SHAPforxgboost (version 0.0.2)

shap.plot.dependence: SHAP dependence plot and interaction plot, optional to be colored by a selected feature

Description

This function makes the simple dependence plot with SHAP values on the y axis, optional to add color by another feature, optional to use a different y variable for SHAP values Not colored if color_feature is not supplied. If data_int (the SHAP interaction values dataset) is supplied, it will plot the interaction effect between y and x on the y axis.

Usage

shap.plot.dependence(data_long, x, y = NULL, color_feature = NULL,
  data_int = NULL, dilute = FALSE, smooth = TRUE, size0 = NULL,
  add_hist = FALSE)

Arguments

data_long

the long format SHAP values from shap.prep

x

which feature to show on x axis, it will plot the feature value.

y

which shap values to show on y axis, it will plot the SHAP value of that feature. y is default to x, if y is not provided, just plot the SHAP values of x on the y axis

color_feature

which feature value to use for coloring, color by the feature value.

data_int

the 3-dimention SHAP interaction values array. if data_int is supplied, y axis will plot the interaction values of y (vs. x)

dilute

a number or logical, dafault to TRUE, will plot nrow(data_long)/dilute data. For example, if dilute = 5 will plot 20 As long as dilute != FALSE, will plot at most half the data.

from predict.xgb.Booster or shap.prep.interaction.

smooth

optional to add loess smooth line, default to TRUE.

size0

point size, default to 1 of nobs<1000, 0.4 if nobs>1000.

add_hist

whether to add histogram using ggMarginal, default to TRUE. But notice the plot after adding histogram it is ggExtraPlot object, cannot add geom to that anymore. If wish to add more ggplot layers, turn the histogram off

Value

returns a ggplot2 object, based on which you could add more geom layers.

Details

Dependence plot is very easy to make if you have the SHAP values dataset from predict.xgb.Booster It is not necessary to start with the long-format data, but since I used that for the summary plot, I just continue to use the long dataset

Examples

# NOT RUN {
# **SHAP dependence plot**

# 1. simple dependence plot with SHAP values of x on the y axis
shap.plot.dependence(data_long = shap_long_iris, x="Petal.Length", add_hist = TRUE)

# 2. can choose a different SHAP values on the y axis
shap.plot.dependence(data_long = shap_long_iris, x="Petal.Length",
                           y = "Petal.Width")

# 3. color by another feature's feature values
shap.plot.dependence(data_long = shap_long_iris, x="Petal.Length",
                           color_feature = "Petal.Width")

# 4. choose 3 different variables for x, y, and color
shap.plot.dependence(data_long = shap_long_iris, x="Petal.Length",
                           y = "Petal.Width", color_feature = "Petal.Width")

# Optional to add hist or remove smooth line, optional to plot fewer data (make plot quicker)
shap.plot.dependence(data_long = shap_long_iris, x="Petal.Length",
                     y = "Petal.Width", color_feature = "Petal.Width",
                     add_hist = TRUE, smooth = FALSE, dilute = 3)

# to make a list of plot
plot_list <- lapply(names(iris)[2:3], shap.plot.dependence, data_long = shap_long_iris)

# **SHAP interaction effect plot **

# To get the interaction SHAP dataset for plotting, need to get `shap_int` first:
mod1 = xgboost::xgboost(
  data = as.matrix(iris[,-5]), label = iris$Species,
  gamma = 0, eta = 1, lambda = 0,nrounds = 1, verbose = FALSE)
# Use either:
data_int <- shap.prep.interaction(xgb_mod = mod1,
                                  X_train = as.matrix(iris[,-5]))
# or:
shap_int <- predict(mod1, as.matrix(iris[,-5]),
                    predinteraction = TRUE)

# if data_int is supplied, y axis will plot the interaction values of y (vs. x)
shap.plot.dependence(data_long = shap_long_iris,
                           data_int = shap_int_iris,
                           x="Petal.Length",
                           y = "Petal.Width",
                           color_feature = "Petal.Width")
# }