I have a table like the following:
myDT <- fread(
"id,other,strformat,content
1, other1, A:B, a1:b1
2, other2, A:C, a2:c2
3, other3, B:A:C, b3:a3:c3
4, other4, A:B, a4:b4
5, other5, XX:whatever, xx5:whatever5
")
And I want to split the content
column based on strformat
, to get this:
id other strformat content A B C XX whatever
1: 1 other1 A:B a1:b1 a1 b1 <NA> <NA> <NA>
2: 2 other2 A:C a2:c2 a2 <NA> c2 <NA> <NA>
3: 3 other3 B:A:C b3:a3:c3 a3 b3 c3 <NA> <NA>
4: 4 other4 A:B a4:b4 a4 b4 <NA> <NA> <NA>
5: 5 other5 XX:whatever xx5:whatever5 <NA> <NA> <NA> xx5 whatever5
I failed with tstrsplit()
on by=
:
myDT[, unlist(strsplit(strformat,':')):=tstrsplit(content,':'), by=strformat]
# Error in strsplit(strformat, ":") : object 'strformat' not found
So for now I resorted to using a cycle:
for (this.format in unique(myDT$strformat)){
myDT[strformat==this.format, unlist(strsplit(this.format,':')):=tstrsplit(content,':')]
}
It does the job, but I'm still wondering what would be the right way with by=
So, I have tested 3 solutions kindly suggested by @akrun, with slight modifications. Skipped the last one because it has the column names hardcoded.
# define functions to compare:
require(splitstackshape)
f_csplit <- function(inpDT, col_format='strformat', col_content='content', sep=':'){
invisible(inpDT[dcast(
cSplit(inpDT, c(col_format, col_content), sep, "long"),
as.formula(paste('id',col_format,sep='~')),
value.var=col_content
), , on = .(id)])
}
f_lapply_str <- function(inpDT, col_format='strformat', col_content='content', sep=':'){
invisible(inpDT[dcast(
inpDT[, unlist(lapply(.SD, strsplit, sep), recursive = FALSE), by = id, .SDcols = 2:3],
as.formula(paste('id',col_format,sep='~')),
value.var=col_content
), on = .(id)])
}
require(tidyverse)
f_unnest <- function(inpDT, col_format='strformat', col_content='content', sep=':'){
invisible(inpDT[dcast(
unnest(inpDT[, lapply(.SD, tstrsplit, sep),by = id, .SDcols = 2:3]),
as.formula(paste('id',col_format,sep='~')),
value.var=col_content
), on = .(id)])
}
f_cycle <- function(inpDT, col_format='strformat', col_content='content', sep=':'){
inpDT <- copy(inpDT); # in fact I don't even need to make a copy:
# := modifies the original table which is fine for me -
# but for benchmarking let's make a copy
for (this.format in unique(inpDT[[col_format]])){
inpDT[get(col_format)==this.format, unlist(strsplit(this.format,sep)):=tstrsplit(get(col_content),sep)]
}
invisible(inpDT)
}
It seems that solutions #2 (lapply
of strsplit
, without cSplit
) and #3 (unnest)
don't work correctly when I have any other columns in the table, it only works if I remove "other":
myDT[dcast(myDT[, unlist(lapply(.SD, strsplit, ":"), recursive = FALSE), by = id, .SDcols = 2:3], id ~ strformat), on = .(id)]
# id other strformat content A B C XX whatever
# 1: 1 other1 A:B a1:b1 A B <NA> <NA> <NA>
# 2: 2 other2 A:C a2:c2 A <NA> C <NA> <NA>
# 3: 3 other3 B:A:C b3:a3:c3 A B C <NA> <NA>
# 4: 4 other4 A:B a4:b4 A B <NA> <NA> <NA>
# 5: 5 other5 XX:whatever xx5:whatever5 <NA> <NA> <NA> XX whatever
myDT[dcast(unnest(myDT[, lapply(.SD, tstrsplit, ":"),by = id, .SDcols = 2:3]), id ~ strformat), on = .(id)]
# (same result as above)
myDT$other <- NULL
myDT[dcast(myDT[, unlist(lapply(.SD, strsplit, ":"), recursive = FALSE), by = id, .SDcols = 2:3], id ~ strformat), on = .(id)]
# id strformat content A B C XX whatever
# 1: 1 A:B a1:b1 a1 b1 <NA> <NA> <NA>
# 2: 2 A:C a2:c2 a2 <NA> c2 <NA> <NA>
# 3: 3 B:A:C b3:a3:c3 a3 b3 c3 <NA> <NA>
# 4: 4 A:B a4:b4 a4 b4 <NA> <NA> <NA>
# 5: 5 XX:whatever xx5:whatever5 <NA> <NA> <NA> xx5 whatever5
myDT[dcast(unnest(myDT[, lapply(.SD, tstrsplit, ":"),by = id, .SDcols = 2:3]), id ~ strformat), on = .(id)]
# (same correct result as above)
Here is the benchmarking with "other" columns removed:
# make a bigger table based on a small one:
myDTbig <- myDT[sample(nrow(myDT),1e5, replace = T),]
myDTbig[, id:=seq_len(nrow(myDTbig))]
myDTbig$other <- NULL
require(microbenchmark)
print(microbenchmark(
f_csplit(myDTbig),
f_lapply_str(myDTbig),
f_unnest(myDTbig),
f_cycle(myDTbig),
times=10L
), signif=2)
# Unit: milliseconds
# expr min lq mean median uq max neval
# f_csplit(myDTbig) 420 430 470 440 450 670 10
# f_lapply_str(myDTbig) 4200 4300 4700 4700 5100 5400 10
# f_unnest(myDTbig) 3900 4400 4500 4500 4800 5100 10
# f_cycle(myDTbig) 88 96 98 98 100 100 10
And with "other" columns kept:
# make a bigger table based on a small one:
myDTbig <- myDT[sample(nrow(myDT),1e5, replace = T),]
myDTbig[, id:=seq_len(nrow(myDTbig))]
require(microbenchmark)
print(microbenchmark(
f_csplit(myDTbig),
f_cycle(myDTbig),
times=100L
), signif=2)
# Unit: milliseconds
# expr min lq mean median uq max neval
# f_csplit(myDTbig) 410 440 500 460 490 1300 100
# f_cycle(myDTbig) 84 93 110 96 100 270 100
And below is with my real dataset. Well, actually, only 1/10th of it: with the full one I had memory allocation error on csplit
solution (while the one with the cycle worked fine).
myDTbig <- dt.vcf[1:2e6,]
myDTbig[,id:=seq_len(nrow(myDTbig))]
print(microbenchmark(
f_csplit(myDTbig, 'FORMAT', 'S_1'),
f_cycle(myDTbig, 'FORMAT', 'S_1'),
times=5L
), signif=2)
# Unit: seconds
# expr min lq mean median uq max neval
# f_csplit(myDTbig, "FORMAT", "S_1") 15.0 16.0 16 16.0 16.0 17.0 5
# f_cycle(myDTbig, "FORMAT", "S_1") 4.9 4.9 6 5.7 5.8 8.5 5
Finally, I tested if having many levels in format
column (i.e. how many cycles we have to run) will increase the time for the solution with the cycle:
myDTbig <- myDT[sample(nrow(myDT),1e6, replace = T),]
myDTbig[, strformat:=paste0(strformat,sample(letters,1e6, replace = T)),]
length(unique(myDTbig$strformat)) # 104
myDTbig[, id:=seq_len(nrow(myDTbig))]
print(microbenchmark(
f_csplit(myDTbig),
f_cycle(myDTbig),
times=10L
), signif=2)
# Unit: seconds
# expr min lq mean median uq max neval
# f_csplit(myDTbig) 7.3 7.4 7.7 7.6 7.9 8.4 10
# f_cycle(myDTbig) 2.7 2.9 3.0 2.9 3.0 3.8 10
So, as a conclusion - surprisingly, the cycle performed better than anything else for this task.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With