.gz" } ], "0.0.19": [ { "comment_text": "", "digests": { "md5": "a4c2de7c74c73ba0ef16ac9c86440ce0", "sha256": "f7428ea1f59b29befc508580d8db190cb07f6d008b1c1dc25c849062bf4ec69c" }, "downloads": -1, "filename": "wikipedia-ner-0.0.19.tar.gz", "has_sig": false, "md5_digest": "a4c2de7c74c73ba0ef16ac9c86440ce0", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 76366, "upload_time": "2015-02-10T00:02:17", "url": "https://files.pythonhosted.org/packages/e5/da/63660d4a928d63740053f94aa2870f5561f2abaa443152627b2ecf409033/wikipedia-ner-0.0.19.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "345eb790e2303ac019f6afece1f794e3", "sha256": "9e7b1c2bd5521b10279614565c8a9acc51c770f4993033c12033e0ea7b44c03a" }, "downloads": -1, "filename": "wikipedia-ner-0.0.2.tar.gz", "has_sig": false, "md5_digest": "345eb790e2303ac019f6afece1f794e3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4218, "upload_time": "2014-10-27T18:28:23", "url": "https://files.pythonhosted.org/packages/3b/35/3b0c03f05669989090f9db9a2bab929587bd2791a460950f03f0f37ee466/wikipedia-ner-0.0.2.tar.gz" } ], "0.0.21": [ { "comment_text": "", "digests": { "md5": "03bfb96544f2755cdf48bb7f060e5f3d", "sha256": "0bfedf55b02f14225269b81bf4acc3857d8973ebb89e15422a4ef3c0fb845807" }, "downloads": -1, "filename": "wikipedia-ner-0.0.21.tar.gz", "has_sig": false, "md5_digest": "03bfb96544f2755cdf48bb7f060e5f3d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 76760, "upload_time": "2015-03-09T18:59:05", "url": "https://files.pythonhosted.org/packages/b4/c1/db0c1024c3e8310c2613eb5d4f5fc6b538026f6bd8660691651fb48d7ee3/wikipedia-ner-0.0.21.tar.gz" } ], "0.0.22": [ { "comment_text": "", "digests": { "md5": "5976d5c215c1a9bc12d50694064362c7", "sha256": "655a949409ac00536a5c69df94242dfc38ddf51067079b14f98b3e76ad3bd96f" }, "downloads": -1, "filename": "wikipedia-ner-0.0.22.tar.gz", "has_sig": false, "md5_digest": "5976d5c215c1a9bc12d50694064362c7", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 76747, "upload_time": "2015-03-09T19:07:55", "url": "https://files.pythonhosted.org/packages/ae/f7/e797583ff1c1e908abcec85f44f217057fce6858cfe169e742cfcb26571a/wikipedia-ner-0.0.22.tar.gz" } ], "0.0.23": [ { "comment_text": "", "digests": { "md5": "7c04f7f4c1f36c6d85c80ab0147669b0", "sha256": "ed16a6ffa1c2779fef1a6a2208a2342a3853b55c3cd3a9255c4cb8c296908ab8" }, "downloads": -1, "filename": "wikipedia-ner-0.0.23.tar.gz", "has_sig": false, "md5_digest": "7c04f7f4c1f36c6d85c80ab0147669b0", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 76778, "upload_time": "2015-03-09T19:22:24", "url": "https://files.pythonhosted.org/packages/f1/0d/5ad7b4c2ad61583a235b05f01c74d4fcbcef4b690ae66456c33298321cf5/wikipedia-ner-0.0.23.tar.gz" } ], "0.0.24": [ { "comment_text": "", "digests": { "md5": "d586e86f33203613956b3401bacca3b8", "sha256": "1f6fc58a8dc82817458b4b890b3219f861e0bdd666e7a67f51758094f0b839a8" }, "downloads": -1, "filename": "wikipedia-ner-0.0.24.tar.gz", "has_sig": false, "md5_digest": "d586e86f33203613956b3401bacca3b8", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 76762, "upload_time": "2015-03-22T21:07:34", "url": "https://files.pythonhosted.org/packages/c9/ee/f46583a5a40ba93a5dd1ca7472542a76a477a8b9d5a2ec2362d123b37307/wikipedia-ner-0.0.24.tar.gz" } ], "0.0.3": [ { "comment_text": "", "digests": { "md5": "f5bd988abe8932e0ed175d89d18bb324", "sha256": "32a1cff87e9f294f03e0751a6dd35270f87f14fd7b27bfd362aa00ae82af4f62" }, "downloads": -1, "filename": "wikipedia-ner-0.0.3.tar.gz", "has_sig": false, "md5_digest": "f5bd988abe8932e0ed175d89d18bb324", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4240, "upload_time": "2014-10-27T18:31:10", "url": "https://files.pythonhosted.org/packages/78/c6/35f9e2c0a126e4cf85f73ece69d6cb0e4aa26fbedc5ce72af2cf6abf3608/wikipedia-ner-0.0.3.tar.gz" } ], "0.0.4": [ { "comment_text": "", "digests": { "md5": "de4534a6b2e80d0e7f09319249baa8f3", "sha256": "bdd5b8ed54b846d009ea5492aaa7bec0cbcccb90a71317908baad01caf23c8f2" }, "downloads": -1, "filename": "wikipedia-ner-0.0.4.tar.gz", "has_sig": false, "md5_digest": "de4534a6b2e80d0e7f09319249baa8f3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 71712, "upload_time": "2014-10-27T18:32:26", "url": "https://files.pythonhosted.org/packages/0d/31/8d9c0dfabcb9e7cdc42ab433398818e894093b759f153cce419bd6c23a7b/wikipedia-ner-0.0.4.tar.gz" } ], "0.0.6": [ { "comment_text": "", "digests": { "md5": "1fb9554bf7dcbb745551fcec47091bd8", "sha256": "73713b940af670297180146298b3ce1cc95de6f47a46abe89a362d1e33ea5f8e" }, "downloads": -1, "filename": "wikipedia-ner-0.0.6.tar.gz", "has_sig": false, "md5_digest": "1fb9554bf7dcbb745551fcec47091bd8", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 73400, "upload_time": "2014-10-27T18:47:13", "url": "https://files.pythonhosted.org/packages/c4/a7/5d4d2ddd20a053bc93ac1750fc19183d49f95f39e36d1dd3f584b26856f8/wikipedia-ner-0.0.6.tar.gz" } ], "0.0.7": [ { "comment_text": "", "digests": { "md5": "1eae40c5b140a02528a4e281d9d6c041", "sha256": "1c290ea1d4af2f6e0d2ca867a32d91c1443c3746b2cf75eed0d57ea88a2a19b4" }, "downloads": -1, "filename": "wikipedia-ner-0.0.7.tar.gz", "has_sig": false, "md5_digest": "1eae40c5b140a02528a4e281d9d6c041", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 73455, "upload_time": "2014-12-22T12:20:17", "url": "https://files.pythonhosted.org/packages/91/90/a0d8a18c81747c5d6eb34c55b75905902ee56dcf5fb54e3e753ab00b8f04/wikipedia-ner-0.0.7.tar.gz" } ], "0.0.8": [ { "comment_text": "", "digests": { "md5": "f3345cf1a94fd41f38f9557574569c28", "sha256": "aa9343dbb6556413636af370bd6ba03c8631f34da1a71db5cfd683f4819e5a79" }, "downloads": -1, "filename": "wikipedia-ner-0.0.8.tar.gz", "has_sig": false, "md5_digest": "f3345cf1a94fd41f38f9557574569c28", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74630, "upload_time": "2014-12-22T16:02:16", "url": "https://files.pythonhosted.org/packages/c6/5e/720e26c6e91f2d8c65b40c8f604410317f76d0eb5474a1ed8bf7a1b5587e/wikipedia-ner-0.0.8.tar.gz" } ], "0.0.9": [ { "comment_text": "", "digests": { "md5": "23ec023293b84c760b04738c313449a0", "sha256": "eb6969fd33b7ed813aa67d262d2edcac8cea923e2d1771a36f78f3b9ddcf3762" }, "downloads": -1, "filename": "wikipedia-ner-0.0.9.tar.gz", "has_sig": false, "md5_digest": "23ec023293b84c760b04738c313449a0", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 74645, "upload_time": "2014-12-22T16:04:49", "url": "https://files.pythonhosted.org/packages/13/74/50bd349cbf12597bc8c88ea1e14864a793cb79bbe16fd6aebe91ef38c815/wikipedia-ner-0.0.9.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "d586e86f33203613956b3401bacca3b8", "sha256": "1f6fc58a8dc82817458b4b890b3219f861e0bdd666e7a67f51758094f0b839a8" }, "downloads": -1, "filename": "wikipedia-ner-0.0.24.tar.gz", "has_sig": false, "md5_digest": "d586e86f33203613956b3401bacca3b8", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 76762, "upload_time": "2015-03-22T21:07:34", "url": "https://files.pythonhosted.org/packages/c9/ee/f46583a5a40ba93a5dd1ca7472542a76a477a8b9d5a2ec2362d123b37307/wikipedia-ner-0.0.24.tar.gz" } ] }