{"adoption": {"forks": 2518, "observed_at": "2026-08-28T04:08:07.410952+00:00", "stars": 3498}, "canonical_url": "https://ross.abutalabs.com/products/hadoop-book", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Example source code accompanying O'Reilly's \"Hadoop: The Definitive Guide\" by Tom White", "domain": ["big-data", "tutorials"], "enriched": true, "function": ["developer-tools", "data-science", "etl"], "health_score": 20, "homepage": "http://www.hadoopbook.com/", "language": "Makefile", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["tomwhite/hadoop-book"], "name": "tomwhite/hadoop-book", "platform": ["jvm", "cross-platform"], "pushed_at": "2020-03-17T05:11:30+00:00", "repo": "tomwhite/hadoop-book", "stars": 3498, "tags": ["hadoop", "mapreduce", "big-data", "book-examples", "oreilly", "sample-code", "distributed-computing", "data-engineering"], "topics": ["hadoop", "book", "o-reilly"], "urls": [], "use_cases": ["learn hadoop mapreduce with worked examples", "find sample code for Hadoop: The Definitive Guide", "practice writing pig and hive scripts", "get example datasets for hadoop exercises", "understand the hadoop ecosystem hands-on", "build hadoop example jars with maven"], "what_it_is": "Example source code accompanying O'Reilly's 'Hadoop: The Definitive Guide' by Tom White, covering the Apache Hadoop ecosystem including Hadoop 2, Pig, Hive, Avro, and ZooKeeper. It provides buildable Maven-based sample code and sample datasets for the book's chapters.", "when_to_avoid": ["you need a production Hadoop framework or library", "you want up-to-date examples for modern Spark or Hadoop 3", "you need maintained, supported software rather than book companion code"], "when_to_choose": ["you are reading the book and want to run its examples", "you want classic MapReduce, Pig, and Hive code samples", "you are learning Hadoop 2 ecosystem tools from scratch"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/hadoop-book", "repo": "tomwhite/hadoop-book", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.410952+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:35:51.608466+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "40482cdaf933235b8b069f744e7a478cd68861cf367eed333c34c39cb0e804f0", "fetched_at": "2026-08-28T04:08:07.410952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tomwhite/hadoop-book"}, {"content_hash": "6cef6075f76fffbdae7b07af09c030cd0e4078341c6c7ede6b35c278ca78d225", "fetched_at": "2026-08-29T09:29:57.014746+00:00", "kind": "homepage", "missing": false, "url": "http://www.hadoopbook.com/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 6260, "days_push": 2360, "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}}