An introduction to explainable AI with Shapley values This is an introduction to explaining machine learning models with Shapley values. Shapley values are a widely used approach from cooperative …

API Reference This page contains the API reference for public objects and functions in SHAP. There are also example notebooks available that demonstrate how to use the API of each object/function. …

Uses Shapley values to explain any machine learning model or python function. This is the primary explainer interface for the SHAP library. It takes any combination of a model and masker and returns …

Basic SHAP Interaction Value Example in XGBoost This notebook shows how the SHAP interaction values for a very simple function are computed. We start with a simple linear function, and then add …

1 SHAP Decision Plots 1.1 Load the dataset and train the model 1.2 Calculate SHAP values 2 Basic decision plot features 3 When is a decision plot helpful? 3.1 Show a large number of feature effects …

A sliceable set of parallel arrays representing a SHAP explanation. Notes The instance methods such as .max () return new Explanation objects with the operation applied. The class methods such as …

Image examples These examples explain machine learning models applied to image data. They are all generated from Jupyter notebooks available on GitHub. Image classification Examples using …

Text examples These examples explain machine learning models applied to text data. They are all generated from Jupyter notebooks available on GitHub. Sentiment analysis Examples of how to …

shap.DeepExplainer class shap.DeepExplainer(model, data, session=None, learning_phase_flags=None) Meant to approximate SHAP values for deep learning models. This is …

Explaining quantitative measures of fairness This hands-on article connects explainable AI methods with fairness measures and shows how modern explainability methods can enhance the usefulness of …