Last active
December 22, 2015 10:49
-
-
Save suminb/6461731 to your computer and use it in GitHub Desktop.
Analytics
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from multiprocessing import Pool | |
from collections import Counter | |
from operator import add, itemgetter | |
import os, sys | |
import csv | |
def substrings(s): | |
n = len(s) | |
for i in xrange(0, n): | |
for j in xrange(i+1, n+1): | |
yield s[i:j] | |
def count(string): | |
counts = {} | |
for substring in substrings(string): | |
if len(substring) < 10: | |
key = ','.join(substring) | |
if key in counts: | |
counts[key] += 1 | |
else: | |
counts[key] = 1 | |
return counts | |
def read_csv(fin): | |
for row in csv.reader(fin, delimiter=',', quotechar='"'): | |
yield row[5].split() | |
if __name__ == '__main__': | |
pool = Pool(8) | |
counts = pool.map(count, read_csv(sys.stdin)) | |
counts = reduce(add, map(Counter, counts)) | |
counts = sorted(counts.iteritems(), key=itemgetter(1)) | |
for c in counts: | |
print '{} :: {}'.format(c[1], c[0]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment