{"id":22492669,"url":"https://github.com/garystafford/dataproc-python-demo","last_synced_at":"2025-07-13T08:09:14.749Z","repository":{"id":74258097,"uuid":"160757177","full_name":"garystafford/dataproc-python-demo","owner":"garystafford","description":"Demonstration of Google Cloud Dataproc for running PySpark jobs","archived":false,"fork":false,"pushed_at":"2018-12-16T16:35:50.000Z","size":564,"stargazers_count":4,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"master","last_synced_at":"2023-08-05T02:22:51.109Z","etag":null,"topics":["cloud-dataproc","dataproc","gcp","google","pyspark","python"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/garystafford.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2018-12-07T02:03:05.000Z","updated_at":"2022-06-05T16:48:45.000Z","dependencies_parsed_at":null,"dependency_job_id":"8c773975-a826-46d5-8232-98c726ce6d10","html_url":"https://github.com/garystafford/dataproc-python-demo","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/garystafford/dataproc-python-demo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-python-demo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-python-demo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-python-demo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-python-demo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/garystafford","download_url":"https://codeload.github.com/garystafford/dataproc-python-demo/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-python-demo/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265108514,"owners_count":23712466,"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":["cloud-dataproc","dataproc","gcp","google","pyspark","python"],"created_at":"2024-12-06T18:20:22.061Z","updated_at":"2025-07-13T08:09:14.741Z","avatar_url":"https://github.com/garystafford.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Google Cloud Dataproc Python/PySpark Demo\n\nCode repository for post, [Big Data Analytics with Java and Python, using Cloud Dataproc, Google’s Fully-Managed Spark and Hadoop Service](https://wp.me/p1RD28-63y).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgarystafford%2Fdataproc-python-demo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgarystafford%2Fdataproc-python-demo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgarystafford%2Fdataproc-python-demo/lists"}