def combine(filename1, filename2):
list1 = FileFunc.read_file_into_list(filename1)
list2 = FileFunc.read_file_into_list(filename2)
print(list1)
combinedMap = {}
list1.pop(0)
for e in list1:
tokens = e.split(',')
combinedMap[(tokens[0], tokens[1])] = 0
list2.pop(0)
for e in list2:
tokens = e.split(',')
combinedMap[(tokens[0], tokens[1])] = 0
for e in list1:
tokens = e.split(',')
combinedMap[(tokens[0], tokens[1])] += int(tokens[2])
for e in list2:
tokens = e.split(',')
combinedMap[(tokens[0], tokens[1])] += int(tokens[2])
with open('combinedEdges.csv', 'w') as f:
f.write('User1,User2,ComFreq\n')
with open('combinedEdges.csv', 'a') as f:
for edge in combinedMap.items():
f.write(str(edge[0][0]) + ',' + str(edge[0][1]) + ',' + str(edge[1]) + '\n')
def __init__(self):
os.chdir("data")
# slang data from https://floatcode.wordpress.com/tag/dataset/
with open("../data/slang.txt", 'rt') as f:
reader = csv.reader(f, delimiter='`', quoting=csv.QUOTE_NONE)
self.slang = [row[0] for row in reader]
self.intensifiers = FileFunc.read_file_into_list("../data/intensifier.txt")
self.exclamations = FileFunc.read_file_into_list("../data/exclamatoryWord.txt")
self.modalVerbs = FileFunc.read_file_into_list("../data/modalVerb.txt")
self.pronouns = FileFunc.read_file_into_list("../data/pronoun.txt")
self.emoticons = FileFunc.read_file_into_list("../data/emoticon.txt")
def split(filename):
tweets = FileFunc.read_file_into_list_unicode('tweets.csv')
data = []
for tweet in tweets:
tmp = tweet.split(',')
data.append({'user': tmp[0], 'tweet': simpleTokenize(tmp[1])})
return data
def parse():
hashtags = FileFunc.read_file_into_list('allhashtags.csv') #gather hashtags
tweets = split('tweets.csv') #parse the tweet data
tweets.pop(0) #remove header
users = [] #collect all unique users
for tweet in tweets:
if tweet['user'] not in users:
users.append(tweet['user'])
# print(users)
# print(tweets)
tagdict = {}
for hashtag in hashtags: #initialize lists
tagdict[hashtag] = []
for tweet in tweets: #check all tweets, hashtags and map users to hashtags
for hashtag in hashtags:
if hashtag in tweet['tweet']:
if tweet['user'] not in tagdict[hashtag]:
tagdict[hashtag].append(tweet['user'])
# print(tweet) #add user to hashtag dictionary
edgemap = {}
for hashtag in tagdict:
if len(tagdict[hashtag]) > 1:
tagdict[hashtag].sort()
for hashtag in tagdict:
if len(tagdict[hashtag]) > 1:
for user1 in tagdict[hashtag]:
for user2 in tagdict[hashtag]:
if user1 != user2:
l = sorted((user1, user2))
key = (l[0], l[1])
if key in edgemap:
edgemap[key] += 1
else:
edgemap[key] = 1
# print(edgemap)
# print(tagdict)
with open('edge.csv', 'w') as f:
f.write('User1,User2,ComFreq\n')
with open('edge.csv', 'a') as f:
for edge in edgemap.items():
f.write(str(edge[0][0]) + ',' + str(edge[0][1]) + ',' + str(edge[1]) + '\n')
if rules['repeatedCharacters'] and self.repeated_character_rule(term):
return True
if rules['slang'] and len(term) > 1 and term in self.slang:
return True
if rules['caps'] and len(term) > 3 and term.isupper():
return True
return False
if __name__ == '__main__':
personals = PersonalTweetClassifier()
os.chdir("..")
rules = {'intensifiers': True, 'exclamations': True, 'modalVerbs': True, 'emoticons': True, 'repeatedCharacters': True, 'slang': True, 'caps': True}
count = 0
for tweet in FileFunc.read_file_into_list("../test_data.txt"):
for term in tweet.split():
if personals.filter(term, rules):
print(tweet)
count += 1
break
print(count, "'personal' tweets found")
# latent factor model http://ijcai.org/papers15/Papers/IJCAI15-322.pdf
# http://dl.acm.org/citation.cfm?id=1858724
# VADER http://comp.social.gatech.edu/papers/icwsm14.vader.hutto.pdf
