运用jieba库分词并生成词云库。

话不多说,直接上代码。

import jieba

txt = open("C:\\Users\\Administrator\\Desktop\\流浪地球","r", encoding='utf-8').read()

words = jieba.lcut(txt)
counts = {}

for word in words:
if len(word) == 1:
continue
else:
counts[word] = counts.get(word, 0) + 1

items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)

for i in range(15):
word, count = items[i]
print("{0:<5}{1:>5}".format(word, count))

def create_word_cloud(filename):
    text = open("{}.txt".format(filename)).read()
    # 结巴分词
    wordlist = jieba.cut(text, cut_all=True)
    wl = " ".join(wordlist)

    # 设置词云
    wc = WordCloud(
        # 设置背景颜色
        background_color="white",
        
        max_words=2000,
        
        font_path='C:\Windows\Fonts\simfang.ttf',
        height=1200,
        width=1600,
        
        max_font_size=200,
        
        random_state=100,
    )

    myword = wc.generate(wl) 
    
    plt.imshow(myword)
    plt.axis("off")
    plt.show()
    wc.to_file('p.png')  


if __name__ == '__main__':
    create_word_cloud('C:\\Users\\Administrator\\Desktop\\阿Q正传')



猜你喜欢

转载自www.cnblogs.com/gsd-tt/p/10652390.html