Created
September 3, 2014 13:12
-
-
Save maximveksler/410917425c7c4bbf8cc7 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
#!/usr/bin/python | |
import csv | |
import re | |
from collections import Counter, OrderedDict | |
count_total = Counter() | |
count_by_date = {} | |
def get_count_today(by_date): | |
if not by_date in count_by_date: | |
count_by_date[by_date] = Counter() | |
return count_by_date[by_date] | |
with open('dribbble.csv', 'rb') as csvfile: | |
spamreader = csv.reader(csvfile, delimiter=',') | |
for row in spamreader: | |
delimiters = "; " | |
regexPattern = '|'.join(map(re.escape, delimiters)) | |
tags_string=row[11] | |
by_date = row[8] | |
# Count the tags | |
tags = re.split(regexPattern, tags_string) | |
for t in tags: | |
if t: | |
count_total[t] += 1 | |
get_count_today(by_date)[t] += 1 | |
print "Total\n\n", count_total.most_common(50), "\n\n" | |
print "By Date:" | |
for by_date_counter in OrderedDict(sorted(count_by_date.items(), key=lambda t: t[0])): | |
print by_date_counter, ": \n", count_by_date[by_date_counter].most_common(50) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment