Skip to content

Instantly share code, notes, and snippets.

View mjcreativeventures's full-sized avatar

Mark Kay mjcreativeventures

  • MJ Creative Ventures Pte Ltd
  • Singapore
View GitHub Profile
@mjcreativeventures
mjcreativeventures / tweet_classifier.py
Created February 15, 2016 05:27
Supervised Classification of Tweets
import nltk
import random
import re
STATIONS = [
'Admiralty MRT',
'Aljunied MRT',
'Ang Mo Kio MRT',
'Bartley MRT',
'Bayfront MRT',
@mjcreativeventures
mjcreativeventures / geocode.py
Created February 15, 2016 05:03
Calculate Journey Times
import simplejson, urllib
import re
import time
import operator
import os
import sys
import argparse
from collections import defaultdict
REMOVE_HTML_TAGS = r'<[^>]+>'
@mjcreativeventures
mjcreativeventures / twitter_network.py
Created February 15, 2016 04:49
Process twitter data to generate an output file of relationships between twitter account
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
mjcreativeventures / get_followers.py
Created February 15, 2016 04:43
Collect twitter followers
import tweepy
import time
import os
import sys
import json
import argparse
FOLLOWING_DIR = 'following'
MAX_FRIENDS = 200
FRIENDS_OF_FRIENDS_LIMIT = 200
@mjcreativeventures
mjcreativeventures / logging.conf
Created February 15, 2016 04:04
nginx logging using json format
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"';