tweet_1 = tweetLibrary.decode_tweet(tweets[0]) tweet_2 = tweetLibrary.decode_tweet(tweets[1]) tweet_3 = tweetLibrary.decode_tweet(tweets[2]) tweet_4 = tweetLibrary.decode_tweet(tweets[3]) print tweetLibrary.get_timestamp(tweet_1) == 'Thu Oct 29 17:51:50 +0000 2015' print tweetLibrary.get_timestamp(tweet_2) == 'Thu Oct 29 17:51:51 +0000 2015' print tweetLibrary.get_timestamp(tweet_3) == "Thu Oct 29 18:10:49 +0000 2015" print tweetLibrary.get_timestamp(tweet_4) == "Thu Oct 29 18:10:49 +0000 2015" print tweet_2["text"] print tweet_1["text"] print tweet_3["text"] print tweet_4["text"] #Test 3: extract hashtags print 'TEST 3: Extracting Hashtags' tweet_5 = tweetLibrary.get_tweet_text(tweetLibrary.decode_tweet(tweets[10])) tweet_6 = tweetLibrary.get_tweet_text(tweetLibrary.decode_tweet(tweets[23])) tweet_7 = tweetLibrary.get_tweet_text(tweetLibrary.decode_tweet(tweets[39])) tweet_8 = tweetLibrary.get_tweet_text(tweetLibrary.decode_tweet(tweets[88])) print tweetLibrary.extract_hashtags(tweet_5) == ['#Trump', '#Election', '#News'] print tweetLibrary.extract_hashtags(tweet_6) == ['#hiring', '#BusinessMgmt', '#NettempsJobs', '#MenloPark', '#Job', '#Jobs', '#CareerArc'] print tweetLibrary.extract_hashtags(tweet_7) == ['#Hangry', '#Rhonda'] print tweetLibrary.extract_hashtags(tweet_8) == ['#TUAUSENCIA'] #Test 4: Type of tweets[i] print 'TEST 4: Check that type of decoded tweet is dictionary' print type(tweetLibrary.decode_tweet(tweets[3])) is dict print type(tweetLibrary.decode_tweet(tweets[77])) is dict #Test 5: Hashtag connections print 'TEST 5: Hashtag connections'
import json
import tweetLibrary
tweets = open('tweets.txt')
tweets = tweets.readlines()
tweet_timestamps = []
tweet_hashtags = []
output = open('tweet_output/ft2.txt', 'w')
for i in range(0,len(tweets)):
tweet = tweetLibrary.decode_tweet(tweets[i])
tweet_timestamps.append(int(tweetLibrary.get_ms_timestamp(tweet)))
tweet_hashtags.append(tweetLibrary.extract_hashtags(tweetLibrary.get_tweet_text(tweet)))
current_timestamps=[]
lowest_index = 0
for i in range(1,len(tweet_timestamps)):
current_timestamps.append(tweet_timestamps[i])
print i
#lowest_index is the lowest index of current_timestamps where the element at that index is
#within 60 seconds of element i
lowest_index = tweetLibrary.compare_timestamp_list(current_timestamps)
del current_timestamps[0:lowest_index]
current_hashtags = tweet_hashtags[i-len(current_timestamps):i]
output.write('Current average degree:')
output.write(str(tweetLibrary.get_average_degree(tweetLibrary.get_hashtag_dictionary(current_hashtags))))
output.write('\n')
output.close()