{"id":20093061,"url":"https://github.com/sankamuk/pysparkcheatsheet","last_synced_at":"2025-05-06T04:31:57.246Z","repository":{"id":129020285,"uuid":"244126770","full_name":"sankamuk/PysparkCheatsheet","owner":"sankamuk","description":"PySpark Cheatsheet","archived":false,"fork":false,"pushed_at":"2023-01-18T03:56:58.000Z","size":11781,"stargazers_count":36,"open_issues_count":0,"forks_count":27,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-09T08:23:25.563Z","etag":null,"topics":["apache-spark","deltalake","python","structured-streaming"],"latest_commit_sha":null,"homepage":"","language":"Python","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/sankamuk.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":"2020-03-01T10:13:30.000Z","updated_at":"2025-01-20T06:15:15.000Z","dependencies_parsed_at":"2023-08-28T01:36:05.550Z","dependency_job_id":null,"html_url":"https://github.com/sankamuk/PysparkCheatsheet","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/sankamuk%2FPysparkCheatsheet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankamuk%2FPysparkCheatsheet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankamuk%2FPysparkCheatsheet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankamuk%2FPysparkCheatsheet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sankamuk","download_url":"https://codeload.github.com/sankamuk/PysparkCheatsheet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252622211,"owners_count":21777942,"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":["apache-spark","deltalake","python","structured-streaming"],"created_at":"2024-11-13T16:45:42.645Z","updated_at":"2025-05-06T04:31:57.230Z","avatar_url":"https://github.com/sankamuk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Pyspark Cheatsheet\n\n![Apache Spark](https://img.shields.io/badge/lang-Python-brightgreen.svg)\n![Python](https://img.shields.io/badge/lib-Spark-brightgreen.svg)\n\nDocumentation for using PySpark. \n\n- [Overview](General-Overview) : General overview.\n\n- [Spark Dataframe](Spark-SQL) : Different use case implementation.\n\n- [Spark Structured Streaming](Structured-Streaming) : Overview and use case implementation.\n\n- [Delta Lake](Delta-Lake) : Overview and use case implementation.\n\n\n\n\u003e Any one can add content if relevent.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsankamuk%2Fpysparkcheatsheet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsankamuk%2Fpysparkcheatsheet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsankamuk%2Fpysparkcheatsheet/lists"}