term_similarity.py 文件源码

def boc_term_vectors(word_list):
    word_list = [word.lower() for word in word_list]
    unique_chars = np.unique(
                        np.hstack([list(word) 
                        for word in word_list]))
    word_list_term_counts = [{char: count for char, count in itemfreq(list(word))}
                             for word in word_list]

    boc_vectors = [np.array([int(word_term_counts.get(char, 0)) 
                            for char in unique_chars])
                   for word_term_counts in word_list_term_counts]
    return list(unique_chars), boc_vectors