{"adoption": {"forks": 652, "observed_at": "2026-08-28T04:03:31.076064+00:00", "stars": 1082}, "canonical_url": "https://ross.abutalabs.com/products/data-algorithms-book", "card": {"archived": false, "artifact_type": "learning-resource", "description": " MapReduce, Spark, Java, and Scala for Data Algorithms Book", "domain": ["big-data", "data-science", "microservices", "tutorials"], "enriched": true, "function": ["machine-learning", "data-science", "etl", "developer-tools"], "health_score": 20, "homepage": "http://mapreduce4hackers.com", "language": "Java", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["mahmoudparsian/data-algorithms-book"], "name": "mahmoudparsian/data-algorithms-book", "platform": ["jvm", "python", "cross-platform"], "pushed_at": "2024-10-14T00:19:15+00:00", "repo": "mahmoudparsian/data-algorithms-book", "stars": 1082, "tags": ["mapreduce", "apache-spark", "pyspark", "hadoop", "scala", "distributed-algorithms", "book-source-code", "design-patterns"], "topics": ["hadoop-mapreduce", "java", "distributed-computing", "scala", "mapreduce", "data-algorithms", "python", "machine-learning", "pyspark", "distributed-algorithms", "mappers", "reducers", "apache-hadoop", "apache-spark", "design-patterns", "partitioning"], "urls": [], "use_cases": ["learn mapreduce with hadoop and spark examples", "find pyspark distributed algorithm code samples", "study spark machine learning algorithm implementations", "get source code for the data algorithms book", "learn mapreduce design patterns in java and scala", "examples of submitting spark jobs from java"], "what_it_is": "The official source code repository for Mahmoud Parsian's O'Reilly books 'Data Algorithms' and related titles, containing MapReduce, Spark, Java, Scala, and PySpark examples for distributed algorithms. It serves as a companion codebase with runnable examples, build scripts, and bonus chapters.", "when_to_avoid": ["you need a production-ready distributed computing library rather than educational example code", "you want a maintained framework with API stability guarantees", "you need solutions for a specific Spark version other than the one the examples target"], "when_to_choose": ["you are reading the Data Algorithms or PySpark Algorithms books and want the accompanying code", "you want worked examples of MapReduce and Spark distributed algorithms in Java, Scala, or Python", "you are learning big data processing with Hadoop and Spark through hands-on examples"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/data-algorithms-book", "repo": "mahmoudparsian/data-algorithms-book", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.076064+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:51:16.628586+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e69496d3edc669d98fe5cf16200435b63b704267ec3b79bb49514a647a964d44", "fetched_at": "2026-08-28T04:03:31.076064+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mahmoudparsian/data-algorithms-book"}, {"content_hash": "2a982d55672e6aea1320fd8f684eee7144da00dbd903ad18c3d593900f4ab407", "fetched_at": "2026-08-29T12:53:25.124618+00:00", "kind": "homepage", "missing": false, "url": "http://mapreduce4hackers.com"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+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": 4410, "days_push": 689, "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}}