Interpretability demos + implementations

Demos of how to use various interpretability techniques (with accompanying slides here or pdf here) and code for implementations of interpretable machine learning models.

Demo notebooks

The demos are contained in 3 main notebooks, summarized in cheat_sheet.pdf

1. model_based.ipynb - how to use different interpretable models
2. posthoc.ipynb - different simple analyses to interpret a trained model
3. uncertainty.ipynb - code to get uncertainty estimates for a model

Code implementations

Provides scikit-learn style wrappers/implementations of different interpretable models (see readmes in individual folders within imodels for details)

• bayesian rule lists
• optimal classification tree
• rulefit
• sparse integer linear models (simple, unstable implementation)

The interpretable models within the imodels folder can be easily installed and used.

pip install git+https://github.com/Pacmed/interpretability-implementations-demos

from imodels import RuleListClassifier, RuleFit
model = RuleListClassifier() # RuleFit()
model.fit(X_train, y_train)
model.score(X_test, y_test)
preds = model.predict(X_test)

References / further reading

• book on interpretable machine learning
• high-level review on interpretable machine learning
• review on black-blox explanation methods
• review on variable importance