{"id":28186493,"url":"https://github.com/taylorwood/adrdemo","last_synced_at":"2025-10-20T03:58:06.873Z","repository":{"id":14704415,"uuid":"17424675","full_name":"taylorwood/ADRDemo","owner":"taylorwood","description":"Simple F# demonstration of text classification","archived":false,"fork":false,"pushed_at":"2015-06-27T16:26:08.000Z","size":164,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-05-14T04:18:32.390Z","etag":null,"topics":["f-sharp","text-classification","tf-idf"],"latest_commit_sha":null,"homepage":"http://taylorwood.github.io/2015/06/15/text-classification.html","language":"F#","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/taylorwood.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2014-03-05T02:01:44.000Z","updated_at":"2017-12-29T19:11:23.000Z","dependencies_parsed_at":"2022-07-12T15:13:23.630Z","dependency_job_id":null,"html_url":"https://github.com/taylorwood/ADRDemo","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/taylorwood%2FADRDemo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taylorwood%2FADRDemo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taylorwood%2FADRDemo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taylorwood%2FADRDemo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/taylorwood","download_url":"https://codeload.github.com/taylorwood/ADRDemo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254485042,"owners_count":22078767,"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":["f-sharp","text-classification","tf-idf"],"created_at":"2025-05-16T07:10:22.744Z","updated_at":"2025-10-20T03:58:01.850Z","avatar_url":"https://github.com/taylorwood.png","language":"F#","readme":"ADRDemo\n=======\n\nA simple F# demonstration of Automated Document Recognition using techniques like text tokenization, n-grams, TF-IDF weighting, CSV parsing, and text classification.\n\nThe code assumes the existence of some training data, in the form of plaintext files organized into folders by category:\n\n- \\TrainingData\n  - \\CategoryA\n    - \\Sample1.txt\n    - \\Sample2.txt\n  - \\CategoryB\n    - \\SampleA.txt\n    \n...and a plain text file to be classified: \"unknown.txt\".\n\nIt also assumes the existence of a word whitelist CSV file, but this can be easily changed to a blacklist (\"stopwords\") or removed altogether.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaylorwood%2Fadrdemo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftaylorwood%2Fadrdemo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaylorwood%2Fadrdemo/lists"}