Drop data frame columns by name

Question

I have a number of columns that I would like to remove from a data frame. I know that we can delete them individually using something like:

df$x <- NULL
<         


        

Answer 1

If you have a large data.frame and are low on memory use [ . . . . or rm and within to remove columns of a data.frame, as subset is currently (R 3.6.2) using more memory - beside the hint of the manual to use subset interactively.

getData <- function() {
  n <- 1e7
  set.seed(7)
  data.frame(a = runif(n), b = runif(n), c = runif(n), d = runif(n))
}

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF <- DF[setdiff(names(DF), c("a", "c"))] ##
#DF <- DF[!(names(DF) %in% c("a", "c"))] #Alternative
#DF <- DF[-match(c("a","c"),names(DF))]  #Alternative
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#0.1 MB are used

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF <- subset(DF, select = -c(a, c)) ##
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#357 MB are used

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF <- within(DF, rm(a, c)) ##
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#0.1 MB are used

DF <- getData()
tt <- sum(.Internal(gc(FALSE, TRUE, TRUE))[13:14])
DF[c("a", "c")]  <- NULL ##
sum(.Internal(gc(FALSE, FALSE, TRUE))[13:14]) - tt
#0.1 MB are used