{"adoption": {"forks": 854, "observed_at": "2026-08-28T04:05:40.672619+00:00", "stars": 1818}, "canonical_url": "https://ross.abutalabs.com/products/hadoop-cluster-docker", "card": {"archived": false, "artifact_type": "infra-config", "description": "Run Hadoop Custer within Docker Containers", "domain": ["big-data", "microservices"], "enriched": true, "function": ["container-runtime", "deployment", "developer-tools"], "health_score": 20, "homepage": null, "language": "Shell", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["kiwenlau/hadoop-cluster-docker"], "name": "kiwenlau/hadoop-cluster-docker", "platform": [], "pushed_at": "2024-07-01T21:01:04+00:00", "repo": "kiwenlau/hadoop-cluster-docker", "stars": 1818, "tags": ["hadoop", "docker-images", "big-data-cluster", "shell-scripts", "learning", "containers", "devops", "docker", "linux", "shell"], "topics": [], "urls": [], "use_cases": ["set up a hadoop cluster locally with docker", "learn how hadoop multi-node clusters work", "run a 3-node hadoop cluster for testing", "spin up an arbitrary-size hadoop cluster in containers", "demo mapreduce wordcount on hadoop", "sandbox environment for big data experiments"], "what_it_is": "A set of Docker images and shell scripts for spinning up a multi-node Hadoop cluster (1 master, N slaves) inside Docker containers. It includes scripts to start containers, launch Hadoop, resize the cluster, and run a sample wordcount job.", "when_to_avoid": ["you need a production-grade Hadoop deployment with resource management and persistence", "you want a modern big data stack (e.g., Kubernetes-based Spark or Hadoop operators)"], "when_to_choose": ["you want a quick local Hadoop cluster for learning or demos without provisioning real machines", "you need a reproducible multi-node Hadoop sandbox for testing MapReduce jobs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/hadoop-cluster-docker", "repo": "kiwenlau/hadoop-cluster-docker", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.672619+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:20:08.629486+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de933206e398847ac9a52be915365bb5d86842b33fb6a6be5bcc7b7ecacbbe67", "fetched_at": "2026-08-28T04:05:40.672619+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kiwenlau/hadoop-cluster-docker"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4122, "days_push": 793, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}