def classification_preprocess_all_datasets():
"""
Preprocesses all datasets to be ready for classification task.
This will include stemming, word correction, lower-casing, hashtag removal, special char removal.
"""
for i in range(0,len(utils.annotated_datasets)):
tweetlines = utils.get_dataset(utils.annotated_datasets[i])
tweets = []
for line in tweetlines:
if len(line)>1:
tweets.append(tweet.to_tweet(line))
# tweets = lower_case(tweets)
tweets = remove_hastags_and_users(tweets)
tweets = count_emoticons(tweets)
tweets = replace_links(tweets)
tweets = remove_specialchars(tweets)
tweets = correct_words(tweets)
tweets = stem(tweets)
tweets = tokenize(tweets)
tweets = pos_tag(tweets)
tweets = count_exclamations(tweets)
analyzer = Analyzer(utils.annotated_datasets[i], tweets)
stats = analyzer.analyze()
print stats
#store tweets in pickles...
print "Storing pickles..."
utils.store_pickles(tweets, utils.annotated_datasets[i][24:len(utils.annotated_datasets[i])-4])
def preprocess_temporal_dataset():
tweetlines = utils.get_dataset(utils.complete_datasets[3])
tweets = []
for line in tweetlines:
if len(line) > 1:
tweets.append(tweet.to_tweet(line))
tweets = preprocessing.preprocess_tweets(tweets)
sentiments = lexicon.perform_google_sentiment_lexicon_lookup(tweets)
pickle.dump(sentiments, open("temporal_sentiments", "wb"))
pickle.dump(tweets, open("temporal_tweets2", "wb"))
def initial_preprocess_all_datasets():
"""
Runs first preprocessing iteration on all datasets.
This is the preprocessing routine performed initially on the datasets before annotation.
This routine includes duplicate removal
"""
for i in range(0,len(utils.datasets)):
#Fetch from dataset
tweets = []
tweetlines = utils.get_dataset(utils.complete_datasets[i])
for tweetline in tweetlines:
tweets.append(tweet.to_tweet(tweetline))
#Perform preprocessing
tweets = remove_duplicates_and_retweets(tweets)
#Store back to dataset
tweetlines = []
for t in tweets:
tweetlines.append(t.to_tsv())
utils.store_dataset(tweetlines, utils.datasets[i])
replacement_chars = {u"&": u"og",
u"6amp;": u"og",
u"+": u"og"}
if __name__ == '__main__':
#Testing
# tweets = [Tweet("13:37", "johnarne", "Jeg () haaater drittt!!!? :( #justinbieber"), Tweet("13:37", "johnarne", "Jeg eeelsker @erna_solberg http://www.erna.no :) #love #jernerna" )]
# for tweet in tweets:
# tweet.set_sentiment("negative")
# print tweet
tweetlines = utils.get_dataset("test_annotated_data/erna_dataset.tsv")
tweets = []
for line in tweetlines:
if len(line)>1:
tweets.append(tweet.to_tweet(line))
# tweets = lower_case(tweets)
tweets = remove_hastags_and_users(tweets)
tweets = count_emoticons(tweets)
tweets = replace_links(tweets)
tweets = remove_specialchars(tweets)
for tweet in tweets:
print tweet
tweets = correct_words(tweets)
tweets = stem(tweets)
tweets = tokenize(tweets)
for tweet in tweets:
print tweet.stat_str()
tweets = pos_tag(tweets)
def user_annotation():
"""
Feed tweets to console one at a time, and ask user for sentiment annotation.
"""
dataset = utils.select_dataset()
text_tweets = utils.get_dataset(dataset)
tweets = []
for text_tweet in text_tweets:
tweets.append(tweet.to_tweet(text_tweet))
username = raw_input("Name? ... ")
print "\n--------------\n"
print "Input: "
print "\n1: Negative sentiment (Negative opinion). \n2: Neutral/objective sentiment (No opinion). \n3: Positive sentiment (Positive opinion). \n5: Delete the tweet from the dataset. \nx: Cancel sequence. 0: Go back to previous tweet. "
print "\n--------------\n"
annotated_to = 0
i = 0
while i < len(tweets):
# tweets[i].text.encode('utf8')
# text = tweets[i].text
# tweets[i].text = text.decode('utf8')
try:
print "Tweet nr. : "+str(i+1)
print str(((i+1.0*1.0)/len(tweets)*1.0)*100)+" % done "
print unicode(tweets[i].__str__().decode('utf8'))
except UnicodeEncodeError:
try:
print "Tweet nr. : "+str(i+1)
print str(tweets[i])
except UnicodeEncodeError:
print "Could not print tweet number "+str(i+1) +". Deleting tweet..."
tweets.remove(tweets[i])
continue
userinput = raw_input("...")
while not legal_input(userinput):
userinput = raw_input("Unlawful input! Please re-introduce.")
if userinput is '1':
tweets[i].set_sentiment("negative")
elif userinput is '2':
tweets[i].set_sentiment("neutral")
elif userinput is '3':
tweets[i].set_sentiment("positive")
elif userinput is '5':
print "Deleting tweet..."
tweets.remove(tweets[i])
continue
elif userinput is '0':
i = i-1
continue
elif userinput is 'x':
break
i = i+1
#TODO: need to encode to utf when getting from dataset?!?!
#Store the sentiment in file!
tweetlines = []
for t in tweets[:i]:
if t.get_sentiment() is None:
continue
tweetlines.append(t.to_tsv())
dir = username+"_annotated_data"
if not os.path.exists(dir):
os.makedirs(dir)
utils.store_dataset(tweetlines, dir+dataset[4:])
print "Domo arigato!"
