{"adoption": {"forks": 1337, "observed_at": "2026-08-28T04:10:59.713541+00:00", "stars": 12749}, "canonical_url": "https://ross.abutalabs.com/products/data-engineer-roadmap", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Roadmap to becoming a data engineer in 2021", "domain": ["tutorials", "cloud-computing", "big-data"], "enriched": true, "function": ["documentation", "developer-tools"], "health_score": 20, "homepage": "https://datastack.tv", "language": null, "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["datastacktv/data-engineer-roadmap"], "name": "datastacktv/data-engineer-roadmap", "platform": ["cross-platform"], "pushed_at": "2022-01-25T21:09:00+00:00", "repo": "datastacktv/data-engineer-roadmap", "stars": 12749, "tags": ["roadmap", "study-guide", "career", "data-engineer", "infographic", "data-engineering"], "topics": ["data-engineer-roadmap", "data-engineering", "cloud", "roadmap"], "urls": [], "use_cases": ["become a data engineer", "learn data engineering skills", "plan a data engineering career path", "find which data tools to study", "understand the modern data stack landscape"], "what_it_is": "A visual roadmap and study guide outlining the tools, skills, and landscape of modern data engineering as of 2021. It is a curated reference document (images plus text versions) rather than runnable software.", "when_to_avoid": ["you need runnable code or a software tool", "you need up-to-date 2024+ tooling guidance since the roadmap targets 2021", "you want interactive lessons rather than a static reference"], "when_to_choose": ["you want a structured overview of data engineering skills and tools", "you are a beginner planning what to learn", "you want a shareable visual curriculum for data engineering"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/data-engineer-roadmap", "repo": "datastacktv/data-engineer-roadmap", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.713541+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:13:49.309639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8a0af20d7c73b329945c541e6cf6985d24c59280ce847ecb3d6dc45218b44c6", "fetched_at": "2026-08-28T04:10:59.713541+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datastacktv/data-engineer-roadmap"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2191, "days_push": 1681, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}