{"id":28824127,"url":"https://github.com/pavithra19/apache_spark_people_data_processor","last_synced_at":"2025-06-19T01:05:08.341Z","repository":{"id":298598842,"uuid":"998884276","full_name":"pavithra19/apache_spark_people_data_processor","owner":"pavithra19","description":"This project is a data processing application built with Apache Spark and Scala. This is designed to efficiently process, analyze and transform large datasets related to people data. It leverages Spark’s distributed computing capabilities to handle scalable data ingestion, cleaning and reporting. Shell scripts are included for hadoop deployment.","archived":false,"fork":false,"pushed_at":"2025-06-11T22:52:40.000Z","size":1902,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-11T23:40:08.325Z","etag":null,"topics":["apachespark","dataengineering","hadoop","hdfs","scala"],"latest_commit_sha":null,"homepage":"https://github.com/pavithra19/apache_spark_people_data_processor","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/pavithra19.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,"zenodo":null}},"created_at":"2025-06-09T12:05:44.000Z","updated_at":"2025-06-11T22:52:43.000Z","dependencies_parsed_at":"2025-06-11T23:40:14.722Z","dependency_job_id":"c1afd9d3-e9b2-440b-aadc-394c526b424a","html_url":"https://github.com/pavithra19/apache_spark_people_data_processor","commit_stats":null,"previous_names":["pavithra19/apache_spark_people_data_processor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pavithra19/apache_spark_people_data_processor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pavithra19%2Fapache_spark_people_data_processor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pavithra19%2Fapache_spark_people_data_processor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pavithra19%2Fapache_spark_people_data_processor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pavithra19%2Fapache_spark_people_data_processor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pavithra19","download_url":"https://codeload.github.com/pavithra19/apache_spark_people_data_processor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pavithra19%2Fapache_spark_people_data_processor/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260660115,"owners_count":23043488,"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":["apachespark","dataengineering","hadoop","hdfs","scala"],"created_at":"2025-06-19T01:05:00.929Z","updated_at":"2025-06-19T01:05:03.326Z","avatar_url":"https://github.com/pavithra19.png","language":"Scala","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpavithra19%2Fapache_spark_people_data_processor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpavithra19%2Fapache_spark_people_data_processor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpavithra19%2Fapache_spark_people_data_processor/lists"}