1

I am using an autoplot to visualise my PCA and need to add code names to each individual point but can't work out how to do it.

I have tried using geom_text but this only seems to work if using ggplot and when adding labels = TRUE, this just adds numbers to each point, instead of the code names in the original data.

this is the code I used to create the autoplot with the iris dataset from r

library(ggfortify)
df <- iris[1:4]
pca_res <- prcomp(df, scale. = TRUE)
autoplot(pca_res, data = iris, colour = 'Species',
     loadings = TRUE, loadings.colour = 'blue',
     loadings.label = TRUE, loadings.label.size = 3, frame = TRUE, frame.type = 'norm')
stefan
  • 90,330
  • 6
  • 25
  • 51
stakrawolf
  • 11
  • 2
  • 1
    It's easier to help you if you include a simple [reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) with sample input and desired output that can be used to test and verify possible solutions. – MrFlick Jul 31 '23 at 13:56
  • 1
    How did you create the `pca_res` object? `autoplot()` is a generic function that behaves different depending on what you pass in. Please make sure you define all variables in your example so we can copy/paste it into our R session for testing. – MrFlick Jul 31 '23 at 14:43

1 Answers1

0

Assuming you are using ggfortify you could set the column used as labels via the label.label argument, e.g. in the code below I simply use "Species".

Note: Under the hood the autoplot function for prcomp or princomp call ggbiplot(). So see ?ggbiplot for a list of available arguments.

library(ggfortify)
#> Loading required package: ggplot2
library(ggplot2)

d <- iris

pca_res <- prcomp(d[, 1:4], scale = TRUE)

autoplot(pca_res,
  data = iris, colour = "Species",
  label = TRUE, label.label = "Species",
  loadings = TRUE, loadings.colour = "blue",
  loadings.label = TRUE, loadings.label.size = 3, frame = TRUE, frame.type = "norm"
)

stefan
  • 90,330
  • 6
  • 25
  • 51