Welcome to the LUX documentation

LUX (Local Universal Rule-Based Explainer) is an XAI algorithm that produces explanations for any type of machine-learning model. It provides local explanations in a form of human-readable (and executable) rules, but also provide counterfactual explanations as well as visualization of the explanations.

Install

LUX can be installed from either PyPI or directly from source code GitHub

To install form PyPI:

pip install lux-explainer

To install from source code:

git clone https://github.com/sbobek/lux
cd lux
pip install .

Examples

• Basic Usage examples
• SHAP-guided explanation generation examples
  • Loading the dataset and building explanations without SHAP support
  • Explanation without SHAP-guided explanations
  • Explanation with SHAP-guided explantions
• Visualization examples
  • Textual
  • Graphviz
  • Advanced
  • Decision Table

Reference

• API reference
  • Explanation interface
  • Explanation tree backend
  • Metrics

Development

• Release notes
• Contributing guide