{"id":21651784,"url":"https://github.com/dev-vivekkumarverma/pyspark-databricks","last_synced_at":"2026-05-05T14:11:15.923Z","repository":{"id":257711926,"uuid":"859105915","full_name":"dev-vivekkumarverma/pyspark-databricks","owner":"dev-vivekkumarverma","description":"spark, databricks, kafka, batch and stream-processing","archived":false,"fork":false,"pushed_at":"2025-01-31T11:52:26.000Z","size":11903,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-09T05:35:17.360Z","etag":null,"topics":["airflow","batch-processing","csv","databricks","delta-tables","distributed-computing","etl-pipeline","file-formats","json","kafka","medallion-architecture","parquet","pyspark","python3","s3","spark","stream-processing","unity-catalog","watermarking"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/dev-vivekkumarverma.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-09-18T05:09:18.000Z","updated_at":"2025-02-25T07:14:18.000Z","dependencies_parsed_at":"2024-09-18T07:50:26.043Z","dependency_job_id":"601b4ef8-a778-4654-8e69-3da6987bc20f","html_url":"https://github.com/dev-vivekkumarverma/pyspark-databricks","commit_stats":null,"previous_names":["dev-vivekkumarverma/databricks"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dev-vivekkumarverma/pyspark-databricks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev-vivekkumarverma%2Fpyspark-databricks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev-vivekkumarverma%2Fpyspark-databricks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev-vivekkumarverma%2Fpyspark-databricks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev-vivekkumarverma%2Fpyspark-databricks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dev-vivekkumarverma","download_url":"https://codeload.github.com/dev-vivekkumarverma/pyspark-databricks/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev-vivekkumarverma%2Fpyspark-databricks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32652689,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-05T11:29:49.557Z","status":"ssl_error","status_checked_at":"2026-05-05T11:29:48.587Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["airflow","batch-processing","csv","databricks","delta-tables","distributed-computing","etl-pipeline","file-formats","json","kafka","medallion-architecture","parquet","pyspark","python3","s3","spark","stream-processing","unity-catalog","watermarking"],"created_at":"2024-11-25T07:49:32.480Z","updated_at":"2026-05-05T14:11:15.905Z","avatar_url":"https://github.com/dev-vivekkumarverma.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pyspark-databricks\n\n`topics covered`\n-  pyspark\n-  databricks\n-  kafka\n-  csv, json, parquet, delta, text\n-  batch data processing\n-  stream-processing\n-  s3, ADLS-v2\n-  unity catalog\n-  watermarking\n-  query optimization\n-  AQE ( adaptive query execution )\n  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdev-vivekkumarverma%2Fpyspark-databricks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdev-vivekkumarverma%2Fpyspark-databricks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdev-vivekkumarverma%2Fpyspark-databricks/lists"}