crazyhottommy's Gist

groupby.py

# this script reformats the tab delimited file like:
#FBgn00001 GO:0016301 [Name:****(annotation)]
#FBgn00002 GO:0016301 [Name:****(annotation)]
#FBgn00003 GO:0016301 [Name:****(annotation)]
#FBgn00004 GO:0003700 [Name:****(annotation)]
#FBgn00004 GO:0009651 [Name:****(annotation)]
#FBgn00004 GO:0006355 [Name:****(annotation)]
#FBgn00005 GO:0009556 [Name:****(annotation)]
#FBgn00005 GO:0005515 [Name:****(annotation)]
#FBgn00005 GO:0080019 [Name:****(annotation)]
#FBgn00005 GO:0016563 [Name:****(annotation)]
#FBgn00005 GO:0016627 [Name:****(annotation)]
#FBgn00006 GO:0003700 [Name:****(annotation)]
#FBgn00006 GO:0010018 [Name:****(annotation)]
# to:
# FBgn00001 GO:0016301
#FBgn00002 GO:0016301
#FBgn00003 GO:0016301
#FBgn00004 GO:0003700 GO:0009651 GO:0006355
#FBgn00005 GO:0009556 GO:0005515 GO:0080019 GO:0016563 GO:0016627
#FBgn00006 GO:0003700 GO:0010018

import csv
reader = csv.reader(open("GO.txt","r"), delimiter="\t")
new={}
for row in reader:
    if row[0] not in new.keys():
        new[row[0]] = [row[1]]
    else:
        new[row[0]].append(row[1])


with open("wego.txt","w") as f:
    for key, value in sorted(new.items()):
       f.write(key+"\t"+"\t".join(value)+"\n")