{"adoption": {"forks": 815, "observed_at": "2026-08-28T04:05:59.140356+00:00", "stars": 1957}, "canonical_url": "https://ross.abutalabs.com/products/spark-ml-source-analysis", "card": {"archived": false, "artifact_type": "learning-resource", "description": "spark ml 算法原理剖析以及具体的源码实现分析", "domain": ["machine-learning", "big-data", "tutorials"], "enriched": true, "function": ["machine-learning", "documentation"], "health_score": 20, "homepage": "https://github.com/endymecy/spark-ml-source-analysis", "language": null, "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["endymecy/spark-ml-source-analysis"], "name": "endymecy/spark-ml-source-analysis", "platform": ["jvm", "python"], "pushed_at": "2019-03-25T13:24:10+00:00", "repo": "endymecy/spark-ml-source-analysis", "stars": 1957, "tags": ["spark", "spark-ml", "source-code-analysis", "distributed-machine-learning", "chinese-language"], "topics": ["spark", "machine-learning", "source-analysis"], "urls": [], "use_cases": ["understand how spark mllib algorithms are implemented internally", "learn distributed implementations of machine learning algorithms", "study spark ml source code for classification and clustering algorithms", "learn how k-means or ALS work in spark", "prepare for spark machine learning interviews", "understand gradient descent and L-BFGS implementations in spark"], "what_it_is": "A Chinese-language tutorial collection analyzing the principles and source code of Spark MLlib's machine learning algorithms. It covers classification, regression, clustering, dimensionality reduction, feature engineering, and optimization with their distributed implementations.", "when_to_avoid": ["you need up-to-date coverage of Spark 3.x or the newer spark.ml DataFrame API", "you want runnable production code rather than analysis articles", "you need English-language documentation"], "when_to_choose": ["you work with Spark 1.6/2.x MLlib and want deep algorithm and source-level understanding", "you prefer Chinese-language explanations of ML theory plus code walkthroughs", "you want to learn how ML algorithms are distributed across a cluster"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/spark-ml-source-analysis", "repo": "endymecy/spark-ml-source-analysis", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.140356+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:06:01.201976+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6a1acf2d8098dfe03264f837cef560c1528fa1d140b9850061b4b53c63995b96", "fetched_at": "2026-08-28T04:05:59.140356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}, {"content_hash": "1ef4adeb7d3ec1866aa72220167cd1188a860435cdc43e006d41b301e8c8b4ca", "fetched_at": "2026-08-29T10:46:19.149624+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/endymecy/spark-ml-source-analysis"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3890, "days_push": 2718, "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}}