Xai Library | Xai Project

The integrated library for explanation methods!

What is XAI Library?

XAI Library is a Python library designed to develop explainable machine learning models. Our library provides an integrated interface to set up and execute explanation methods for black boxes.

Key Features:

Modular and Extensible: The library is designed to be modular, allowing the addition of new explanation methods and their integration with existing ones.
Simple Interface: We provide a simple interface to add new explanation methods, making the library easy to use and extend.

Available Explanation Methods:

For Tabular Data:

SHAP (SHapley Additive exPlanations)
LIME (Local Interpretable Model-agnostic Explanations)
Anchors
LORE (Local Rule-based Explanations)

For Image Data:

GradCAM (Gradient-weighted Class Activation Mapping)
LIME (Local Interpretable Model-agnostic Explanations)
SHAP (SHapley Additive exPlanations)
ABELE

Why Choose XAI Library?

Ease of Use: An intuitive modular structure that facilitates the integration of explanation methods into your machine learning projects.
Versatility: Support for various data types, including tabular, image, (text, and time series data coming soon).
Community and Support: We are here to support the community with comprehensive documentation and practical examples.

We are excited to see what you create with XAI Library and how this library can help make your machine learning models more transparent and understandable.

🔗 * *Download XAI Library today and start building explainable machine learning models! **

Documentation

Full documentation can be found at this link.

The documentation for the implemented classes has been set up, and each individual method contains descriptions of the input parameters and the generated output.

We look forward to your feedback and seeing your implementations!