{"adoption": {"forks": 187, "observed_at": "2026-08-28T04:05:06.208163+00:00", "stars": 1578}, "canonical_url": "https://ross.abutalabs.com/products/dataprofiler", "card": {"archived": false, "artifact_type": "library", "description": "What's in your data? Extract schema, statistics and entities from datasets", "domain": ["data-science", "privacy", "security", "developer-tools"], "enriched": true, "function": ["data-science", "nlp", "machine-learning", "privacy", "security", "analytics"], "health_score": 94, "homepage": "https://capitalone.github.io/DataProfiler", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["capitalone/DataProfiler"], "name": "capitalone/DataProfiler", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T15:47:52+00:00", "repo": "capitalone/DataProfiler", "stars": 1578, "tags": ["data-profiling", "pii-detection", "sensitive-data", "schema-extraction", "pandas", "csv", "avro", "parquet", "gdpr", "entity-recognition", "natural-language-processing"], "topics": ["python", "privacy", "pii", "npi", "nlp", "data-science", "gdpr", "data-analysis", "data-labels", "avro", "dataprofiling", "sensitive-data", "security", "pandas", "csv", "tabular-data", "dataset", "network-data", "graph-data", "machine-learning"], "urls": [], "use_cases": ["profile a csv dataset to get schema and statistics", "detect PII and sensitive data in datasets for GDPR compliance", "automatically load csv, avro, parquet, or  files into a pandas dataframe", "identify entities like names, emails, and phone numbers in tabular or text data", "generate data quality reports for downstream monitoring", "profile graph or network data", "extend entity recognition with custom labels or regex pipelines"], "what_it_is": "DataProfiler is a Python library that loads CSV, AVRO, Parquet, JSON, text, or URL data into a pandas-compatible DataFrame and profiles it with a single command. It extracts schema, statistics, and entities, including sensitive data (PII/NPI) detection via a pre-trained deep learning model.", "when_to_avoid": ["you need a lightweight tool and cannot install TensorFlow or heavy ML dependencies", "you only need simple descriptive statistics already covered by pandas describe()", "you need real-time streaming profiling rather than batch analysis"], "when_to_choose": ["you need automated data profiling with statistics and schema extraction", "you must scan datasets for PII/NPI to meet privacy or compliance requirements", "you want a pre-trained sensitive-data detection model without building your own NLP pipeline", "you work with heterogeneous file formats and want a unified pandas-compatible loader"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dataprofiler", "repo": "capitalone/DataProfiler", "role": "main", "score": 79}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:06.208163+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:56:54.761174+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "77966b7ad765ab261cbfad0f5a2635d05f78632642aa5e7988a3c00270cfb4b8", "fetched_at": "2026-08-28T04:05:06.208163+00:00", "kind": "readme", "missing": false, "url": "https://github.com/capitalone/DataProfiler"}, {"content_hash": "901a5548453e6822fe694d5c2cf787acab705fe4d765158d76f594f7de93bcd3", "fetched_at": "2026-08-29T11:27:15.588633+00:00", "kind": "homepage", "missing": false, "url": "https://capitalone.github.io/DataProfiler"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 41}, "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": 2123, "days_push": 7, "days_rel": 399, "gap_med": 30.0, "n_releases_24m": 5}, "score": 79, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}