mjcreativeventures

import nltk
import random
import re

STATIONS = [
        'Admiralty MRT',
        'Aljunied MRT',
        'Ang Mo Kio MRT',
        'Bartley MRT',
        'Bayfront MRT',

mjcreativeventures

import simplejson, urllib
import re
import time
import operator
import os
import sys
import argparse
from collections import defaultdict

REMOVE_HTML_TAGS = r'<[^>]+>'

mjcreativeventures

import glob
import os
import json
import sys
from collections import defaultdict

users = defaultdict(lambda: { 'followers': 0 })

for f in glob.glob('twitter-users/*.json'):
    data = json.load(file(f))

mjcreativeventures

import tweepy
import time
import os
import sys
import json
import argparse

FOLLOWING_DIR = 'following'
MAX_FRIENDS = 200
FRIENDS_OF_FRIENDS_LIMIT = 200

mjcreativeventures

log_format le_json '"time": "$time_iso8601", '
             '"remote_addr": "$remote_addr", '
             '"remote_user": "$remote_user", '
             '"body_bytes_sent": "$body_bytes_sent", '
             '"request_time": "$request_time", '
             '"status": "$status", '
             '"request": "$request", '
             '"request_method": "$request_method", '
             '"http_referrer": "$http_referer", '
             '"http_user_agent": "$http_user_agent"';