{"adoption": {"forks": 205, "observed_at": "2026-08-28T04:03:30.032467+00:00", "stars": 1079}, "canonical_url": "https://ross.abutalabs.com/products/datacleaner", "card": {"archived": false, "artifact_type": "library", "description": "A Python tool that automatically cleans data sets and readies them for analysis.", "domain": ["data-science", "machine-learning"], "enriched": true, "function": ["etl", "data-science", "machine-learning", "cli"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["rhiever/datacleaner"], "name": "rhiever/datacleaner", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2019-05-22T13:53:35+00:00", "repo": "rhiever/datacleaner", "stars": 1079, "tags": ["data-cleaning", "pandas", "preprocessing", "missing-values", "categorical-encoding", "data-engineering"], "topics": ["python", "data-science", "machine-learning", "automation"], "urls": [], "use_cases": ["automatically clean a csv dataset before analysis", "impute missing values with mode or median per column", "encode categorical string variables as numbers", "drop rows with missing values from a dataframe", "preprocess data for machine learning pipelines", "clean datasets from the command line"], "what_it_is": "A Python package and command-line tool that automatically cleans pandas DataFrames, handling missing values and encoding categorical variables for machine learning analysis. It works on data already loadable into pandas and is built on pandas and scikit-learn preprocessing.", "when_to_avoid": ["you need to parse unstructured or messy raw text into structured data", "you need advanced feature engineering or custom cleaning logic", "you need actively maintained tooling with modern Python support"], "when_to_choose": ["your data is already in a pandas-compatible format and needs quick cleaning", "you want simple automated imputation and categorical encoding", "you prefer a lightweight CLI or one-line Python call"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datacleaner", "repo": "rhiever/datacleaner", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.032467+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:53:06.201506+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8328157efd28ba34ebfe4226d0e1358cdca6ee21810478b14be75e343208c891", "fetched_at": "2026-08-28T04:03:30.032467+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rhiever/datacleaner"}, {"content_hash": "beea244db4c959c600e0335f98c42665eb82b821a65da527b5438b7beec22b20", "fetched_at": "2026-08-29T12:54:19.721099+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/datacleaner/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3840, "days_push": 2660, "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}}