NICEx 0.2.2

Nearest Instance Counterfactual explanations

Nearest Instance Counterfactual Explanations (NICE)

NICE is an algorithm to generate Counterfactual Explanations for heterogeneous tabular data. Our approach exploits information from a nearest instance to speed up the search process and guarantee that an explanation will be found.

Installation

Install NICE through Pypi

pip install NICEx

or github

pip install git git+https://github.com/ADMantwerp/nice.git 

Usage

NICE requires acces to the prediction score and trainingdata to generate counterfactual explanations.

from nice import NICE

# Initialize NICE by specifing the optimization strategy
NICE_explainer = NICE(optimization='sparsity')
# Fit our NICE explainer on the training data and classifier
NICE_explainer.fit(predict_fn,X_train,cat_feat,num_feat,y_train,optimization='sparsity')
# explain an instance
NICE_explainer.explain(x)

Examples

NICE on Adult

References

NICE: An Algorithm for Nearest Instance Counterfactual Explanations