{ "info": { "author": "['Luyao Peng, Rui Yang']", "author_email": "luyaopeng.cn@gmail.com, rkzyang@gmail.com", "bugtrack_url": null, "classifiers": [ "License :: OSI Approved :: MIT License", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.6" ], "description": "In name entity recognition projects, we need to pre-process the character in sentences, which need to be converted into numeric features. In this package, we represent each character in two features: (1) vocabulary id, and (2) capitalization type. For example, the first record in the raw data is \n\n\n (['EU', 'rejects', 'German', 'call', 'to', 'boycott', 'British', 'lamb', '.'],\n ['ORG', 'O', 'MISC', 'O', 'O', 'O', 'MISC', 'O', 'O'])\n\n\nthe first list in this tuple is the original sentence, the second list in the tuple is the name entity for each character.\n\nUsing our package, the raw data bacome\n\n ([[1, 12],\n [2, 11],\n [3, 13],\n [4, 11],\n [5, 11],\n [6, 11],\n [7, 13],\n [8, 11],\n [9, 14]],\n [1, 4, 3, 4, 4, 4, 3, 4, 4])\n\n\nin which the first list is the numeric features for the characters (id, capitalization type), the second list is the corresponding numeric labels for the name entity type. \n\nAt the same time, you can also retrieve the vocabulary dictionary built from your sentence data.\n\nTo do this, run the following code in terminal\n\n python -m plnlp './plnlp/tiny.conll' './plnlp/tiny.conll'\n\nThe first and second arguments are the path of the train dataset and the development dataset, respectively.\n\nThe resulting datasets will be written and saved under your current working directory in a csv file.\n\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/pengluyaoyao/lpnlp", "keywords": "", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "plnlp", "package_url": "https://pypi.org/project/plnlp/", "platform": "", "project_url": "https://pypi.org/project/plnlp/", "project_urls": { "Homepage": "https://github.com/pengluyaoyao/lpnlp" }, "release_url": "https://pypi.org/project/plnlp/1.0.1/", "requires_dist": [ "logging", "csv" ], "requires_python": "", "summary": "Keyword Recognition and Pre-processing", "version": "1.0.1" }, "last_serial": 5591685, "releases": { "1.0.0": [ { "comment_text": "", "digests": { "md5": "4813c739b24fedd141ef4117bafa8292", "sha256": "206550eef7922a7e7ed5c4d468b343d101ea33776593c57b83101f2b3392bd8a" }, "downloads": -1, "filename": "plnlp-1.0.0-py2-none-any.whl", "has_sig": false, "md5_digest": "4813c739b24fedd141ef4117bafa8292", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 4179, "upload_time": "2019-07-27T03:32:07", "url": "https://files.pythonhosted.org/packages/c8/6c/f5b7e2ddb3518203a17fff1333d3ca26e281ea79c6ae34a15df58dec775a/plnlp-1.0.0-py2-none-any.whl" } ], "1.0.1": [ { "comment_text": "", "digests": { "md5": "e80b3bd0f7d56750ea78757c7d942d37", "sha256": "a2f64ad997b33ae7e6b8808ca54e6dc05d20c986ea6d16ae2adf80e6c81281d1" }, "downloads": -1, "filename": "plnlp-1.0.1-py3-none-any.whl", "has_sig": false, "md5_digest": "e80b3bd0f7d56750ea78757c7d942d37", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 4778, "upload_time": "2019-07-27T03:54:42", "url": "https://files.pythonhosted.org/packages/e1/71/14f26958ceb7670ce86de8c58ac491b71cfa0fb9d5dcb9133bd1650741fd/plnlp-1.0.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "c90f76855d5534de0aa6cf7f7a5eaa8c", "sha256": "6409db3be330b0719ae8fdfdaaeae262f13e3d15f153da35d9de904f0d391b76" }, "downloads": -1, "filename": "plnlp-1.0.1.tar.gz", "has_sig": false, "md5_digest": "c90f76855d5534de0aa6cf7f7a5eaa8c", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3982, "upload_time": "2019-07-27T03:54:44", "url": "https://files.pythonhosted.org/packages/fe/51/285d27afbd060c20c6d696b98ba92dec63e8e4d485ad6af8c485b78faf3c/plnlp-1.0.1.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "e80b3bd0f7d56750ea78757c7d942d37", "sha256": "a2f64ad997b33ae7e6b8808ca54e6dc05d20c986ea6d16ae2adf80e6c81281d1" }, "downloads": -1, "filename": "plnlp-1.0.1-py3-none-any.whl", "has_sig": false, "md5_digest": "e80b3bd0f7d56750ea78757c7d942d37", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 4778, "upload_time": "2019-07-27T03:54:42", "url": "https://files.pythonhosted.org/packages/e1/71/14f26958ceb7670ce86de8c58ac491b71cfa0fb9d5dcb9133bd1650741fd/plnlp-1.0.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "c90f76855d5534de0aa6cf7f7a5eaa8c", "sha256": "6409db3be330b0719ae8fdfdaaeae262f13e3d15f153da35d9de904f0d391b76" }, "downloads": -1, "filename": "plnlp-1.0.1.tar.gz", "has_sig": false, "md5_digest": "c90f76855d5534de0aa6cf7f7a5eaa8c", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 3982, "upload_time": "2019-07-27T03:54:44", "url": "https://files.pythonhosted.org/packages/fe/51/285d27afbd060c20c6d696b98ba92dec63e8e4d485ad6af8c485b78faf3c/plnlp-1.0.1.tar.gz" } ] }