Plotting Shapley values
Construct Shapley-based importance plots or Shap-based dependence plots.
## S3 method for class 'explain'
autoplot(
object,
type = c("importance", "dependence", "contribution"),
feature = NULL,
num_features = NULL,
X = NULL,
color_by = NULL,
smooth = FALSE,
smooth_color = "red",
smooth_linetype = "solid",
smooth_size = 1,
smooth_alpha = 1,
row_num = NULL,
...
)object |
An object of class |
type |
Character string specifying which type of plot to construct.
Current options are |
feature |
Character string specifying which feature to use when
|
num_features |
Integer specifying the number of variables to plot.
Default is |
X |
A matrix-like R object (e.g., a data frame or matrix) containing ONLY the feature columns from the training data. |
color_by |
Character string specifying an optional feature column in
|
smooth |
Logical indicating whether or not to add a smoother to the
scatterplot whenever |
smooth_color |
The color to use for the smoother whenever
|
smooth_linetype |
The type of line to use for the smoother whenever
|
smooth_size |
The size to use for the smoother whenever
|
smooth_alpha |
The transparency to use for the smoother whenever
|
row_num |
Integer specifying a single row/instance in |
... |
Additional optional arguments to be passed on to
|
A "ggplot" object; see
ggplot2-package for details.
#
# A projection pursuit regression (PPR) example
#
# Load the sample data; see ?datasets::mtcars for details
data(mtcars)
# Fit a projection pursuit regression model
mtcars.ppr <- ppr(mpg ~ ., data = mtcars, nterms = 1)
# Compute approximate Shapley values using 10 Monte Carlo simulations
set.seed(101) # for reproducibility
shap <- explain(mtcars.ppr, X = subset(mtcars, select = -mpg), nsim = 10,
pred_wrapper = predict)
shap
# Shapley-based plots
library(ggplot2)
autoplot(shap) # Shapley-based importance plot
autoplot(shap, type = "dependence", feature = "wt", X = mtcars)
autoplot(shap, type = "contribution", row_num = 1) # explain first row of XPlease choose more modern alternatives, such as Google Chrome or Mozilla Firefox.