{"adoption": {"forks": 421, "observed_at": "2026-08-28T04:07:24.834770+00:00", "stars": 2842}, "canonical_url": "https://ross.abutalabs.com/products/sklearn-pandas", "card": {"archived": false, "artifact_type": "library", "description": "Pandas integration with sklearn", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["machine-learning", "etl", "serialization"], "health_score": 20, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["scikit-learn-contrib/sklearn-pandas"], "name": "scikit-learn-contrib/sklearn-pandas", "platform": ["python"], "pushed_at": "2023-06-08T06:48:29+00:00", "repo": "scikit-learn-contrib/sklearn-pandas", "stars": 2842, "tags": ["scikit-learn", "pandas", "dataframe", "feature-engineering", "data-preprocessing", "column-transformer", "data-engineering"], "topics": [], "urls": [], "use_cases": ["apply sklearn transformers to pandas dataframe columns", "build preprocessing pipelines for mixed numeric and categorical data", "map dataframe columns to feature transformations", "integrate pandas with scikit-learn workflows", "preprocess tabular data before model training", "handle categorical encoding in sklearn pipelines"], "what_it_is": "A Python library that bridges pandas DataFrames and scikit-learn by mapping DataFrame columns to sklearn transformations. Its DataFrameMapper lets you declare per-column transformers that are applied and recombined into feature matrices.", "when_to_avoid": ["you only use modern scikit-learn, where sklearn.compose.ColumnTransformer covers most needs natively", "your data is not in pandas DataFrames"], "when_to_choose": ["you work with pandas DataFrames and want declarative column-wise sklearn transformations", "you need a mapper that predates or complements sklearn's ColumnTransformer with extra conveniences like feature naming"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/sklearn-pandas", "repo": "scikit-learn-contrib/sklearn-pandas", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.834770+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:37:14.472421+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2c1bfd05c08ed24e24103d8ec74a214f79ea822dcdb2abae004389c61716b132", "fetched_at": "2026-08-28T04:07:24.834770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/scikit-learn-contrib/sklearn-pandas"}, {"content_hash": "ce5be381d937caa7ecb4ff90e2f6977eb3877d142c43ae4ec9b42f5de5859201", "fetched_at": "2026-08-29T09:52:46.539052+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sklearn-pandas/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4881, "days_push": 1182, "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}}