One-Hot Encoding in R

one_hot_encode.R

### one-hot encoding
vars <- colnames(data)
## to one hot encode factor values and normalize numeric ones if needed
cat_vars <- vars[sapply(data[, vars], class) %in%
                   c("factor", "character", "logical")]
data2 <- data[, cat_vars]
for (i in cat_vars) {
  dict <- unique(data2[, i])
  for (key in dict) {
    data2[[paste0(i, "_", key)]] <- 1.0 * (data2[, i] == key)
  }
}
# to remove the original categorical variables
#data[, which(colnames(data) %in% cat_vars)] <- NULL