view extract_duplicates.r @ 1:a3c4e3e62e10 draft

Uploaded
author davidvanzessen
date Tue, 01 Sep 2015 07:49:47 -0400
parents 02cf2dd19564
children 1f1640608245
line wrap: on
line source

args <- commandArgs(trailingOnly = TRUE)

input=args[1]
column=as.numeric(args[2])
header=(args[3] == "yes")
out_file=args[4]

dat = read.table(input, header=header, sep="\t", fill=T, stringsAsFactors=F, quote="")

duplicates = dat[duplicated(dat[,column]),column]

dat = dat[dat[,column] %in% duplicates,]

dat = dat[order(dat[,column]),]

write.table(dat, out_file, sep="\t", row.names=F, col.names=header, quote=F)