jieba库使用和好玩的词云

 

 

1、词频分析：

import jieba

txt = open("小王子.txt", "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(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

 

运行结果：

 

2、词云图：

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba
import numpy as np
from PIL import Image
def create_word_cloud(filename):
    txt = open("小王子.txt", "r", encoding='utf-8').read()

    wordlist = jieba.cut(txt, cut_all=True)
    wl = " ".join(wordlist)

    cloud_mask = np.array(Image.open("xin.jpg"))
    wc = WordCloud(
        background_color="white",
        mask=cloud_mask,
        max_words=300,
        font_path='C:\Windows\Fonts\simfang.ttf',
        height=1200,
        width=1600,
        max_font_size=500,
        random_state=50,
    )

    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\\86123\\.spyder-py3\\小王子')

 

运行结果：