Skip to content

Instantly share code, notes, and snippets.

@lukashavrlant
Created June 11, 2014 08:50
Show Gist options
  • Save lukashavrlant/c11ca09ba2e257a82362 to your computer and use it in GitHub Desktop.
Save lukashavrlant/c11ca09ba2e257a82362 to your computer and use it in GitHub Desktop.
import sys
from glob import glob
from os.path import join
ID_SERVER = 0
ID_SECTION = 1
ID_PLACEMENT = 2
BANNER_TYPE = 3
UUID_INDEX = 27
users = dict()
for path in glob(join(sys.argv[1], '*.csv')):
with open(path) as f:
for line in f:
arr = line.split("\t")
if arr[UUID_INDEX] != "0":
if users.get(arr[ID_SERVER], False):
users[arr[ID_SERVER]].add(arr[UUID_INDEX])
else:
users[arr[ID_SERVER]] = set([UUID_INDEX])
for k, v in users.items():
print "SERVER_ID: %s, cardinality: %s" % (k, len(v))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment