{"adoption": {"forks": 208, "observed_at": "2026-08-28T04:03:17.909097+00:00", "stars": 1030}, "canonical_url": "https://ross.abutalabs.com/products/data-engineering-projects", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Personal Data Engineering Projects", "domain": ["databases", "big-data", "tutorials"], "enriched": true, "function": ["etl", "database", "web-scraping", "data-science", "workflow-automation"], "health_score": 20, "homepage": null, "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["alanchn31/Data-Engineering-Projects"], "name": "alanchn31/Data-Engineering-Projects", "platform": ["python", "cloud"], "pushed_at": "2023-02-08T00:44:31+00:00", "repo": "alanchn31/Data-Engineering-Projects", "stars": 1030, "tags": ["data-warehouse", "data-lake", "airflow", "spark", "cassandra", "redshift", "mongodb", "star-schema", "udacity-nanodegree", "jupyter-notebook", "data-engineering"], "topics": ["data-lake", "ingest-data", "data-engineering", "data-warehouse", "cassandra", "aws-redshift", "mongodb", "scrapy", "spark", "airflow", "postgres", "data-engineering-nanodegree", "star-schema", "data-modeling"], "urls": [], "use_cases": ["learn data engineering through hands-on projects", "see examples of ETL pipelines with Airflow", "understand star schema data modeling in Postgres", "learn how to build a data lake with Spark and S3", "practice web scraping with Scrapy into MongoDB", "study for a data engineering nanodegree", "see how to load data into AWS Redshift"], "what_it_is": "A collection of personal data engineering projects completed as part of Udacity's Data Engineering Nanodegree, covering ETL into Postgres, Cassandra, MongoDB, Redshift, and S3 data lakes with Spark and Airflow. It includes course notes and example notebooks demonstrating data modeling, warehousing, and pipeline orchestration.", "when_to_avoid": ["you need production-ready, maintained software with a license", "you want a reusable library rather than educational notebooks", "you need up-to-date tooling, as the projects were last updated in early 2023"], "when_to_choose": ["you want worked examples of common data engineering patterns", "you are following or reviewing Udacity's data engineering curriculum", "you need reference code for ETL with Spark, Airflow, Cassandra, or Redshift"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/data-engineering-projects", "repo": "alanchn31/Data-Engineering-Projects", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/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": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.909097+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/Data-Engineering-Projects"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.180879+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc89ea6ede76b53d6d4282d791f9f0926a127c84f24980131f72459c7c18ba23", "fetched_at": "2026-08-28T04:03:17.909097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alanchn31/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": 2326, "days_push": 1303, "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}}