teex

A Python Toolbox for the evaluation of machine learning explanations.

This project aims to provide a simple way of evaluating individual black box explanations. Moreover, it contains a collection of easy-to-access datasets with available ground truth explanations.

teex contains a subpackage for each explanation type, and each subpackage contains two modules:

• eval: with methods for explanation evaluation.

• data: with methods for data generation, loading and manipulation.

Visit our GitHub for source.

Examples

• Notebook demos
  • Saliency map
  • Decision rule
  • Feature importance
  • Word importance
  • Model selection

API reference

• API reference