def test_load_review_words(): dal = ReviewsDAL() r_stream = dal.load_reviews_words("unlabeled") for index in xrange(10): review = next(r_stream) print "*************** {} ***************".format(index+1) print "sentiment: {}".format(review.sent.sentiment) print "words: {}".format(review.sent.words) dal.close()
def test_load_review_words(): dal = ReviewsDAL() r_stream = dal.load_reviews_words("unlabeled") for index in xrange(10): review = next(r_stream) print "*************** {} ***************".format(index + 1) print "sentiment: {}".format(review.sent.sentiment) print "words: {}".format(review.sent.words) dal.close()
def stream(self): dal = ReviewsDAL() review_stream = dal.load_words(self._colname) for index, r in enumerate(review_stream): self.append_sentiment_words(r.sent.words) yield r.sent.words if index % 300 == 0: print "{} examples loaded from mongodb[{}]".format(index + 1, self._colname) dal.close()
def words_stream(): word_coder = WordCoder() dal = ReviewsDAL() review_stream = dal.load_words() for index, r in enumerate(review_stream): yield word_coder.code(r.sent.words) if index % 300 == 0: print "{} examples loaded from mongodb".format(index + 1) dal.close()
def words_stream(self): self._metas = [] dal = ReviewsDAL() review_stream = dal.load_words(self._colname) for index, r in enumerate(review_stream): self._metas.append((r.id, r.sent.sentiment)) yield r.sent.words if index % 300 == 0: print "{} examples loaded from mongodb[{}]".format(index + 1, self._colname) dal.close()
def read_save_mongodb(filename,labeled,colname,buffersize=300): r_stream = reviews_stream(filename,labeled) dal = ReviewsDAL() buffer = [] for index,review in enumerate(r_stream): if index % buffersize == 0: dal.insert_many(colname,buffer) del buffer[:] # clear print "{} reviews saved into mongo[{}]".format(index,colname) buffer.append(review) dal.insert_many(colname,buffer) dal.close() print "----------- DONE -----------" print "totally {} reviews inserted into mongodb[{}]".format(index+1,colname)
def read_save_mongodb(buffersize=300): r_stream = review_stream() dal = ReviewsDAL() buffer = [] for index,review in enumerate(r_stream): if index % buffersize == 0: dal.insert_many(buffer) del buffer[:] # clear print "{} reviews saved into mongodb".format(index) buffer.append(review) dal.insert_many(buffer) dal.close() print "----------- DONE -----------" print "totally {} reviews inserted into mongodb".format(index+1)
coded_words = wordcoder.code(sentence.words) bow = dictionary.doc2bow(coded_words) topic_distribution = lda_model[bow] topic_distribution.sort(key=lambda t: t[1], reverse=True) tags = None for index, (topic_id, topic_percentage) in enumerate(topic_distribution): mt = MixTopic(topic_mapping[topic_id]) mt.weight(topic_percentage) if tags is None: tags = mt else: tags.add(mt) tags.normalize() print tags if __name__ == "__main__": dal = ReviewsDAL() review_stream = dal.sampling(10) for index,review in enumerate( review_stream): print "*********** [{}] ***********".format(index+1) for sentence in sent_tokenizer.tokenize(review.sent.raw): print_topics(sentence) dal.close()