{"adoption": {"forks": 985, "observed_at": "2026-08-28T04:04:31.169622+00:00", "stars": 1365}, "canonical_url": "https://ross.abutalabs.com/products/pyspark-examples", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Pyspark RDD, DataFrame and Dataset Examples in Python language", "domain": ["big-data", "tutorials", "data-science"], "enriched": true, "function": ["developer-tools", "data-science", "etl"], "health_score": 54, "homepage": "https://sparkbyexamples.com", "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["spark-examples/pyspark-examples"], "name": "spark-examples/pyspark-examples", "platform": ["python", "cross-platform", "cli"], "pushed_at": "2025-12-07T16:27:23+00:00", "repo": "spark-examples/pyspark-examples", "stars": 1365, "tags": ["pyspark", "apache-spark", "rdd", "dataframe", "examples", "tutorial", "spark-sql", "big-data", "data-engineering"], "topics": [], "urls": [], "use_cases": ["learn pyspark dataframe operations with runnable examples", "understand rdd vs dataframe in spark with python code", "find example pyspark join groupby and filter code", "practice spark sql queries in python", "prepare for data engineering interviews on spark", "set up a local pyspark learning environment"], "what_it_is": "A collection of runnable Python example scripts demonstrating PySpark RDD, DataFrame, and SQL operations, companion to the SparkByExamples tutorial site. Each example is a single-file script with sample data for learning Apache Spark in Python.", "when_to_avoid": ["you need a production data pipeline framework rather than learning material", "you want a maintained library with a license and API guarantees", "you need Scala, Java, or R Spark examples instead of Python"], "when_to_choose": ["you are learning PySpark and want copy-paste runnable example scripts", "you need quick reference snippets for RDD, DataFrame, or Spark SQL operations", "you follow the sparkbyexamples.com tutorials and want the companion code"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pyspark-examples", "repo": "spark-examples/pyspark-examples", "role": "main", "score": 57}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:31.169622+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:41:17.134165+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "58dc036ba1177240ebe116827857830abe7eab5ed92e738d05503f0f6396ff50", "fetched_at": "2026-08-28T04:04:31.169622+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spark-examples/pyspark-examples"}, {"content_hash": "12f7a01c37c910fd66db3d74f59f8d99bdd9b12734bbf0ac6ea31af4ed35153e", "fetched_at": "2026-08-29T11:58:47.447336+00:00", "kind": "homepage", "missing": false, "url": "https://sparkbyexamples.com"}, {"content_hash": "2443520a3ed2365dbd6d602dc827471661c5c7d6a440e996f3c7e5325fa64c99", "fetched_at": "2026-08-29T11:58:47.463124+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/about-sparkbyexamples"}, {"content_hash": "71380dc8f4646f0d141b8eb13549b39ea27632dc3a0d63c00d2be8f465a19ce4", "fetched_at": "2026-08-29T11:58:47.467840+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-installation-on-windows"}, {"content_hash": "a9732d62e40fb6a9c8d5bc9bf5c1ba0a594dc12cd440e2413b7caebe5bd311c7", "fetched_at": "2026-08-29T11:58:47.469755+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/spark-installation-on-linux-ubuntu"}, {"content_hash": "5d57168c2ce64ac38dfe5495f443503f0c92af795ef05ab6c1efd8649b1282d9", "fetched_at": "2026-08-29T11:58:47.471665+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/install-apache-spark-on-mac"}, {"content_hash": "cd24e8739793a742246a1deb082f28b9e31da54acaf3e28b9c741022ae2ec9af", "fetched_at": "2026-08-29T11:58:47.473464+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/spark/apache-spark-3-5-0-features"}, {"content_hash": "417090292fd670e73595e0459b5f268d3adcaf1890e58da1958a3e996139b3e1", "fetched_at": "2026-08-29T11:58:47.465778+00:00", "kind": "site_page", "missing": false, "url": "https://sparkbyexamples.com/membership-account/membership-levels"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 56, "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": 2472, "days_push": 269, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 57, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}