Metadata-Version: 2.4
Name: model-agnostic-toolkit
Version: 1.0.0
Summary: Toolkit with model agnostic methods of Explainable Artificial Intelligence for Python.
Project-URL: Homepage, https://git-ce.rwth-aachen.de/wzl-iqs3/quality-insights/publications/model_agnostic_toolkit/
Author: Chrismarie Enslin, Daniel Buschmann, Marcos Padrón Hinrichs, Felix Sohnius, Robert H. Schmitt
Author-email: Tobias Schulze <tobias.schulze@wzl-iqs.rwth-aachen.de>
License: MIT
License-File: LICENSE.md
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Requires-Python: <=3.10.15,>=3.9
Requires-Dist: alibi~=0.9.4
Requires-Dist: bunch~=1.0.1
Requires-Dist: ipython~=8.11.0
Requires-Dist: joblib~=1.2.0
Requires-Dist: matplotlib~=3.7.1
Requires-Dist: numpy~=1.23.0
Requires-Dist: pandas~=1.5.3
Requires-Dist: pdpbox~=0.3.0
Requires-Dist: plotly~=5.13.1
Requires-Dist: psutil~=5.9.4
Requires-Dist: pyale~=1.1.3
Requires-Dist: ray
Requires-Dist: requests~=2.31.0
Requires-Dist: scikit-learn~=1.2.2
Requires-Dist: scipy~=1.10.1
Requires-Dist: seaborn~=0.13.0
Requires-Dist: setuptools~=68.0.0
Requires-Dist: shap~=0.41.0
Requires-Dist: tables
Requires-Dist: torch
Requires-Dist: xgboost~=1.7.4
Description-Content-Type: text/plain

The Model Agnostic Toolkit is a package for determining the effect of individual features
and their interplay toward a target variable for tabular datasets.

It includes tools for:
- Individual feature importances
- Feature pair interactions

For more details, please refer to the project documentation.
