{"adoption": {"forks": 593, "observed_at": "2026-08-28T04:06:00.759633+00:00", "stars": 1969}, "canonical_url": "https://ross.abutalabs.com/products/udacity-data-engineering-projects", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Few projects related to Data Engineering including Data Modeling, Infrastructure setup on cloud, Data Warehousing and Data Lake development.", "domain": ["big-data", "cloud-computing", "databases"], "enriched": true, "function": ["etl", "database", "data-science", "infrastructure-as-code", "workflow-automation"], "health_score": 20, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["san089/Udacity-Data-Engineering-Projects"], "name": "san089/Udacity-Data-Engineering-Projects", "platform": ["python", "cloud"], "pushed_at": "2022-08-26T00:09:15+00:00", "repo": "san089/Udacity-Data-Engineering-Projects", "stars": 1969, "tags": ["data-modeling", "data-warehouse", "data-lake", "apache-airflow", "apache-cassandra", "postgresql", "amazon-redshift", "spark", "aws-emr", "udacity", "tutorial-projects", "etl-pipelines", "data-engineering", "aws"], "topics": ["data", "data-engineering", "data-engineering-pipeline", "etl-pipeline", "cassandra-database", "postgresql-database", "data-modeling", "data-warehouse", "data-lake", "airflow", "airflow-operators", "cluster", "cassandra", "infrastructure", "postgres", "aws", "aws-ec2", "aws-sdk", "aws-s3", "cloudformation"], "urls": [], "use_cases": ["learn data engineering by example", "build an ETL pipeline with Python and Postgres", "set up a data warehouse on AWS Redshift", "create a data lake with Spark on EMR", "orchestrate scheduled ETL jobs with Airflow", "practice data modeling with Cassandra", "study for a data engineering interview"], "what_it_is": "A collection of Udacity Data Engineering Nanodegree projects covering data modeling with Postgres and Cassandra, cloud data warehousing with Redshift, data lakes with Spark on EMR, and pipeline orchestration with Airflow. Each project includes Python ETL code and AWS infrastructure setup examples.", "when_to_avoid": ["you need production-ready, maintained data engineering tooling", "you want a library or framework to import into your own codebase", "you need up-to-date cloud practices, as the projects were last updated in 2022"], "when_to_choose": ["you want hands-on, project-based learning for data engineering concepts", "you need reference implementations of ETL pipelines on AWS", "you are following or supplementing the Udacity Data Engineering Nanodegree"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/udacity-data-engineering-projects", "repo": "san089/Udacity-Data-Engineering-Projects", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.759633+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:05:10.339205+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7ee1edd9a462e01153650d3142af595344b8ba36983fa3d3a69febd387c699d2", "fetched_at": "2026-08-28T04:06:00.759633+00:00", "kind": "readme", "missing": false, "url": "https://github.com/san089/Udacity-Data-Engineering-Projects"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2417, "days_push": 1469, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}