{"id":24630709,"url":"https://github.com/kirlewn/dataengineeringzoomcamp2025","last_synced_at":"2026-04-11T14:02:35.428Z","repository":{"id":274064817,"uuid":"913812761","full_name":"Kirlewn/DataEngineeringZoomCamp2025","owner":"Kirlewn","description":"This repository is my work as I follow along with the Data Engineering Zoomcamp found here: https://github.com/DataTalksClub/data-engineering-zoomcamp","archived":false,"fork":false,"pushed_at":"2025-02-04T16:12:59.000Z","size":24467,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-04T17:22:47.282Z","etag":null,"topics":["data-engineering","docker","docker-compose","docker-container","etl-pipeline","postgresql","terraform"],"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/Kirlewn.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}},"created_at":"2025-01-08T11:59:07.000Z","updated_at":"2025-02-04T16:13:04.000Z","dependencies_parsed_at":"2025-01-24T17:40:08.607Z","dependency_job_id":null,"html_url":"https://github.com/Kirlewn/DataEngineeringZoomCamp2025","commit_stats":null,"previous_names":["kirlewn/dataengineeringzoomcamp2025"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kirlewn%2FDataEngineeringZoomCamp2025","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kirlewn%2FDataEngineeringZoomCamp2025/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kirlewn%2FDataEngineeringZoomCamp2025/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kirlewn%2FDataEngineeringZoomCamp2025/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kirlewn","download_url":"https://codeload.github.com/Kirlewn/DataEngineeringZoomCamp2025/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244560384,"owners_count":20472218,"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":["data-engineering","docker","docker-compose","docker-container","etl-pipeline","postgresql","terraform"],"created_at":"2025-01-25T07:12:42.033Z","updated_at":"2025-12-30T20:57:33.940Z","avatar_url":"https://github.com/Kirlewn.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DataEngineeringZoomCamp2025\nThis repository is my work as I follow along with the Data Engineering Zoomcamp found here: https://github.com/DataTalksClub/data-engineering-zoomcamp\n\nThe goal of the course is to create a working Data Engineering pipeline. \n\n![image](https://github.com/user-attachments/assets/ad9cfca8-3d4e-4d9b-ba8e-943c1f5157ee)\n\n# Modules\n\n## Module 1: Containerization and Infrastructure as Code\n- Introduction to GCP\n- Docker and Docker Compose\n- Running PostgreSQL with Docker\n- Infrastructure setup with Terraform\n\n## Module 2: Workflow Orchestration\n- Data Lakes and Workflow Orchestration\n- Workflow orchestration with Kestra\n\n## Workshop 1: Data Ingestion\n- API reading and pipeline scalability\n- Data normalization and incremental loading\n\n## Module 3: Data Warehousing\n- Introduction to BigQuery\n- Partitioning, clustering, and best practices\n- Machine learning in BigQuery\n\n## Module 4: Analytics Engineering\n- dbt (data build tool) with PostgreSQL \u0026 BigQuery\n- Testing, documentation, and deployment\n- Data visualization with Metabase\n\n## Module 5: Batch Processing\n- Introduction to Apache Spark\n- DataFrames and SQL\n- Internals of GroupBy and Joins\n\n## Module 6: Streaming\n- Introduction to Kafka\n- Kafka Streams and KSQL\n- Schema management with Avro\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkirlewn%2Fdataengineeringzoomcamp2025","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkirlewn%2Fdataengineeringzoomcamp2025","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkirlewn%2Fdataengineeringzoomcamp2025/lists"}