{"adoption": {"forks": 395, "observed_at": "2026-08-28T04:05:39.048505+00:00", "stars": 1806}, "canonical_url": "https://ross.abutalabs.com/products/bigdata-growth", "card": {"archived": false, "artifact_type": "learning-resource", "description": "大数据知识仓库涉及到数据仓库建模、实时计算、大数据、数据中台、系统设计、Java、算法等。", "domain": ["big-data", "tutorials"], "enriched": true, "function": ["documentation"], "health_score": 67, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["collabH/bigdata-growth"], "name": "collabH/bigdata-growth", "platform": ["python"], "pushed_at": "2026-04-18T13:12:36+00:00", "repo": "collabH/bigdata-growth", "stars": 1806, "tags": ["big-data", "data-warehouse", "flink", "spark", "hadoop", "interview-preparation", "knowledge-base", "chinese", "data-engineering"], "topics": ["flink", "kafka", "hive", "mapreduce", "spark", "olap", "kudu", "hadoop", "hbase", "debezium", "hdfs", "bigdata", "hudi", "bigdatalearning"], "urls": [], "use_cases": ["learn big data from scratch", "prepare for big data engineer interviews", "understand flink checkpoint mechanism", "study data warehouse modeling", "learn hudi iceberg paimon data lakehouse", "get a spark streaming learning path", "review hive tuning strategies"], "what_it_is": "A curated Chinese-language knowledge repository covering big data topics such as data warehouse modeling, stream processing, data lakes, and distributed systems, with notes on Flink, Spark, Hadoop, Hudi, Paimon, and Iceberg. It also includes an AI skill assistant for interview prep and study guidance.", "when_to_avoid": ["you need production-ready code or tooling rather than documentation", "you need English-language materials"], "when_to_choose": ["you want structured study notes on the Hadoop/Flink/Spark ecosystem", "you are preparing for big data interviews", "you need data lake (Hudi/Paimon/Iceberg) learning material"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bigdata-growth", "repo": "collabH/bigdata-growth", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:39.048505+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:21:29.274057+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeb94dce2fe8064252723e4beac8ccaabb3d0c9632f928e1c418063756c1a9d", "fetched_at": "2026-08-28T04:05:39.048505+00:00", "kind": "readme", "missing": false, "url": "https://github.com/collabH/bigdata-growth"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 78, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2275, "days_push": 137, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}