{"adoption": {"forks": 182, "observed_at": "2026-08-28T04:03:46.350972+00:00", "stars": 1149}, "canonical_url": "https://ross.abutalabs.com/products/dstk", "card": {"archived": false, "artifact_type": "dataset", "description": "A collection of the best open data sets and open-source tools for data science", "domain": ["data-science", "awesome-lists"], "enriched": true, "function": ["data-science", "developer-tools"], "health_score": 20, "homepage": "http://www.datasciencetoolkit.org/", "language": "Ruby", "license": null, "license_family": "other", "maturity": "abandoned", "member_repos": ["petewarden/dstk"], "name": "petewarden/dstk", "platform": ["cross-platform"], "pushed_at": "2016-08-29T12:16:48+00:00", "repo": "petewarden/dstk", "stars": 1149, "tags": ["awesome-list", "open-data", "curated-resources", "geospatial-data", "algorithms"], "topics": [], "urls": [], "use_cases": ["find open datasets for a data science project", "discover open-source data science tools", "locate free geocoding and text analysis data", "get started with public data sources", "find resources for machine learning datasets"], "what_it_is": "A curated collection of the best open datasets and open-source tools for data science, associated with the Data Science Toolkit project. It serves as a reference index rather than a runnable library.", "when_to_avoid": ["you need an actively maintained tool or library", "you need a supported software dependency with a license", "you need up-to-date data sources"], "when_to_choose": ["you want a curated starting point for open data and data science tooling", "you need pointers to free datasets instead of building one"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dstk", "repo": "petewarden/dstk", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.350972+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:33:46.587282+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0e81bcb0e506f7c485e3500292c7bce86870f0d1802e8154f52ab96e170f24bc", "fetched_at": "2026-08-29T12:38:45.391052+00:00", "kind": "homepage", "missing": false, "url": "http://www.datasciencetoolkit.org/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license", "no_readme"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5658, "days_push": 3656, "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}}