{"id":30151470,"url":"https://github.com/jbloch100/scalable-analytics-pipeline","last_synced_at":"2026-05-19T05:41:18.557Z","repository":{"id":307216063,"uuid":"1026937963","full_name":"jbloch100/scalable-analytics-pipeline","owner":"jbloch100","description":"Python-based real-time data pipeline using Kafka and Spark for streaming analytics","archived":false,"fork":false,"pushed_at":"2025-07-30T02:13:16.000Z","size":4,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-11T11:02:18.861Z","etag":null,"topics":["big-data","data-pipeline","kafka","python","spark","stream-processing"],"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/jbloch100.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}},"created_at":"2025-07-27T00:22:10.000Z","updated_at":"2025-07-30T02:13:20.000Z","dependencies_parsed_at":"2025-07-30T04:42:32.625Z","dependency_job_id":null,"html_url":"https://github.com/jbloch100/scalable-analytics-pipeline","commit_stats":null,"previous_names":["jbloch100/scalable-analytics-pipeline"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jbloch100/scalable-analytics-pipeline","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloch100%2Fscalable-analytics-pipeline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloch100%2Fscalable-analytics-pipeline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloch100%2Fscalable-analytics-pipeline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloch100%2Fscalable-analytics-pipeline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jbloch100","download_url":"https://codeload.github.com/jbloch100/scalable-analytics-pipeline/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloch100%2Fscalable-analytics-pipeline/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279010342,"owners_count":26084738,"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","status":"online","status_checked_at":"2025-10-12T02:00:06.719Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["big-data","data-pipeline","kafka","python","spark","stream-processing"],"created_at":"2025-08-11T11:02:15.287Z","updated_at":"2025-10-12T05:10:53.322Z","avatar_url":"https://github.com/jbloch100.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Scalable Analytics Pipeline\n\n## Overview\nSimulates a simple analytics event processor for backend engineering. Processes mock ad events in real-time and generates aggregated metrics.\n\n## Features\n- Processes click/view/impression events\n- Aggregates data in real-time\n- CLI output summary\n\n## Run\n```bash\npython src/main.py\n```\n\n## Test\n```bash\npython -m unittest tests/test_main.py\n```\n\n---\n\n## Docker\n\n### Build\n```bash\ndocker build -t scalable-analytics-pipeline .\n```\n\n### Run\n```bash\ndocker run --rm scalable-analytics-pipeline\n```\n\n### Test\n```bash\ndocker run --rm scalable-analytics-pipeline python -m unittest discover -s tests\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjbloch100%2Fscalable-analytics-pipeline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjbloch100%2Fscalable-analytics-pipeline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjbloch100%2Fscalable-analytics-pipeline/lists"}