{"adoption": {"forks": 797, "observed_at": "2026-08-28T04:04:36.928836+00:00", "stars": 1399}, "canonical_url": "https://ross.abutalabs.com/products/learningsparkv2", "card": {"archived": false, "artifact_type": "learning-resource", "description": "This is the github repo for Learning Spark: Lightning-Fast Data Analytics [2nd Edition]", "domain": ["big-data", "tutorials", "data-science"], "enriched": true, "function": ["data-science", "machine-learning", "streaming", "etl"], "health_score": 22, "homepage": "https://learning.oreilly.com/library/view/learning-spark-2nd/9781492050032/", "language": "Scala", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["databricks/LearningSparkV2"], "name": "databricks/LearningSparkV2", "platform": ["jvm", "python", "cross-platform"], "pushed_at": "2025-01-28T04:30:40+00:00", "repo": "databricks/LearningSparkV2", "stars": 1399, "tags": ["apache-spark", "spark-sql", "structured-streaming", "mllib", "delta-lake", "mlflow", "book-examples", "scala", "notebooks", "data-engineering"], "topics": ["apache-spark", "spark", "structured-streaming", "spark-sql", "spark-mllib", "mllib", "mlflow", "delta-lake"], "urls": [], "use_cases": ["learn apache spark from scratch", "find spark structured streaming examples", "study spark sql code samples", "learn mllib machine learning with spark", "get working examples of delta lake and mlflow", "follow along with the learning spark book exercises"], "what_it_is": "The official companion repository for the book 'Learning Spark: Lightning-Fast Data Analytics, 2nd Edition', containing example Spark applications and notebooks. It provides buildable Scala JARs per chapter plus Databricks-style notebooks covering Spark SQL, structured streaming, MLlib, Delta Lake, and MLflow.", "when_to_avoid": ["you need production-ready Spark tooling rather than educational examples", "you want comprehensive documentation instead of book companion code", "you need a maintained library with an API to depend on"], "when_to_choose": ["you are reading Learning Spark 2nd Edition and want its runnable code", "you want curated, book-quality examples of Spark SQL, streaming, and MLlib", "you prefer learning via notebooks or standalone spark-submit applications"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/learningsparkv2", "repo": "databricks/LearningSparkV2", "role": "main", "score": 34}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.928836+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:39:10.515631+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f5d49384f0e9ebb0d2085c15f77a823521a50eeff8a9f8248cdfb46bb19c50c0", "fetched_at": "2026-08-28T04:04:36.928836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/LearningSparkV2"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 3, "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": 2761, "days_push": 582, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 34, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}