Average word vectors in a text

doc2vec.py

def calc_embedding(text):
    tokens = word_tokenize(text)
    vec = np.zeros(100)
    num_tokens = 0
    for token in tokens:
        if token in stopwords_list:
            continue
        if token in new_model:
            vec += new_model[token]
            num_tokens += 1
    if num_tokens:
        return vec/num_tokens
    else:
        return np.NAN