//Usinng Word2Vec
model = gensim.models.Word2Vec(X, size=100) // x be tokenized text
w2v = dict(zip(model.wv.index2word, model.wv.syn0))
class MeanEmbeddingVectorizer(object):
def __init__(self, word2vec):
After Change
train_count = countV.fit_transform(DataPrep.train_news["Statement"].values)
print(countV)
print(train_count)
//print training doc term matrix
//we have matrix of size of (10240, 12196) by calling below
def get_countVectorizer_stats():
