mlr3viz (version 0.5.8)

autoplot.PredictionSurv: Plot for PredictionSurv

Description

Generates plots for mlr3proba::PredictionSurv, depending on argument type:

• "calib" (default): Calibration plot comparing the average predicted survival distribution to a Kaplan-Meier prediction, this is not a comparison of a stratified crank or lp prediction. object must have distr prediction. geom_line() is used for comparison split between the prediction (Pred) and Kaplan-Meier estimate (KM). In addition labels are added for the x (T) and y (S(T)) axes.

• "dcalib": Distribution calibration plot. A model is D-calibrated if X% of deaths occur before the X/100 quantile of the predicted distribution, e.g. if 50% of observations die before their predicted median survival time. A model is D-calibrated if the resulting plot lies on x = y.

• "preds": Matplots the survival curves for all predictions

Usage

# S3 method for PredictionSurv
autoplot(
  object,
  type = "dcalib",
  task = NULL,
  row_ids = NULL,
  times = NULL,
  xyline = TRUE,
  cuts = 11L,
  ...
)

Arguments

object

(mlr3proba::PredictionSurv).

type

(character(1)): Type of the plot. See description.

task

(mlr3proba::TaskSurv) If type = "calib" then task is passed to $predict in the Kaplan-Meier learner.

row_ids

(integer()) If type = "calib" then row_ids is passed to $predict in the Kaplan-Meier learner.

times

(numeric()) If type = "calib" then times is the values on the x-axis to plot over, if NULL uses all times from task.

xyline

(logical(1)) If TRUE (default) plots the x-y line for type = "dcalib".

cuts

(integer(1)) Number of cuts in (0,1) to plot dcalib over, default is 11.

...

(any): Additional arguments, currently unused.

Theme

The theme_mlr3() and viridis color maps are applied by default to all autoplot() methods. To change this behavior set options(mlr3.theme = FALSE).

References

Haider H, Hoehn B, Davis S, Greiner R (2020). “Effective Ways to Build and Evaluate Individual Survival Distributions.” Journal of Machine Learning Research, 21(85), 1-63. https://jmlr.org/papers/v21/18-772.html.

Examples

# NOT RUN {
library(mlr3)
library(mlr3proba)
library(mlr3viz)

learn = lrn("surv.coxph")
task = tsk("unemployment")
p = learn$train(task, row_ids = 1:300)$predict(task, row_ids = 301:400)

# calibration by comparison of average prediction to Kaplan-Meier
autoplot(p, type = "calib", task = task, row_ids = 301:400)

# Distribution-calibration (D-Calibration)
autoplot(p, type = "dcalib")

# Predictions
autoplot(p, type = "preds")
# }