A package for quantifying bias in Danish language models.
Project description
Getting started
The package can be found on pypi and can be installed using pip.
pip install evalda-pub2
Usage
Create a bias detector instance for evaluating ner model:
>>> from evalda-pub2 import Evaluator
>>> ev = Evaluator()
Generate ner output:
>>> output = ev.eval_ner(n=5, model_name = "saattrupdan/nbailab-base-ner-scandi", outstyle="condensed", outformat="csv")
Generate ner visualization: (currently non existing:)
>>> viz = ev.visualize(outformat="png")
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
evalda_pub2-0.0.7.tar.gz
(3.2 MB
view hashes)
Built Distribution
Close
Hashes for evalda_pub2-0.0.7-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3acaf20964f374f8943f38634d73ad89f9dfcc2f61951ac81e33e922e3526354 |
|
MD5 | 838b7a8e27c98b465b0dff87debfd724 |
|
BLAKE2b-256 | 368b500526ffcbeb001c4482b41e082742219deab33262b29b55a423c86e6751 |