{"id":17867224,"url":"https://github.com/s/bigdataanalysis","last_synced_at":"2025-06-19T07:39:54.467Z","repository":{"id":71889208,"uuid":"47897851","full_name":"s/BigDataAnalysis","owner":"s","description":"A project to analyze Enron Email Dataset with MapReduce pattern","archived":false,"fork":false,"pushed_at":"2015-12-19T08:05:03.000Z","size":18,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-02T22:27:50.741Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/s.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":"2015-12-12T22:57:10.000Z","updated_at":"2025-02-24T01:09:47.000Z","dependencies_parsed_at":"2023-06-05T18:45:44.737Z","dependency_job_id":null,"html_url":"https://github.com/s/BigDataAnalysis","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/s/BigDataAnalysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/s%2FBigDataAnalysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/s%2FBigDataAnalysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/s%2FBigDataAnalysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/s%2FBigDataAnalysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/s","download_url":"https://codeload.github.com/s/BigDataAnalysis/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/s%2FBigDataAnalysis/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260709960,"owners_count":23050312,"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":"2024-10-28T09:45:37.770Z","updated_at":"2025-06-19T07:39:49.457Z","avatar_url":"https://github.com/s.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BigDataAnalysis\nThis project is done for the course Big Data Analysis in [Computer Engineering Department](http://ce.yildiz.edu.tr) of [YTU](http://yildiz.edu.tr).\n\n##Functions\n- Finding each person's mail count\n- Finding word count in each person's mails\n- Finding most used 30 words for each person\n- Finding word count in all mails\n- Clustering persons with k-Means clustering algorithm using their most used 30 words as features.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fs%2Fbigdataanalysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fs%2Fbigdataanalysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fs%2Fbigdataanalysis/lists"}