---
id: "dataprofiler"
category: "detector"
url: "http://registry.apicrafter.io/tool/dataprofiler"
---

# Capital One DataProfiler (`dataprofiler`)

DataProfiler is an open source Python library from Capital One that profiles datasets and detects sensitive data. Its data labeler is a character-level neural model that predicts an entity label for each cell of structured data, and the profiler aggregates these predictions into a label for the column. The default structured labeler has 23 labels, such as EMAIL_ADDRESS, CREDIT_CARD, SSN, IPV4 and US_STATE; the list is in the label_mapping.json resource of the structured model and on the data labeling page of the docs.

Website: <https://capitalone.github.io/DataProfiler/data_labeling.html>

## Supported datatypes (17)

- `address`
- `bankaccount`
- `bankcard`
- `date`
- `datetime`
- `driver_license`
- `email`
- `ipv4`
- `ipv6`
- `mac_address`
- `person_fullname`
- `phone`
- `time`
- `url`
- `usssn`
- `usstate`
- `uuid`