{"id":16446477,"url":"https://github.com/fbukevin/hadoop-cooccurrence","last_synced_at":"2025-04-27T02:32:58.953Z","repository":{"id":20549922,"uuid":"23829694","full_name":"fbukevin/hadoop-cooccurrence","owner":"fbukevin","description":"This is a hadoop project implementing words co-occurrence algorithm.","archived":false,"fork":false,"pushed_at":"2014-09-10T07:38:05.000Z","size":2144,"stargazers_count":4,"open_issues_count":0,"forks_count":5,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-04T20:22:12.947Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Java","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/fbukevin.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}},"created_at":"2014-09-09T10:52:20.000Z","updated_at":"2021-10-13T00:14:46.000Z","dependencies_parsed_at":"2022-08-31T00:20:10.316Z","dependency_job_id":null,"html_url":"https://github.com/fbukevin/hadoop-cooccurrence","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/fbukevin%2Fhadoop-cooccurrence","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fbukevin%2Fhadoop-cooccurrence/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fbukevin%2Fhadoop-cooccurrence/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fbukevin%2Fhadoop-cooccurrence/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fbukevin","download_url":"https://codeload.github.com/fbukevin/hadoop-cooccurrence/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251080744,"owners_count":21533142,"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":"2024-10-11T09:47:42.584Z","updated_at":"2025-04-27T02:32:56.659Z","avatar_url":"https://github.com/fbukevin.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"Introduction\n===\nThis is a project that implements co-occurrence of text words algorithm with Hadoop. Here we follow the tutorial of book \u003cData-Intensive Processing with MapReduce\u003e implementing Pairs and Stripes algorithm. \n\nUsage\n===\n`$ yarn jar \u003chadoop\u003e.jar [pairs | stripes] \u003cinput_file\u003e` \n\ntutorial\n===\n* Book - [Data-Intensive Processing with MapReduce](http://www.amazon.com/Data-Intensive-Processing-MapReduce-Synthesis-Technologies/dp/1608453421)\n* Original Blog - [Calculating a Co-Occurrence Matrix With Hadoop](http://codingjunkie.net/cooccurrence/)\n* Adapter to this repo - [以 Hadoop 計算共現矩陣](http://veck.logdown.com/posts/231257-hadoop-co-occurrence-matrix-calculation)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffbukevin%2Fhadoop-cooccurrence","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffbukevin%2Fhadoop-cooccurrence","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffbukevin%2Fhadoop-cooccurrence/lists"}