{"id":21974741,"url":"https://github.com/andrewrporter/wikipedia-stoplist","last_synced_at":"2025-03-22T23:41:20.647Z","repository":{"id":141138455,"uuid":"194946669","full_name":"AndrewRPorter/wikipedia-stoplist","owner":"AndrewRPorter","description":"Build robust StopLists from Wikipedia articles","archived":false,"fork":false,"pushed_at":"2019-10-17T21:40:05.000Z","size":24,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-28T03:21:36.978Z","etag":null,"topics":["natural-language-processing","nlp","python","stoplist","wikipedia","wikipedia-api"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AndrewRPorter.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-07-02T23:11:46.000Z","updated_at":"2019-10-17T21:40:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"34de01a6-0fca-425a-9edc-2b092ecc833d","html_url":"https://github.com/AndrewRPorter/wikipedia-stoplist","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AndrewRPorter%2Fwikipedia-stoplist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AndrewRPorter%2Fwikipedia-stoplist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AndrewRPorter%2Fwikipedia-stoplist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AndrewRPorter%2Fwikipedia-stoplist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AndrewRPorter","download_url":"https://codeload.github.com/AndrewRPorter/wikipedia-stoplist/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245036127,"owners_count":20550662,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["natural-language-processing","nlp","python","stoplist","wikipedia","wikipedia-api"],"created_at":"2024-11-29T15:47:35.383Z","updated_at":"2025-03-22T23:41:20.603Z","avatar_url":"https://github.com/AndrewRPorter.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"wikipedia-stoplist\n==================\n\nThis project will serve as an exploration into building robust stoplists from Wikipedia article contents.\n\nUsage\n=====\n\n`$ python main.py --num-pages 50 --term-freq 0.6 --limit 200`\n\nThis will generate a csv file called output.csv. You can pass this CSV file in to be analyzed again\nwith:\n\n`$ python main.py --input output.csv --term-freq 0.6 --limit 200`","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrewrporter%2Fwikipedia-stoplist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandrewrporter%2Fwikipedia-stoplist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrewrporter%2Fwikipedia-stoplist/lists"}