Using factor values in PCA Analysis (using prcomp)

Asked Feb 27 '19 at 14:49

Active Feb 27 '19 at 14:49

Viewed 431 times

I am trying to figure out how I can incorporate the factor/levels into my PCA analysis. Suppose I have the following:

> df <- data.frame(col1=c("A", "B", "C", "D"), col2=c(1, 2, 3, 4))
> str(df)
'data.frame':   4 obs. of  2 variables:
 $ col1: Factor w/ 4 levels "A","B","C","D": 1 2 3 4
 $ col2: num  1 2 3 4

Theoretically df[,"col1"] is numeric internally in the df (since it is a factor) so I should be able to use its factor values for PCA analysis. But I can't seem to figure out how I can do it:

> prcomp(df, center=T, scale. = T)
Error in colMeans(x, na.rm = TRUE) : 'x' must be numeric

How can I include col1 in my PCA analysis? Is there another PCA function I should be using?

asked Feb 27 '19 at 14:49

Denis

11,796
16
88
150

2

see here: https://stats.stackexchange.com/questions/5774/can-principal-component-analysis-be-applied-to-datasets-containing-a-mix-of-cont – RLave Feb 27 '19 at 14:52
2

You can't (or you shouldn't) use PCA on categorical data, see linked post on cross-validated – pogibas Feb 27 '19 at 14:54
great pointers! Thank you! – Denis Feb 27 '19 at 15:18

Using factor values in PCA Analysis (using prcomp)

0 Answers0