【词云】代码

 1 import sys
 2 reload(sys)
 3 sys.setdefaultencoding(‘utf-8‘)
 4
 5 from os import path
 6 from PIL import Image
 7 import numpy as np
 8 import matplotlib.pyplot as plt
 9
10 from wordcloud import WordCloud
11 import jieba
12 d = path.dirname(__file__)
13
14 stopWordFile = u‘stopwords.txt‘
15 stopWordList = []
16 for L in open(path.join(d , stopWordFile)).readlines():
17     stopWordList.append(L.strip().decode(‘utf-8‘))
18 stopWordList = set(stopWordList)
19
20 new = ‘words.txt‘
21
22 text = open(path.join( d , new )).read().strip(‘\r‘)
23 wordDict = {}
24 for w in jieba.cut(text):
25     if w not in stopWordList:
26         wordDict.setdefault(w , 0)
27         wordDict[w] += 1
28
29 maskImg = ‘china.jpeg‘
30 alice_mask = np.array( Image.open(path.join(d , maskImg)))
31
32 wc = WordCloud(background_color = ‘white‘, max_words = 2000 , mask = alice_mask ,
33                font_path = path.join(d , ‘msyh.ttf‘))
34 wc.generate_from_frequencies(wordDict)
35
36 wc.to_file(path.join(d, "example.png"))
37
38 # show
39 plt.imshow(wc, interpolation=‘bilinear‘)
40 plt.axis("off")
41 plt.figure()
42 plt.imshow(alice_mask, cmap=plt.cm.gray, interpolation=‘bilinear‘)
43 plt.axis("off")
44 plt.show()