focus-cfe 0.0.dev2

FOCUS is a python package for generating counterfactual explanations for a tree-based model

Deployment & Documentation & Stats & License

---

This library is an implementation of FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles.

FOCUS generates optimal distance counterfactual explanations to the original data for all the instances in tree‐based machine learning models.

FOCUS counterfactual explanation generation with 3 Lines of Code:

from focus import Focus
# Initialize Focus instance with default values
focus = Focus()
# Generate counterfactual explanations for given tree model and features
pertubed = focus.generate(tree_model, X)

Examples:

• More comprehensive example can be found in the examples folder.

• Another example in a kaggle notebook can be found here.

• Below demonstrates the comparison of before and after FOCUS was applied to feature set from the above example.

Note:

Currently FOCUS can be applied to scikit-learn DecisionTreeClassifier, RandomForestClassifier and AdaBoostClassifier.

Installation

It is recommended to use pip or conda for installation. Please make sure the latest version is installed:

pip install focus-cfe            # normal install
pip install --upgrade focus-cfe  # or update if needed

conda install -c conda-forge focus-cfe