SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions (see [papers](https://github.com/slundberg/shap#citations) for details and citations.

Explainers

shap.TreeExplainer

alias of shap.explainers._tree.Tree

shap.GradientExplainer

alias of shap.explainers._gradient.Gradient

shap.DeepExplainer

alias of shap.explainers._deep.Deep

shap.KernelExplainer

alias of shap.explainers._kernel.Kernel

shap.SamplingExplainer

alias of shap.explainers._sampling.Sampling

shap.PartitionExplainer

alias of shap.explainers._partition.Partition

Plots

shap.summary_plot(*args, **kwargs)

shap.dependence_plot(*args, **kwargs)

shap.waterfall_plot(*args, **kwargs)

shap.force_plot(*args, **kwargs)

shap.image_plot(*args, **kwargs)

shap.decision_plot(*args, **kwargs)