{"adoption": {"forks": 275, "observed_at": "2026-08-28T04:05:16.803707+00:00", "stars": 1650}, "canonical_url": "https://ross.abutalabs.com/products/skrub", "card": {"archived": false, "artifact_type": "library", "description": "Machine learning with dataframes", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["machine-learning", "data-science", "etl"], "health_score": 100, "homepage": "https://skrub-data.org/", "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["skrub-data/skrub"], "name": "skrub-data/skrub", "platform": ["python"], "pushed_at": "2026-08-25T15:12:35+00:00", "repo": "skrub-data/skrub", "stars": 1650, "tags": ["dataframes", "data-preprocessing", "data-cleaning", "scikit-learn", "dirty-data", "tabular-data"], "topics": ["machine-learning", "data-science", "data-cleaning", "data", "data-preparation", "data-preprocessing", "data-analysis", "dirty-data", "data-wrangling", "dataframe", "dataframes"], "urls": [], "use_cases": ["preprocess messy dataframes for machine learning", "encode high-cardinality categorical columns", "clean dirty tabular data before training models", "build sklearn pipelines on pandas or polars dataframes", "join and featurize multiple tables for ML", "prepare text and categorical columns for scikit-learn estimators"], "what_it_is": "skrub is a Python library that facilitates machine learning with dataframes, providing preprocessing, encoding, and wrangling tools for tabular and dirty data. It integrates with scikit-learn-style pipelines to turn messy dataframes into ML-ready features.", "when_to_avoid": ["you need deep learning on images or raw text rather than tabular data", "you want a full AutoML or model-training framework", "your data is not dataframe/tabular in nature"], "when_to_choose": ["you train ML models on tabular data stored in dataframes", "you need robust encoders for messy categorical or text columns", "you want scikit-learn-compatible transformers for data preparation", "you work with pandas or polars and need feature engineering helpers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/skrub", "repo": "skrub-data/skrub", "role": "main", "score": 93}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:16.803707+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:45:05.921010+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1863f5a0d94da56ff77f2c3f475a5e73fd1cb49716bb8f94dde8be8bb01a5245", "fetched_at": "2026-08-28T04:05:16.803707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/skrub-data/skrub"}, {"content_hash": "1b10ad816110d55dd08c6d240d6619b99e275b51a25e3a9044a30ce34887c983", "fetched_at": "2026-08-29T11:18:14.608274+00:00", "kind": "homepage", "missing": false, "url": "https://skrub-data.org/"}, {"content_hash": "578b8d7935951d174f7b7384e691ede7444a61903cd9412eb75763fbd3db26a4", "fetched_at": "2026-08-29T11:18:14.610549+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/skrub/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 80}, "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": 3096, "days_push": 8, "days_rel": 58, "gap_med": 39.5, "n_releases_24m": 9}, "score": 93, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}