transform columns to binary encoded columns in R

Question

I have some nominal variables encoded as integers (not ordinal), which I would like to encode as binary (not dummies nor one hot!). The following code is what I came up with (adapted from other code I found). Is this a valid/scalable approach? Thanks!

library(binaryLogic)

df <- data.frame(x1 = c(1, 1, 2, 3), x2 = c(1, 2, 3, 4))

encode_binary <- function(x, name = "binary_") {
    x2 <- as.binary(x)
    maxlen <- max(sapply(x2, length))
    x2 <- lapply(x2, function(y) {
        l <- length(y)
        if (l < maxlen) {
            y <- c(rep(0, (maxlen - l)), y)
        }
        y
    })
    d <- as.data.frame(t(as.data.frame(x2)))
    rownames(d) <- NULL
    colnames(d) <- paste0(name, 1:maxlen)
    d
}

df <- cbind(df, encode_binary(df[["x1"]], name = "binary_x1_"))
df <- cbind(df, encode_binary(df[["x2"]], name = "binary_x2_"))

df

Answer 1

If we test on larger vector your approach is quite slow:

test_vec <- 1:1e5
system.time(v1 <- encode_binary(test_vec, name = "binary_x1_"))
#  user  system elapsed 
# 22.23    0.08   22.37 

Based on this SO question I managed to write code that performs a lot faster:

encode_binary2 <- function(x, name = "binary_") {
  m <- sapply(x, function(x) rev(as.integer(intToBits(x))))
  tm <- t(m)
  # remove empty bit cols
  i <- which(colSums(tm) != 0L)[1]
  tm <- tm[, i:ncol(tm)]
  # save to data.frame
  d <- as.data.frame(tm)
  rownames(d) <- NULL
  colnames(d) <- paste0(name, 1:ncol(d))
  d
}

system.time(v2 <- encode_binary2(test_vec, name = "binary_x1_"))
# user  system elapsed 
# 0.61    0.02    0.63 

# test that results are equal:
all.equal(v1, v2)
# [1] TRUE