Genetic Algorithm for Generating Metacounterfactual Explanations
Project description
\n# Manic: A Genetic Algorithm-based Metaheuristic Approach for Nature-Inspired Aggregation of Counterfactuals
Table of Contents
Introduction
Manic is a Python package that provides a genetic algorithm-based metaheuristic approach for aggregating counterfactual explanations. It implements a nature-inspired optimization technique to generate counterfactuals that explain the disagreement between different explainers. The goal is to find counterfactual instances that are both diverse and informative to enhance the interpretability of machine learning models.
Installation
To install Manic, use the following pip3 command:
pip3 install manic-xai
Usage
You can use Manic in your Python code as follows:
from manic import Manic
# Define your data_instance, base_counterfactuals, categorical_features, immutable_features, feature_ranges, data, and predict_fn
manic_instance = Manic(data_instance, base_counterfactuals, categorical_features, immutable_features, feature_ranges, data, predict_fn)
# Generate counterfactuals
counterfactuals = manic_instance.generate_counterfactuals()
Docker Instructions
To run Manic using Docker, follow these steps:
- Build the Docker image:
docker build -t manic .
- Run the Docker container
docker run -v /path/to/your/data:/data -it manic python3 your_script.py
Citation
If you use the Manic package in your research or work and find it helpful, we kindly request that you cite it using the following BibTeX entry:
@software{manic,
author = {Craig Pirie},
title = {Manic: A Genetic Algorithm-based Metaheuristic Approach for Nature-Inspired Aggregation of Counterfactuals},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/your-username/manic}},
}
We appreciate your support and acknowledgment of our work.
Contact
For any inquiries or collaborations, please contact Craig Pirie at c.pirie11@rgu.ac.uk.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Contributions
Contributions to the Manic package are always welcome. If you find any issues or have ideas for improvements, please feel free to open an issue or submit a pull request on the GitHub repository. Together, we can make Manic better for everyone.
Changelog
For updates and a history of changes to the Manic package, please refer to the Changelog.
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file manic-xai-1.0.39.tar.gz.
File metadata
- Download URL: manic-xai-1.0.39.tar.gz
- Upload date:
- Size: 23.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a8c62849495f3f871f30f2fdb2b7dff1ce1b71ea4f6c195a26849f5c5665a461
|
|
| MD5 |
25420ca3d3e3d0f8d4835b0af107d513
|
|
| BLAKE2b-256 |
830e5d834dfec7056aacd7f03859aedc8bfbab300fc42db45b38534a6b6eab84
|
File details
Details for the file manic_xai-1.0.39-py3-none-any.whl.
File metadata
- Download URL: manic_xai-1.0.39-py3-none-any.whl
- Upload date:
- Size: 36.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f629e7bcd2cbd6f4d2272a981999af982ca2d7dc984f232fbaa42b7983934b5a
|
|
| MD5 |
791e24730e38776af0c2f3994c4219ec
|
|
| BLAKE2b-256 |
35a72deb1761a7cfb6ef40a7f42efb933876c6ffb2d8bfd52ee732a4096b4193
|
