def add_tweet(self, tweet):
self.tweets_by_id[tweet['id']] = tweet
toks = tweet['toks']
self.model.info['big_n'] += len(toks)
the_unigrams = set(bigrams.filtered_unigrams(toks))
tweet['unigrams'] = the_unigrams
for unigram in the_unigrams:
self.model.add(unigram)
self.index[unigram].append(tweet)
the_bigrams = set(bigrams.filtered_bigrams(toks))
tweet['bigrams'] = the_bigrams
for bigram in the_bigrams:
self.model.add(bigram)
self.index[bigram].append(tweet)
self.bigram_index[bigram[0], None].append(bigram)
self.bigram_index[None, bigram[1]].append(bigram)
tweet['trigrams'] = set(bigrams.filtered_trigrams(toks))
for trigram in tweet['trigrams']:
self.model.add(trigram)
self.index[trigram].append(tweet)
def add_tweet(self, tweet):
self.tweets_by_id[tweet['id']] = tweet
toks = tweet['toks']
self.model.info['big_n'] += len(toks)
the_unigrams = set(bigrams.filtered_unigrams(toks))
tweet['unigrams'] = the_unigrams
for unigram in the_unigrams:
self.model.add(unigram)
self.index[unigram].append(tweet)
the_bigrams = set(bigrams.filtered_bigrams(toks))
tweet['bigrams'] = the_bigrams
for bigram in the_bigrams:
self.model.add(bigram)
self.index[bigram].append(tweet)
self.bigram_index[bigram[0], None].append(bigram)
self.bigram_index[None, bigram[1]].append(bigram)
tweet['trigrams'] = set(bigrams.filtered_trigrams(toks))
for trigram in tweet['trigrams']:
self.model.add(trigram)
self.index[trigram].append(tweet)
import sys
sys.path.insert(0, '/usr2/corpora/tweets/tweetmotif')
import twokenize, util, bigrams
util.fix_stdio()
from sane_re import *
AposFix = _R(r"( |^)(' [stm])( |$)")
for line in sys.stdin:
parts = util.unicodify(line[:-1]).split("\t")
text = parts[-1]
toks = twokenize.simple_tokenize(text)
toked = " ".join(toks)
#print "\t".join(parts[:-1]) + "\t" + toked
#try: AposFix.show_match(toked)
#except: pass
featstr = AposFix.gsub(toked,
lambda m: m[1] + m[2].replace(" ", "") + m[3])
featstr = featstr.lower()
toks = featstr.split()
feats = [ug[0] for ug in bigrams.filtered_unigrams(toks)]
feats += ["_".join(ng) for ng in bigrams.filtered_bigrams(toks)]
print "\t".join(parts[:-1]) + "\t" + util.unicodify(" ".join(feats))
import sys
sys.path.insert(0,'/usr2/corpora/tweets/tweetmotif')
import twokenize,util,bigrams
util.fix_stdio()
from sane_re import *
AposFix = _R(r"( |^)(' [stm])( |$)")
for line in sys.stdin:
parts = util.unicodify(line[:-1]).split("\t")
text = parts[-1]
toks = twokenize.simple_tokenize(text)
toked = " ".join(toks)
#print "\t".join(parts[:-1]) + "\t" + toked
#try: AposFix.show_match(toked)
#except: pass
featstr = AposFix.gsub(toked, lambda m: m[1]+m[2].replace(" ","")+m[3])
featstr = featstr.lower()
toks = featstr.split()
feats = [ug[0] for ug in bigrams.filtered_unigrams(toks)]
feats += ["_".join(ng) for ng in bigrams.filtered_bigrams(toks)]
print "\t".join(parts[:-1]) + "\t" + util.unicodify(" ".join(feats))
