comparison extract_duplicates.r @ 0:02cf2dd19564 draft

Uploaded
author davidvanzessen
date Fri, 21 Aug 2015 10:49:14 -0400
parents
children a3c4e3e62e10
comparison
equal deleted inserted replaced
-1:000000000000 0:02cf2dd19564
1 args <- commandArgs(trailingOnly = TRUE)
2
3 input=args[1]
4 column=as.numeric(args[2])
5 header=(args[3] == "yes")
6 out_file=args[4]
7
8 dat = read.table(input, header=header, sep="\t", fill=T, stringsAsFactors=F)
9
10 duplicates = dat[duplicated(dat[,column]),column]
11
12 dat = dat[dat[,column] %in% duplicates,]
13
14 dat = dat[order(dat[,column]),]
15
16 write.table(dat, out_file, sep="\t", row.names=F, col.names=header, quote=F)