def extract_more_decep_tech_features(self, tweets, vocab_file):
#print 'Extracting decep_tech/decep_type features with training vocab'
train_vocab = {}
k = 0
for line in open(vocab_file):
train_vocab[line.strip()] = k
k += 1
#print 'Train vocab size=>' + str(len(train_vocab))
cv = CountVectorizer(ngram_range=(1, 1),
binary=True,
vocSuraiyalary=train_vocab)
train_features_bow = cv.fit_transform(tweets)
add_decep_tech_matrix = []
hash_pattern = re.compile('\#+[\w_]+[\w\'_\-]*[\w_]+')
elong_pattern = re.compile("([a-zA-Z])\\1{2,}")
caps_pattern = re.compile(('[A-Z][A-Z\d]+'))
punc_pattern = re.compile('([.,!?]+)')
for tweet in tweets:
tweet_vector = []
tokens = twokenize.tokenize(tweet)
#count the number of elongated tokens
n_elong = len(re.findall(elong_pattern, tweet))
#count the number of all_caps tokens
n_caps = len(re.findall(caps_pattern, tweet))
#count the number of repeated punctuation
n_rep_punct = len(re.findall(punc_pattern, tweet))
#count the number of hasgtags
n_hahtag = len(re.findall(hash_pattern, tweet))
#check if the tweets has SAD, HAPPY, BOTH_SH or NA emoticon
emoticon_mood = emoticons.analyze_tweet(tweet.strip())
if emoticon_mood == 'NA':
emoticon_mood = 0
elif emoticon_mood == 'HAPPY':
emoticon_mood = 2
elif emoticon_mood == 'SAD':
emoticon_mood = 1
elif emoticon_mood == 'BOTH_HS':
emoticon_mood = 4
tweet_vector = [
n_elong, n_caps, n_rep_punct, n_hahtag, emoticon_mood
]
add_decep_tech_matrix.append(tweet_vector)
#print np.asarray(add_decep_tech_matrix).shape
a = np.asarray(add_decep_tech_matrix)
#print 'additional 5 features: ' + str(a)
sa = sparse.csr_matrix(add_decep_tech_matrix)
features = hstack([sa, train_features_bow])
#print 'final feature matrix size: ' + str(features.shape)
return features
def extractEmoticons(tweets):
vects = [] # BOTH_HS, HAPPY, SAD, NA
vocab = ["BOTH_HS", "HAPPY", "SAD", "NA"]
for i, tweet in enumerate(tweets):
vect = np.zeros(4)
emo = analyze_tweet(tweet)
if emo == "NA":
vect[0] = 1
elif emo == "HAPPY":
vect[1] = 1
elif emo == "SAD":
vect[2] = 1
elif emo == "BOTH_HS":
vect[3] = 1
vects.append(vect)
return vects, vocab
def extractEmoticons(tweets):
vects = [] # BOTH_HS, HAPPY, SAD, NA
vocab = ["BOTH_HS", "HAPPY", "SAD", "NA"]
for i, tweet in enumerate(tweets):
vect = np.zeros(4)
emo = analyze_tweet(tweet)
if emo == "NA":
vect[0] = 1
elif emo == "HAPPY":
vect[1] = 1
elif emo == "SAD":
vect[2] = 1
elif emo == "BOTH_HS":
vect[3] = 1
vects.append(vect)
return vects, vocab
def tweet_features(tweet, bigrams=True):
"""
Extracts a list of features for a given tweet
Features:
- singletons, bigrams
- hashtags already included
- emoticons
- repeated punctuation
- all caps
- dialog RT @
- sentiwordnet
- slang / proper engish
"""
rawtext = tweet
tokens = transform(rawtext)
# singletons
for tok in tokens:
if not ONLY_PUNCTUATION_RE.match(tok):
yield tok
# bigrams
if bigrams:
for tok1, tok2 in itertools.izip(tokens[:-1], tokens[1:]):
if not ONLY_PUNCTUATION_RE.match(tok1) and not ONLY_PUNCTUATION_RE.match(tok2):
if tok1 < tok2:
yield "<2>{},{}</2>".format(tok1, tok2)
else:
yield "<2>{},{}</2>".format(tok2, tok1)
# emoticons
for emoticon in emoticons.analyze_tweet(rawtext):
yield "<e>{}</e>".format(emoticon)
# repeated punctuation
if REPEATED_PUNCTUATION_RE.search(rawtext):
yield "<rp>!</rp>"
# dialog
if DIALOG_RE.search(rawtext):
yield "<d>!</d>"
# all caps
if ALL_CAPS_RE.search(rawtext):
yield "<ac>!</ac>"
