-
-
Save mrdwab/6873058 to your computer and use it in GitHub Desktop.
#' Split concatenated cells in a \code{data.frame} or a \code{data.table} | |
#' | |
#' A variation of the \code{concat.split} family of functions designed for | |
#' large rectangular datasets. | |
#' | |
#' While the general \code{concat.split} functions are able to handle | |
#' "unbalanced" datasets (for example, where the number of fields in a given | |
#' column might differ from row to row) because of the nature of \code{fread} | |
#' from the "data.table" package, this function does not support such data | |
#' types. | |
#' | |
#' @param dataset The input \code{data.frame} or \code{data.table}. | |
#' @param splitcols The columns that need to be split up. | |
#' @param sep The character that serves as a delimiter within the columns that | |
#' need to be split up. | |
#' @param drop Logical. Should the original columns be dropped? Defaults to | |
#' \code{TRUE}. | |
#' @param dotsub The character that should be substituted as a delimiter | |
#' \emph{if \code{sep = "."}}. \code{fread} does not seem to work nicely with | |
#' \code{sep = "."}, so it needs to be substituted. By default, this function | |
#' will substitute \code{"."} with \code{"|"}. | |
#' @return A \code{data.table}. | |
#' @author Ananda Mahto | |
#' @references \url{http://stackoverflow.com/a/19231054/1270695} | |
#' @examples | |
#' | |
#' small_file <- system.file("concatDT.csv", package = "SOfun") | |
#' small_data <- read.csv(small_file) | |
#' dim(small_data) | |
#' head(small_data) | |
#' out <- concat.split.DT(small_data, | |
#' splitcols = c("VARIABLE", "VAR2", "VAR3", "VAR4"), | |
#' sep = "_", drop = TRUE) | |
#' out | |
#' | |
#' \dontrun{ | |
#' ## Make a much bigger dataset | |
#' big_data <- small_data[rep(rownames(small_data), | |
#' 1500000/nrow(small_data)), ] | |
#' dim(big_data) | |
#' system.time(big_out <- concat.split.DT(big_data, | |
#' splitcols = c("VARIABLE", "VAR2", | |
#' "VAR3", "VAR4"), | |
#' sep = "_", drop = TRUE)) | |
#' big_out | |
#' } | |
#' | |
#' @export concat.split.DT | |
concat.split.DT <- function(dataset, splitcols, sep, drop = TRUE, dotsub = "|") { | |
require(data.table) | |
if (is.numeric(splitcols)) splitcols <- names(dataset)[splitcols] | |
if (!is.data.table(dataset)) dataset <- data.table(dataset) | |
if (sep == ".") { | |
dataset[, (splitcols) := gsub(".", dotsub, get(splitcols), fixed = TRUE)] | |
sep <- dotsub | |
} | |
Splits <- do.call(cbind, lapply(splitcols, function(Z) { | |
x <- tempfile() | |
if (!is.character(dataset[[Z]])) writeLines(as.character(dataset[[Z]]), x) | |
else writeLines(dataset[[Z]], x) | |
Split <- fread(x, sep = sep, header = FALSE) | |
setnames(Split, paste(Z, seq_along(Split), sep = "_")) | |
Split | |
})) | |
final <- cbind(dataset, Splits) | |
if (isTRUE(drop)) final <- final[, setdiff(names(final), splitcols), with = FALSE] | |
final | |
} |
@mrdwab, looks good. Here are some suggestions:
as.data.table(.)
is faster thandata.table(.)
.- Your
sep == "."
if-statement will modifydataset
by reference, if the input dataset is already adata.table
. Is this intended? - Use of
tempfile()
is fine. Atext=.
argument would be much nicer, I agree. I'll write to Matt about this. - A bit more speed-up can be obtained by using
set
instead ofcbind
.
Here's a proof of concept. This function ran in 0.8 seconds as opposed to 2.1 secs on the data out
. But it'd be better to benchmark it on bigger data sets (especially with length(splitcols) > 1
).
concat.split.DT.mod <- function(dataset, splitcols, sep, drop = TRUE, dotsub = "|") {
if (!require(data.table)) stop("data.table package not found")
if (!length(splitcols)) {
warning("No columns to split by, returning dataset as such.")
return(dataset)
}
if (is.numeric(splitcols)) splitcols <- names(dataset)[splitcols]
if (!is.data.table(dataset)) dataset <- as.data.table(dataset) else dataset <- copy(dataset)
if (sep == ".") {
dataset[, (splitcols) := gsub(".", dotsub, get(splitcols), fixed = TRUE)]
sep <- dotsub
}
write_fread <- function(Z) {
x = tempfile()
if (!is.character(dataset[[Z]])) writeLines(as.character(dataset[[Z]]), x)
else writeLines(dataset[[Z]], x)
fread(x, sep = sep, header = FALSE)
}
split_names <- function(Z, Split) {
paste(Z, seq_along(Split), sep = "_")
}
# treat splitcols[1L] first
Splits = write_fread(splitcols[1L])
setnames(Splits, split_names(splitcols[1L], Splits))
for (i in seq_along(splitcols)[-1L]) {
tmp = write_fread(splitcols[i])
set(Splits, i = NULL, j = split_names(splitcols[i], tmp), value = tmp)
}
set(dataset, i = NULL, j = names(Splits), value = Splits)
if (isTRUE(drop)) set(dataset, i = NULL, j = splitcols, value = NULL)
dataset
}
However, one check you'll have to do, if you use set
, is to make sure that the new columns you'll create with set
don't already exist in the data.table. If so, they'll be overwritten. cbind
on the other hand binds duplicate names as such. But it'll make a copy - for every binding.
So, if you can take care of this issue, I'd suggest working on the copy
(either with as.data.table(.)
or copy(.)
as shown above) and using set
.
HTH
This part:
Splits = write_fread(splitcols[1L])
setnames(Splits, split_names(splitcols[1L], Splits))
for (i in seq_along(splitcols)[-1L]) {
tmp = write_fread(splitcols[i])
set(Splits, i = NULL, j = split_names(splitcols[i], tmp), value = tmp)
}
set(dataset, i = NULL, j = names(Splits), value = Splits)
if (isTRUE(drop)) set(dataset, i = NULL, j = splitcols, value = NULL)
dataset
can be written directly with dataset
instead as:
for (i in seq_along(splitcols)) {
Split = write_fread(splitcols[i])
set(dataset, i = NULL, j = split_names(splitcols[i], Split), value = Split)
}
if (isTRUE(drop)) set(dataset, i = NULL, j = splitcols, value = NULL)
dataset
That'll avoid the second set
and add by reference directly yo dataset
.
HTH
Get some medium-sized sample data here. Make it large with:
Try the function: