memory usage multi value hash

Thu Apr 14 12:55:09 EDT 2011

christian wrote:
> Hello,
>> i'm not very experienced in python. Is there a way doing below more
> memory efficient and maybe faster.
> I import a 2-column file and then concat for every unique value in
> the first column ( key) the value from the second
> columns.
>> So The ouptut is something like that.
> A,1,2,3
> B,3,4
> C,9,10,11,12,90,34,322,21
>>> Thanks for advance & regards,
> Christian
>>> import csv
> import random
> import sys
> from itertools import groupby
> from operator import itemgetter
>> f=csv.reader(open(sys.argv[1]),delimiter=';')
> z=[[i[0],i[1]] for i in f]
> z.sort(key=itemgetter(0))
> mydict = dict((k,','.join(map(itemgetter(1), it)))
> for k, it in groupby(z, itemgetter(0)))
> del(z)
>> f = open(sys.argv[2], 'w')
> for k,v in mydict.iteritems():
> f.write(v + "\n")
>> f.close()

I don't expect that it matters much, but you don't need to sort your data if 
you use a dictionary anyway:
import csv
import sys
infile, outfile = sys.argv[1:]
d = {}
with open(infile, "rb") as instream:
 for key, value in csv.reader(instream, delimiter=';'):
 d.setdefault(key, [key]).append(value)
with open(outfile, "wb") as outstream:
 csv.writer(outstream).writerows(d.itervalues())