{"adoption": {"forks": 2905, "observed_at": "2026-08-28T04:07:45.914412+00:00", "stars": 3144}, "canonical_url": "https://ross.abutalabs.com/products/spark-the-definitive-guide", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Spark: The Definitive Guide's Code Repository", "domain": ["big-data", "tutorials"], "enriched": true, "function": ["data-science", "etl", "developer-tools"], "health_score": 20, "homepage": "http://shop.oreilly.com/product/0636920034957.do", "language": "Scala", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["databricks/Spark-The-Definitive-Guide"], "name": "databricks/Spark-The-Definitive-Guide", "platform": ["jvm", "python", "cross-platform"], "pushed_at": "2020-08-26T08:17:35+00:00", "repo": "databricks/Spark-The-Definitive-Guide", "stars": 3144, "tags": ["apache-spark", "book-code", "databricks", "scala", "pyspark", "notebooks", "data-engineering"], "topics": [], "urls": [], "use_cases": ["learn apache spark from scratch", "find example code for spark dataframes and sql", "run spark book examples on databricks", "study structured streaming and mllib examples", "get sample datasets for practicing spark"], "what_it_is": "The official code repository for the book 'Spark: The Definitive Guide' by Bill Chambers and Matei Zaharia, containing example code and datasets organized by chapter and language. It is a companion learning resource for Apache Spark, runnable locally or on Databricks notebooks.", "when_to_avoid": ["you need a production Spark library or framework", "you want up-to-date examples for the latest Spark versions", "you need a maintained tool rather than book companion material"], "when_to_choose": ["you are reading Spark: The Definitive Guide and want its code", "you want runnable Spark examples in Scala and Python", "you want sample datasets to practice Spark locally or on Databricks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/spark-the-definitive-guide", "repo": "databricks/Spark-The-Definitive-Guide", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.914412+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:25:59.471521+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4c08062590d50317118716f18bd5cc93a82a64dd3137ddce3553d3ffc9e95c0f", "fetched_at": "2026-08-28T04:07:45.914412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/Spark-The-Definitive-Guide"}], "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": 3397, "days_push": 2198, "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}}