{"adoption": {"forks": 144, "observed_at": "2026-08-28T04:03:17.750515+00:00", "stars": 1030}, "canonical_url": "https://ross.abutalabs.com/products/dumbo", "card": {"archived": false, "artifact_type": "library", "description": "Python module that allows one to easily write and run Hadoop programs.", "domain": ["big-data", "microservices"], "enriched": true, "function": ["etl", "developer-tools"], "health_score": 20, "homepage": "http://projects.dumbotics.com/dumbo", "language": "Python", "license": null, "license_family": "other", "maturity": "abandoned", "member_repos": ["klbostee/dumbo"], "name": "klbostee/dumbo", "platform": ["python", "cross-platform"], "pushed_at": "2018-01-09T10:05:41+00:00", "repo": "klbostee/dumbo", "stars": 1030, "tags": ["hadoop", "mapreduce", "hadoop-streaming", "data-pipeline", "data-engineering", "linux"], "topics": [], "urls": [], "use_cases": ["write mapreduce jobs in python", "run python code on hadoop clusters", "process large datasets with hadoop streaming", "simplify hadoop streaming development", "batch process log files with mapreduce"], "what_it_is": "Dumbo is a Python module that makes writing and running Hadoop Streaming programs easy, providing a convenient Python API for MapReduce programs. It wraps Hadoop's streaming interface so developers can write mappers and reducers in plain Python.", "when_to_avoid": ["starting a new big data project - use Spark, Dask, or modern frameworks instead", "your cluster does not run Hadoop", "you need actively maintained software with support for recent Python versions"], "when_to_choose": ["you maintain a legacy Hadoop Streaming stack and want a Pythonic API", "you need to run simple MapReduce jobs in Python on an existing Hadoop cluster"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dumbo", "repo": "klbostee/dumbo", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.750515+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:34.228857+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5638c78fb2a923fdc2d45664a580678463b2a75d2b6090f5757684aa566534ea", "fetched_at": "2026-08-28T04:03:17.750515+00:00", "kind": "readme", "missing": false, "url": "https://github.com/klbostee/dumbo"}, {"content_hash": "aba61f56e400a88ea40932de00a9795284bad208e6dbe873c80f10527d452fd5", "fetched_at": "2026-08-29T13:07:26.704955+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dumbo/json"}], "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": 6654, "days_push": 3158, "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}}