{"id":24685044,"url":"https://github.com/dipeshdimi/data-science-systems-project","last_synced_at":"2026-05-19T04:40:58.630Z","repository":{"id":200157449,"uuid":"704931303","full_name":"dipeshdimi/Data-Science-Systems-Project","owner":"dipeshdimi","description":null,"archived":false,"fork":false,"pushed_at":"2023-10-14T15:57:29.000Z","size":9678,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-21T20:46:37.697Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Scala","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/dipeshdimi.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}},"created_at":"2023-10-14T14:42:39.000Z","updated_at":"2023-10-14T15:16:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"ac2d5947-0d1a-4795-ba7a-0fd1e46f68a8","html_url":"https://github.com/dipeshdimi/Data-Science-Systems-Project","commit_stats":null,"previous_names":["dipeshdimi/data-science-systems-project"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dipeshdimi/Data-Science-Systems-Project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dipeshdimi%2FData-Science-Systems-Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dipeshdimi%2FData-Science-Systems-Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dipeshdimi%2FData-Science-Systems-Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dipeshdimi%2FData-Science-Systems-Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dipeshdimi","download_url":"https://codeload.github.com/dipeshdimi/Data-Science-Systems-Project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dipeshdimi%2FData-Science-Systems-Project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33202116,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-18T09:27:30.708Z","status":"online","status_checked_at":"2026-05-19T02:00:06.763Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2025-01-26T15:17:38.707Z","updated_at":"2026-05-19T04:40:58.614Z","avatar_url":"https://github.com/dipeshdimi.png","language":"Scala","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data-Science-Systems-Project\n# Team Members Details :-\n    1. Dipesh Mishra (20bcs043) \n    2. Mahendra Singh Puniya (20bcs082) \n    3. Ravikant (20bcs110) \n    4. Rishabh Gautam (20bcs112)\n\n# How to use this Project\nTo use this project, follow these steps :-\n1. Data Preparation: Ensure you have the Amazon Product Co-Purchasing Network dataset ready. You can download it from https://snap.stanford.edu/data/amazon0302.txt.gz.\n\n2. Environment Setup: Set up your environment with Apache Spark (version 3.5.0), Scala (version 2.11.12), and OpenJDK.\n\n3. Code Execution: Run the provided code. It will load the dataset, identify connected components, calculate their sizes, sort them, and display the results.\n\n4. Interpret Results: Review the printed results in the console. These results will provide insights into the co-purchasing behavior patterns and clusters within the Amazon Co-Purchasing Network.\n\nRemember to update the location of the downloaded dataset in the program file while using. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdipeshdimi%2Fdata-science-systems-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdipeshdimi%2Fdata-science-systems-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdipeshdimi%2Fdata-science-systems-project/lists"}