plot.surv_feature_importance {survex}

Plot Permutational Feature Importance for Survival Models

Description

This function plots feature importance objects created for survival models using the model_parts() function with a time-dependent metric, that is loss_one_minus_cd_auc() or loss_brier_score().

Usage

## S3 method for class 'surv_feature_importance'
plot(
  x,
  ...,
  title = "Time-dependent feature importance",
  subtitle = "default",
  max_vars = 7,
  colors = NULL,
  rug = "all",
  rug_colors = c("#dd0000", "#222222")
)

Arguments

x

an object of class "surv_feature_importance" to be plotted

...

additional objects of class "surv_feature_importance" to be plotted together

title

character, title of the plot

subtitle

character, subtitle of the plot, 'default' automatically generates "created for XXX, YYY models", where XXX and YYY are the explainer labels

max_vars

maximum number of variables to be plotted (least important variables are ignored)

colors

character vector containing the colors to be used for plotting variables (containing either hex codes "#FF69B4", or names "blue")

rug

character, one of "all", "events", "censors", "none" or NULL. Which times to mark on the x axis in geom_rug().

rug_colors

character vector containing two colors (containing either hex codes "#FF69B4", or names "blue"). The first color (red by default) will be used to mark event times, whereas the second (grey by default) will be used to mark censor times.

Value

An object of the class ggplot.

See Also

Other functions for plotting 'model_parts_survival' objects: plot.model_parts_survival()

Examples

library(survival)
library(survex)

model <- coxph(Surv(time, status) ~ ., data = veteran, x = TRUE, model = TRUE, y = TRUE)
model_rf <- randomForestSRC::rfsrc(Surv(time, status) ~ ., data = veteran)
explainer <- explain(model)
explainer_rf <- explain(model_rf)

mp <- model_parts(explainer)
mp_rf <- model_parts(explainer_rf)

plot(mp, mp_rf)