{"id":18034727,"url":"https://github.com/bobluppes/spark-baseline","last_synced_at":"2025-04-04T23:12:45.731Z","repository":{"id":111442099,"uuid":"319753397","full_name":"bobluppes/spark-baseline","owner":"bobluppes","description":null,"archived":false,"fork":false,"pushed_at":"2020-12-08T20:47:23.000Z","size":1,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-02-10T07:30:35.686Z","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/bobluppes.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":"2020-12-08T20:29:57.000Z","updated_at":"2020-12-08T20:47:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"84af5153-34b3-4597-970e-26726d8a6557","html_url":"https://github.com/bobluppes/spark-baseline","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/bobluppes%2Fspark-baseline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bobluppes%2Fspark-baseline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bobluppes%2Fspark-baseline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bobluppes%2Fspark-baseline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bobluppes","download_url":"https://codeload.github.com/bobluppes/spark-baseline/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247261605,"owners_count":20910108,"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":"2024-10-30T11:13:53.085Z","updated_at":"2025-04-04T23:12:45.705Z","avatar_url":"https://github.com/bobluppes.png","language":"Scala","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Spark Baseline\nMeasures the execution times of reading a parquet file and performing a sql query encompassing a filter and an aggregate sum operation.\n\n## Setup\nFour parquet files with 10e5, 50e6, 100e6, and 150e6 rows should be present in a datafolder specified by `baseFile`. These filenames should be appended by `10M`, `50M`, `100M`, and `150M` respectively.\n\nTODO: Make base file path input parameter and determine sizes dynamically\n\n## Running\nTo execute the baseline, run\n\n    sbt compile\n    sbt run","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbobluppes%2Fspark-baseline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbobluppes%2Fspark-baseline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbobluppes%2Fspark-baseline/lists"}