Metadata-Version: 2.1
Name: evalda-pub2
Version: 0.0.6
Summary: A package for quantifying bias in Danish language models.
Home-page: https://github.com/DaDebias/evalda-pub2
License: MIT
Author: Astrid Rybner
Author-email: astrid.rybner@hotmail.com
Requires-Python: >=3.9,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: augmenty (==1.3.1)
Requires-Dist: dacy (==2.3.1)
Requires-Dist: gensim (>=4.3.1,<5.0.0)
Requires-Dist: nltk (>=3.8.1,<4.0.0)
Requires-Dist: progressbar (>=2.5,<3.0)
Requires-Dist: protobuf (==3.20.3)
Requires-Dist: scikit-learn (>=1.2.2,<2.0.0)
Requires-Dist: spacy (==3.4.4)
Project-URL: Repository, https://github.com/DaDebias/evalda-pub2
Description-Content-Type: text/markdown

### Getting started 
The package can be found on pypi and can be installed using pip. 
```bash
pip install evalda-pub2
```

### Usage

**Create a bias detector instance for evaluating ner model:**

```python
>>> from evalda-pub2 import Evaluator
 
>>> ev = Evaluator()
```

**Generate ner output:** 

```python
>>> output = ev.eval_ner(n=5, model_name = "saattrupdan/nbailab-base-ner-scandi", outstyle="condensed", outformat="csv")
```
**Generate ner visualization:** (currently non existing:)

```python
>>> viz = ev.visualize(outformat="png")
```

