test["review"].size, unlabeled_train["review"].size )
# Load the punkt tokenizer
tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
# ****** Split the labeled and unlabeled training sets into clean sentences
#
sentences = [] # Initialize an empty list of sentences
print "Parsing sentences from training set"
for review in train["review"]:
sentences += Util.review_to_sentences(review, tokenizer)
print "Parsing sentences from unlabeled set"
for review in unlabeled_train["review"]:
sentences += Util.review_to_sentences(review, tokenizer)
# ****** Set parameters and train the word2vec model
#
# Import the built-in logging module and configure it so that Word2Vec
# creates nice output messages
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',\
level=logging.INFO)
# Set values for various parameters
num_features = 300 # Word vector dimensionality
min_word_count = 40 # Minimum word count
