{"id":13704084,"url":"https://github.com/preset-io/dbt_github_archive_bigquery","last_synced_at":"2025-04-13T12:51:32.775Z","repository":{"id":172077556,"uuid":"648819307","full_name":"preset-io/dbt_github_archive_bigquery","owner":"preset-io","description":"A dbt project to make GitHub archive events useful","archived":false,"fork":false,"pushed_at":"2023-06-28T01:12:52.000Z","size":573,"stargazers_count":3,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-01-28T23:09:57.489Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/preset-io.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}},"created_at":"2023-06-02T22:39:35.000Z","updated_at":"2023-12-12T11:27:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"ff0eaae3-112b-4f93-a923-6b98436d6a63","html_url":"https://github.com/preset-io/dbt_github_archive_bigquery","commit_stats":null,"previous_names":["preset-io/dbt_github_archive_bigquery"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/preset-io%2Fdbt_github_archive_bigquery","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/preset-io%2Fdbt_github_archive_bigquery/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/preset-io%2Fdbt_github_archive_bigquery/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/preset-io%2Fdbt_github_archive_bigquery/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/preset-io","download_url":"https://codeload.github.com/preset-io/dbt_github_archive_bigquery/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248717251,"owners_count":21150388,"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":"2024-08-02T21:01:04.017Z","updated_at":"2025-04-13T12:51:32.748Z","avatar_url":"https://github.com/preset-io.png","language":"Python","readme":"# dbt reference implementation for Github Archive\n\n\u003cimg src=\"https://github.com/preset-io/dbt_github_archive_bigquery/assets/487433/91891250-821c-40b7-b9e7-8215382aeefe\"/\u003e\n\nThis is a quick and dirty reference implementation to make sense of the\nGitHub public information made available by the\n[GH Archive](https://www.gharchive.org/) through BigQuery public datasets.\n\nThat data is a bit rough in a bunch of yearly/monthly/daily archived tables\nthat are fairly large (TBs) and you probably want to bring only the orgs/repos\nyou care about in a single table, and hopefully do some decent incremental\nloads to make this queryable.\n\nThis dbt project does all this:\n- brings all the archived tables in one centralized table in your local BigQuery project\n- partitions by day, does incremental loads\n- allows you to select just the repos you need\n- rebuils some state tables off of the events table\n- parses out important information out of JSON blobs\n- get rid of redundant or not-so-useful-for-analytics information\n","funding_links":[],"categories":["Sample Projects"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpreset-io%2Fdbt_github_archive_bigquery","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpreset-io%2Fdbt_github_archive_bigquery","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpreset-io%2Fdbt_github_archive_bigquery/lists"}