{"id":17560127,"url":"https://github.com/juanmanuel-tirado/pyspark-tutorial","last_synced_at":"2026-05-09T10:37:55.698Z","repository":{"id":219094912,"uuid":"748156147","full_name":"juanmanuel-tirado/pyspark-tutorial","owner":"juanmanuel-tirado","description":"This is a collection of PySpark tutorials","archived":false,"fork":false,"pushed_at":"2024-02-13T21:15:34.000Z","size":656,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-04T04:30:43.446Z","etag":null,"topics":["jupyter-notebook","machine-learning","ml","pyspark","python","spark","tutorial"],"latest_commit_sha":null,"homepage":"https://jmtirado.net","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/juanmanuel-tirado.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2024-01-25T11:48:59.000Z","updated_at":"2024-01-25T11:53:54.000Z","dependencies_parsed_at":"2024-12-09T14:43:42.655Z","dependency_job_id":"97ce8277-ea63-4f13-a4ea-553d570edbbc","html_url":"https://github.com/juanmanuel-tirado/pyspark-tutorial","commit_stats":{"total_commits":7,"total_committers":2,"mean_commits":3.5,"dds":0.4285714285714286,"last_synced_commit":"c1b570562dea4b0674c2f0853605b0c448caaf5f"},"previous_names":["juanmanuel-tirado/pyspark-tutorial"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juanmanuel-tirado%2Fpyspark-tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juanmanuel-tirado%2Fpyspark-tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juanmanuel-tirado%2Fpyspark-tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juanmanuel-tirado%2Fpyspark-tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/juanmanuel-tirado","download_url":"https://codeload.github.com/juanmanuel-tirado/pyspark-tutorial/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246169499,"owners_count":20734672,"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":["jupyter-notebook","machine-learning","ml","pyspark","python","spark","tutorial"],"created_at":"2024-10-21T11:10:28.152Z","updated_at":"2026-05-09T10:37:50.643Z","avatar_url":"https://github.com/juanmanuel-tirado.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pyspark-tutorial\nThis repo contains a collection of PySpark tutorials and examples.\n\n- [PySpark MLlib](pyspark-ml.ipynb)\n  Code examples of how to use Spark MLlib with PySpark.\n- [PySpark FMA](pyspark_fma.ipynb)\n  Does a song with a long title have a longer duration? Learn how to answer this question using PySpark and the FMA dataset.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuanmanuel-tirado%2Fpyspark-tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjuanmanuel-tirado%2Fpyspark-tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuanmanuel-tirado%2Fpyspark-tutorial/lists"}