R: plotting graphs (ggplot vs autoplot)

问题

I am following a R tutorial over here https://rviews.rstudio.com/2017/09/25/survival-analysis-with-r/

The computer I use for work does not have internet access nor a USB port - it only has R with some preinstalled libraries. The tutorial requires "survival", "ggplot2", "ranger", "dplyr" and "ggfortify". The computer I use for work has all of these libraries EXCEPT ggfortfiy. Apparently, a function called "autoplot" is required from the ggfortify library to make some of the plots in this tutorial.

When I try to run the code from the tutorial:

#load libraries
library(survival)
library(ranger)
library(ggplot2)
library(dplyr)

#load data
data(veteran)
head(veteran)

# Kaplan Meier Survival Curve
km <- with(veteran, Surv(time, status))
km_fit <- survfit(Surv(time, status) ~ 1, data=veteran)

#plot(km_fit, xlab="Days", main = 'Kaplan Meyer Plot') #base graphics is always ready


#here is where the error is 
autoplot(km_fit)

I get the following error: Error: Objects of type survfit not supported by autoplot.

Does anyone know how to fix this? Is it possible to make similar plots without the ggfortify library? Can it just be made with ggplot2?

On my personal computer, I am able to make this plot once I install the ggfortify library.

(note: I also do not have the "survminer" library)

Thanks

回答1:

Yes, this is possible, because the autoplot function uses ggplot2 under the hood:

tibble(time = km_fit$time, surv = km_fit$surv, 
       min = km_fit$lower, max = km_fit$upper) %>% 
  ggplot(aes(x = time)) +
  geom_line(aes(y = surv)) +
  geom_ribbon(aes(ymin = min, ymax = max), alpha = 0.3)

来源：https://stackoverflow.com/questions/65033260/r-plotting-graphs-ggplot-vs-autoplot