Function tokens_to_vector

nlp_class/sentiment.py:94–101

(tokens, label)

# now let's create our input matrices
def tokens_to_vector(tokens, label):
    x = np.zeros(len(word_index_map) + 1) # last element is for the label
    for t in tokens:
        i = word_index_map[t]
        x[i] += 1
    x = x / x.sum() # normalize it before setting label
    x[-1] = label
    return x

N = len(positive_tokenized) + len(negative_tokenized)
# (N x D+1 matrix - keeping them together for now so we can shuffle more easily later