lyric_nlp.py 文件源码

def lyrics():
    with open('lyrics.json', 'r', encoding='utf-8') as f:
        data = json.load(f)
    tokens = list()
    for v in data.values():
        # ??????, ???????? 2 ??, ?????
        tokens += [seg for seg in jieba.cut(v) if seg.split() and len(seg) > 1]

    # ?? tokens ?????????
    counter = Counter(tokens)
    print(counter.most_common(10))

    # ???, ???????????
    wcloud = WordCloud(font_path='NotoSansMonoCJKtc-Regular.otf').generate(' '.join(tokens))
    plt.imshow(wcloud)
    plt.axis('off')
    plt.show()