Extension of text_explainability for sensitivity testing (robustness, fairness)
Project description
Extension of text_explainability for sensitivity testing (robustness, fairness).
Marcel Robeer, 2021
Installation
Method | Instructions |
---|---|
pip |
Install from PyPI via pip3 install text_sensitivity . |
Local | Clone this repository and install via pip3 install -e . or locally run python3 setup.py install . |
Documentation
Full documentation of the latest version is provided at https://marcelrobeer.github.io/text_sensitivity/.
Example usage
See example_usage.md to see an example of how the package can be used, or run the lines in example_usage.py
to do explore it interactively.
Releases
text_explainability
is officially released through PyPI.
See CHANGELOG.md for a full overview of the changes for each version.
Citation
@misc{text_sensitivity,
title = {Python package text_sensitivity},
author = {Marcel Robeer and Elize Herrewijnen},
howpublished = {https://git.science.uu.nl/m.j.robeer/text_sensitivity},
year = {2021}
}
Maintenance
Contributors
- Marcel Robeer (
@m.j.robeer
) - Elize Herrewijnen (
@e.herrewijnen
)
Todo
Tasks yet to be done:
- Word-level perturbations
- Add fairness-specific metrics:
- Subgroup fairness
- Counterfactual fairness
- Tests
- Add tests for data generation
- Add tests for perturbations
- Add tests for test-schemes
- Add visualization ability
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
text_sensitivity-0.1.4.tar.gz
(16.1 kB
view hashes)
Built Distributions
text_sensitivity-0.1.4-py3.9.egg
(31.5 kB
view hashes)
Close
Hashes for text_sensitivity-0.1.4-py3.9.egg
Algorithm | Hash digest | |
---|---|---|
SHA256 | d7ce232104aae0f287eaaf51e0c7742b6f00e48467adb0e33b9b64ce28096a0a |
|
MD5 | 3b317eae9baadab230a257e3c4406578 |
|
BLAKE2b-256 | ad1d08e989779299a3583f93a6f3fb2fdf5adb25ec6aa43e9dfda020eca4c405 |
Close
Hashes for text_sensitivity-0.1.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9e1fa5d3135e442bbdebba1912083e911372cc5d535904ef6bfcccb6afdc968d |
|
MD5 | 9336958af30bca0fb2ac74c16cadba38 |
|
BLAKE2b-256 | b2304e6fd7d06e910b4da661d8aae1eab8fc1bf090b44b7618ab83c519c9e8aa |