{"adoption": {"forks": 2753, "observed_at": "2026-08-28T04:11:09.729639+00:00", "stars": 15371}, "canonical_url": "https://ross.abutalabs.com/products/andkret-cookbook", "card": {"archived": false, "artifact_type": "learning-resource", "description": "The Data Engineering Cookbook", "domain": ["big-data", "tutorials", "education"], "enriched": true, "function": ["developer-tools", "etl", "data-science"], "health_score": 76, "homepage": "https://learndataengineering.com/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["andkret/Cookbook"], "name": "andkret/Cookbook", "platform": ["cross-platform"], "pushed_at": "2026-07-23T10:28:49+00:00", "repo": "andkret/Cookbook", "stars": 15371, "tags": ["data-engineering", "cookbook", "interview-preparation", "career", "best-practices", "free-book"], "topics": ["data-engineer", "data-engineering", "big-data", "best-practices", "cookbook"], "urls": [], "use_cases": ["learn how to become a data engineer", "prepare for data engineering interviews", "find data sources for portfolio projects", "understand data platform architecture and ETL pipelines", "review data engineering best practices for cloud platforms", "find recommended books, courses, and podcasts for data engineering"], "what_it_is": "The Data Engineering Cookbook is a free, open-source book by Andreas Kretz covering the skills, tools, and best practices needed to become a data engineer. It includes sections on basic and advanced engineering skills, hands-on tutorials, case studies, cloud platform best practices, portfolio project data sources, and interview questions.", "when_to_avoid": ["you need a runnable software tool or library rather than learning material", "you want a structured, certified course with hands-on labs (the companion Academy is paid)", "you need deep, up-to-date documentation for a specific tool like Spark or Kafka"], "when_to_choose": ["you are transitioning into data engineering from software development or another field", "you want a free, curated roadmap of data engineering skills and tools", "you need interview questions and case studies for job preparation", "you are looking for ideas and data sources for portfolio projects"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/andkret-cookbook", "repo": "andkret/Cookbook", "role": "main", "score": 75}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.729639+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:06:20.649458+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5cb93a3f39def70b70ff9dabbcf1e85858a5e1d3a1f2712e0842c930cc95f0c6", "fetched_at": "2026-08-28T04:11:09.729639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andkret/Cookbook"}, {"content_hash": "b096fe4deaddcbd6d7e48daeaa1110120192521a8e157677c939b00f90e20f38", "fetched_at": "2026-08-29T08:04:19.550216+00:00", "kind": "homepage", "missing": false, "url": "https://learndataengineering.com/"}, {"content_hash": "60e4d9074211b39a8712d7059f262f63eac09c64c2350219c003808f558df4f3", "fetched_at": "2026-08-29T08:04:19.564459+00:00", "kind": "site_page", "missing": false, "url": "https://hello.learndataengineering.com/quickstart-guide"}, {"content_hash": "7419e3755e995b0b55a4f8274c4b2560868c3deccf2d9fa4583a015e5b296d45", "fetched_at": "2026-08-29T08:04:19.559704+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/free-labs"}, {"content_hash": "ac1e5aab912434904423b96ec88d8092dec25857c4018fc0b7682247f48741ab", "fetched_at": "2026-08-29T08:04:19.561955+00:00", "kind": "site_page", "missing": false, "url": "https://learndataengineering.com/p/academy"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 94, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2733, "days_push": 41, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 75, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}