{"id":18398892,"url":"https://github.com/lyeoni/nlp-cheatsheets","last_synced_at":"2025-04-12T15:56:51.001Z","repository":{"id":196956108,"uuid":"280092908","full_name":"lyeoni/nlp-cheatsheets","owner":"lyeoni","description":null,"archived":false,"fork":false,"pushed_at":"2020-08-26T06:34:32.000Z","size":10,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-16T02:44:08.858Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lyeoni.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}},"created_at":"2020-07-16T08:06:06.000Z","updated_at":"2024-07-28T10:43:37.000Z","dependencies_parsed_at":"2023-09-28T11:47:29.199Z","dependency_job_id":null,"html_url":"https://github.com/lyeoni/nlp-cheatsheets","commit_stats":null,"previous_names":["lyeoni/nlp-cheatsheets"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyeoni%2Fnlp-cheatsheets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyeoni%2Fnlp-cheatsheets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyeoni%2Fnlp-cheatsheets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyeoni%2Fnlp-cheatsheets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lyeoni","download_url":"https://codeload.github.com/lyeoni/nlp-cheatsheets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248592979,"owners_count":21130305,"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":[],"created_at":"2024-11-06T02:24:47.767Z","updated_at":"2025-04-12T15:56:50.970Z","avatar_url":"https://github.com/lyeoni.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# nlp-cheatsheets\n\n## Usage\n\n#### split_corpus.sh\nSplit given corpus into random train/test subsets. `TRAIN_RATIO` represent the proportion of the dataset to include in the train split.\n\n```shell\n$ scripts/split_corpus.sh [INPUT_FILE] [OUTPUT_FILE] [TRAIN_RATIO]\n\n# example\n$ scripts/split_corpus.sh sample/zero_to_hundred.txt sample/zero_to_hundred 0.8\nSplit corpus into train(#80) and test(#20) corpus, respectively.\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flyeoni%2Fnlp-cheatsheets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flyeoni%2Fnlp-cheatsheets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flyeoni%2Fnlp-cheatsheets/lists"}