{"adoption": {"forks": 411, "observed_at": "2026-08-28T04:06:56.823537+00:00", "stars": 2499}, "canonical_url": "https://ross.abutalabs.com/products/category_encoders", "card": {"archived": false, "artifact_type": "library", "description": "A library of sklearn compatible categorical variable encoders", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["machine-learning", "data-science", "etl"], "health_score": 100, "homepage": "http://contrib.scikit-learn.org/category_encoders/", "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["scikit-learn-contrib/category_encoders"], "name": "scikit-learn-contrib/category_encoders", "platform": ["python"], "pushed_at": "2026-08-25T23:13:51+00:00", "repo": "scikit-learn-contrib/category_encoders", "stars": 2499, "tags": ["categorical-encoding", "sklearn-transformers", "feature-engineering", "target-encoding", "pandas"], "topics": [], "urls": [], "use_cases": ["encode categorical columns for machine learning models", "target encode high-cardinality categorical features", "one-hot encode pandas dataframes in sklearn pipelines", "convert string categories to numbers for sklearn", "avoid target leakage when encoding categories", "pickle and reuse a fitted categorical encoder"], "what_it_is": "A scikit-learn-contrib library providing a collection of sklearn-compatible transformers for encoding categorical variables into numeric form using techniques like one-hot, binary, hashing, target, and CatBoost encoding. It supports pandas DataFrames, works in sklearn pipelines, and includes both supervised and unsupervised encoders.", "when_to_avoid": ["your data has no categorical features", "you need deep-learning-native embedding layers instead of tabular encoding", "you are outside the Python/sklearn ecosystem"], "when_to_choose": ["you need sklearn-pipeline-compatible categorical transformers", "you work with pandas DataFrames and want column-level control", "you need supervised encoders like target, CatBoost, or James-Stein encoding"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/category_encoders", "repo": "scikit-learn-contrib/category_encoders", "role": "main", "score": 94}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:56.823537+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:27:00.340826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "410fc57cd3e6cd4fdf9e6565434043af42514dcf8325405077f9b690f6427bd3", "fetched_at": "2026-08-28T04:06:56.823537+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/category_encoders"}, {"content_hash": "3492b0148215547f06e072bc429fc133816d039be65a411b8d29b3764d64f2e7", "fetched_at": "2026-08-29T10:09:32.090269+00:00", "kind": "homepage", "missing": false, "url": "http://contrib.scikit-learn.org/category_encoders/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 83}, "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": 3930, "days_push": 8, "days_rel": 38, "gap_med": 54, "n_releases_24m": 8}, "score": 94, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}