{"adoption": {"forks": 2391, "observed_at": "2026-08-28T04:08:28.421400+00:00", "stars": 3893}, "canonical_url": "https://ross.abutalabs.com/products/learning-spark", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Example code from Learning Spark book", "domain": ["big-data", "tutorials"], "enriched": true, "function": ["developer-tools", "data-science", "etl"], "health_score": 74, "homepage": null, "language": "Java", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["databricks/learning-spark"], "name": "databricks/learning-spark", "platform": ["jvm", "python", "cross-platform"], "pushed_at": "2026-06-30T07:11:37+00:00", "repo": "databricks/learning-spark", "stars": 3893, "tags": ["apache-spark", "book-examples", "scala", "java", "pyspark", "sample-code", "data-engineering"], "topics": [], "urls": [], "use_cases": ["learn Apache Spark from book examples", "run sample Spark jobs in Java Scala and Python", "see how to build and submit Spark assemblies with sbt or maven", "follow along with the Learning Spark book exercises", "reference pyspark example scripts"], "what_it_is": "Example code accompanying the O'Reilly 'Learning Spark' book, with implementations in Java, Scala, and Python. The examples target Spark 1.3 and demonstrate core Spark APIs and usage patterns.", "when_to_avoid": ["you need examples for modern Spark versions or Spark SQL/DataFrame APIs", "you want production-ready Spark application templates"], "when_to_choose": ["you are reading the Learning Spark book and want runnable code", "you want simple, small examples for learning Spark fundamentals"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/learning-spark", "repo": "databricks/learning-spark", "role": "main", "score": 73}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:28.421400+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:25:36.060345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a433e2e43e99bf74b2a30bca5fdb4572e9fc05cdb998b40e553944a9cc29558f", "fetched_at": "2026-08-28T04:08:28.421400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/learning-spark"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "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": 4461, "days_push": 64, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 73, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}