safe-ai-metrics 0.1.1

SAFE-AI metrics for accuracy, robustness, and explainability evaluation

SAFE-AI Metrics

SAFE-AI Metrics is a Python package for evaluating machine learning models using accuracy, robustness, and explainability-oriented metrics.

The package provides implementations of:

• RGA — Rank Graduation Accuracy
• RGE — Rank Graduation Explainability
• RGR — Rank Graduation Robustness

Installation

pip install safe-ai-metrics

Acknowledgements

The development of this package builds on the safeaipackage project by Golnoosh Babaei.

The original safeaipackage repository is available at: https://github.com/GolnooshBabaei/safeaipackage

This repository is currently maintained as a separate implementation for development and packaging purposes, but it is expected to be merged or aligned with the original SAFE-AI package in the future.

If you use this package in academic work, please consider citing the related SAFE-AI and RGB paper referenced in the original project.