plot_feature_importance {treeshap} | R Documentation |
SHAP value based Feature Importance plot
Description
This function plots feature importance calculated as means of absolute values of SHAP values of variables (average impact on model output magnitude).
Usage
plot_feature_importance(
treeshap,
desc_sorting = TRUE,
max_vars = ncol(shaps),
title = "Feature Importance",
subtitle = NULL
)
Arguments
treeshap |
A treeshap object produced with the |
desc_sorting |
logical. Should the bars be sorted descending? By default TRUE. |
max_vars |
maximum number of variables that shall be presented. By default all are presented. |
title |
the plot's title, by default |
subtitle |
the plot's subtitle. By default no subtitle. |
Value
a ggplot2
object
See Also
treeshap
for calculation of SHAP values
plot_contribution
, plot_feature_dependence
, plot_interaction
Examples
library(xgboost)
data <- fifa20$data[colnames(fifa20$data) != 'work_rate']
target <- fifa20$target
param <- list(objective = "reg:squarederror", max_depth = 3)
xgb_model <- xgboost::xgboost(as.matrix(data), params = param, label = target,
nrounds = 20, verbose = FALSE)
unified_model <- xgboost.unify(xgb_model, as.matrix(data))
shaps <- treeshap(unified_model, as.matrix(head(data, 3)))
plot_feature_importance(shaps, max_vars = 4)
[Package treeshap version 0.3.1 Index]