【词云】代码

import sys
reload(sys)
sys.setdefaultencoding('utf-8')

from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

from wordcloud import WordCloud
import jieba
d = path.dirname(__file__)

stopWordFile = u'stopwords.txt'
stopWordList = []
for L in open(path.join(d , stopWordFile)).readlines():
    stopWordList.append(L.strip().decode('utf-8'))
stopWordList = set(stopWordList)

new = 'words.txt'

text = open(path.join( d , new )).read().strip('
')
wordDict = {}
for w in jieba.cut(text):
    if w not in stopWordList:
        wordDict.setdefault(w , 0)
        wordDict[w] += 1
    
maskImg = 'china.jpeg'
alice_mask = np.array( Image.open(path.join(d , maskImg)))

wc = WordCloud(background_color = 'white', max_words = 2000 , mask = alice_mask ,
               font_path = path.join(d , 'msyh.ttf'))
wc.generate_from_frequencies(wordDict)

wc.to_file(path.join(d, "example.png"))

# show
plt.imshow(wc, interpolation='bilinear')
plt.axis("off")
plt.figure()
plt.imshow(alice_mask, cmap=plt.cm.gray, interpolation='bilinear')
plt.axis("off")
plt.show()