{"id":25377124,"url":"https://github.com/terrierscript/archive-qiita","last_synced_at":"2026-02-23T23:32:12.261Z","repository":{"id":145723905,"uuid":"250003276","full_name":"terrierscript/archive-qiita","owner":"terrierscript","description":null,"archived":false,"fork":false,"pushed_at":"2020-03-25T14:37:46.000Z","size":13032,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-15T04:41:31.247Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/terrierscript.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2020-03-25T14:37:28.000Z","updated_at":"2020-03-25T14:49:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"74647cc7-5231-4bf0-8a09-b2f74bc5b7cb","html_url":"https://github.com/terrierscript/archive-qiita","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/terrierscript%2Farchive-qiita","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/terrierscript%2Farchive-qiita/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/terrierscript%2Farchive-qiita/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/terrierscript%2Farchive-qiita/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/terrierscript","download_url":"https://codeload.github.com/terrierscript/archive-qiita/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248020593,"owners_count":21034459,"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":"2025-02-15T04:41:12.308Z","updated_at":"2026-02-23T23:32:07.241Z","avatar_url":"https://github.com/terrierscript.png","language":"HTML","readme":"@eleven_2012 \n文字列からの数値化についてはgensimの`corpora.Dictionary`を利用しました。\nざっくり主要な部分のコードとしては、こんな感じでサンプルデータを結合したデータを食わせました\n\n```py\nfrom gensim import corpora\n\nchars = [ list(r.strip()) for r in concatinated_sample_string_data ]\ndic = corpora.Dictionary(chars)\n```\n\nここらへんのやり方はTensorFlowで同様のことを行っていた下記スクリプトも参考の一端としましたので、こちらも参考になるかもしれません\nhttps://github.com/dennybritz/sentiment-analysis/blob/master/utils/ymr_data.py#L36\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fterrierscript%2Farchive-qiita","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fterrierscript%2Farchive-qiita","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fterrierscript%2Farchive-qiita/lists"}