calibrated-explanations 0.0.4

Extract calibrated explanations from machine learning models.

Calibrated Explanations

Calibrated Explanations is a Python library that is able to explain predictions of a black-box model using Venn Abers predictors (classification) or conformal predictive systems (regression) and perturbations.

Install

First, you need a Python environment installed with pip.

Calibrated Explanations can be installed from PyPI:

pip install calibrated-explanations

The dependencies are:

• crepes
• lime
• matplotlib
• NumPy
• pandas
• scikit-learn
• SHAP
• tqdm

Getting started

>>> import calibrated_explanations
... TODO: write me...

Development

This project has tests that can be executed using pytest. Just run the following command from the project root.

pytest

Further reading

The calibrated explanations library is based on the paper "Calibrated Explanations for Black-Box Predictions" by Helena Löfström, Tuwe Löfström, Ulf Johansson and Cecilia Sönströd.

If you would like to cite this work, please cite the above paper.