Counterfactuals: Take the uncertainty out of your machine learning models
Counterfactuals is a Python library for machine learning that enables you to better understand your models. We combine several techniques to provide a comprehensive understanding of your model's predictions. With those insights you are able to eliminate uncertainties and make better decisions.
CLUE is a method for explaining uncertainty estimates of machine learning models. It is based on the idea of counterfactuals and provides a comprehensive understanding of the model's predictions.
Model Paper: CLUE: A Method for Explaining Uncertainty Estimates
The current recommended way to install counterfactual is from source.
git clone https://github.com/lsch0lz/counterfactuals.git
cd counterfactuals
python3 -m pip install -e .python3 -m pip install git+https://github.com/lsch0lz/counterfactuals.gitDocumentation along with a quick start guide can be found in the docs/ directory.