Prediction Explanation with Dependence-Aware Shapley Values


[Up] [Top]

Documentation for package ‘shapr’ version 1.0.4

Help Pages

explain Explain the output of machine learning models with dependence-aware (conditional/observational) Shapley values
explain_forecast Explain a forecast from time series models with dependence-aware (conditional/observational) Shapley values
get_extra_comp_args_default Gets the default values for the extra computation arguments
get_iterative_args_default Function to specify arguments of the iterative estimation procedure
get_output_args_default Gets the default values for the output arguments
get_supported_approaches Gets the implemented approaches
get_supported_models Provides a data.table with the supported models
plot.shapr Plot of the Shapley value explanations
plot_MSEv_eval_crit Plots of the MSEv Evaluation Criterion
plot_SV_several_approaches Shapley value bar plots for several explanation objects
plot_vaeac_eval_crit Plot the training VLB and validation IWAE for 'vaeac' models
plot_vaeac_imputed_ggpairs Plot Pairwise Plots for Imputed and True Data
print.shapr Print method for shapr objects
vaeac_get_extra_para_default Function to specify the extra parameters in the 'vaeac' model
vaeac_train_model_continue Continue to Train the vaeac Model