{"adoption": {"forks": 518, "observed_at": "2026-08-28T04:07:08.892375+00:00", "stars": 2663}, "canonical_url": "https://ross.abutalabs.com/products/dpark", "card": {"archived": true, "artifact_type": "framework", "description": "Python clone of Spark,  a MapReduce alike framework in Python", "domain": ["big-data", "microservices", "data-science"], "enriched": true, "function": ["etl", "streaming", "data-science", "workflow-automation"], "health_score": 10, "homepage": null, "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["douban/dpark"], "name": "douban/dpark", "platform": ["python", "cli"], "pushed_at": "2020-12-25T10:36:06+00:00", "repo": "douban/dpark", "stars": 2663, "tags": ["mapreduce", "spark-clone", "rdd", "mesos", "batch-processing", "iterative-computation", "data-engineering", "linux"], "topics": ["bigdata", "mapreduce", "dpark", "stream-processing", "spark", "python"], "urls": [], "use_cases": ["run mapreduce word count jobs in python", "process large datasets on a mesos cluster", "run iterative algorithms like pagerank in python", "batch etl over text files without learning scala spark", "debug distributed jobs via a web ui with stage graphs"], "what_it_is": "DPark is a Python clone of Apache Spark, providing a MapReduce-like distributed computing framework that supports iterative computation. Jobs written with DparkContext can run locally or on a Mesos cluster without code changes.", "when_to_avoid": ["you need modern Spark features like DataFrames, SQL, or MLlib", "you want an actively developed project - the last release was 2020", "your infrastructure uses Kubernetes or YARN instead of Mesos"], "when_to_choose": ["you want Spark-style RDD programming in pure Python", "your cluster runs Mesos and you prefer Python over Scala/Java", "you need lightweight MapReduce with iterative computation support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dpark", "repo": "douban/dpark", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:08.892375+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:18:20.115247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "829601821a02d108b35fb4db1cfc900acddf4a561b81ec396844821a42a72129", "fetched_at": "2026-08-28T04:07:08.892375+00:00", "kind": "readme", "missing": false, "url": "https://github.com/douban/dpark"}, {"content_hash": "3ae26260e880698f45b5a7e98678ec2abd4f3ecd31f675182f84c4a17c3e8cbf", "fetched_at": "2026-08-29T10:01:02.807629+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dpark/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5257, "days_push": 2077, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}