Geek Answers Handbook

R cropping columns in data.frame or data.table using gsub, cropping, etc.

I have a question about deletion leading trailing spaces in data.frame or data.table.

I have working solutions, but I'm trying to speed up my code.

Here are some sample data:

number_strings <- paste("  ",seq(from=1, to=100000, by=1),"  ",sep="")

data <- as.data.frame(matrix(number_strings,nrow=length(number_strings),ncol=10),stringsAsFactors=FALSE)
colnames(data) <- paste("Col",seq(from=1, to=ncol(data), by=1),sep="")

Here are some columns that I would like to crop:

odd_columns <- paste("Col",seq(from=1, to=ncol(data), by=2),sep="")

Here are three options that I still have:

f_trim_for <- function(x,cols){
  for(i in 1:length(cols))
  {
    x[,cols[i]] = trim(x[,cols[i]])
  }
  return(x)
} 
system.time(data1 <- f_trim_for(data,odd_columns)) 

f_gsub_for <- function(x,cols){
  for(i in 1:length(cols))
  {
    x[,cols[i]] <- gsub("^\\s+|\\s+$", "", x[,cols[i]], perl = TRUE)
  }
  return(x)
} 
system.time(data2 <- f_gsub_for(data,odd_columns)) 

f_trim_dt <- function(x,cols){
  data.table(x)[, (cols) := trim(.SD), .SDcols = cols]
} 
system.time(data3 <- f_trim_dt(data,odd_columns))

Here are some examples:

              user  system elapsed 
f_trim_for    1.50    0.08    1.92 
f_gsub_for    0.75    0.00    0.74 
f_trim_dt     0.81    0.00    1.17

My question is: Are there other ways that I don’t think about that could be faster?

The reason is because my actual data is 1.5 million rows and 110 columns. Consequently, speed is a serious problem.

I tried other options, but they do not work:

f_gsub_dt <- function(x,cols){
  data.table(x)[, (cols) := gsub("^\\s+|\\s+$", "", .SD, perl = TRUE), .SDcols = cols]
} 

f_set_dt <- function(x,cols){
 for (j in cols)
 {
   set(x,x[[j]],j,gsub("^\\s+|\\s+$", "", j, perl = TRUE))
 }  
 return(x)
}
+4
source share
2

colwise plyr str_trim stringr.

require(plyr)
require(stringr)
data[, odd_columns] <- colwise(str_trim)(data[, odd_columns])
+2

dplyr trimws ;

mutate_if(data, is.character, funs(trimws(.)))
0

More articles:


All Articles