莫愁前路无知己,天下谁人不识君。。。。

python----云图小编程2

上一篇 / 下一篇  2017-09-07 20:41:13 / 个人分类:python 小编程

# coding:utf-8
from wordcloud import WordCloud
import jieba
import matplotlib.pyplot as plt
# 读取停用词​
stopwords = {}
def stopword(filename = ''):
global stopwords
f = open(filename, 'r')
line = f.readline().rstrip()
while line:
stopwords.setdefault(line, 0)
stopwords[line.decode('gbk')] = 1
line = f.readline().rstrip()
f.close()
stopword(filename='e:/testandtry/cloudword.txt')

#定义中文分词和停用词清洗
def cleancntxt(txt, stopwords):
seg_generator = jieba.cut(txt, cut_all=False)
seg_list = [i for i in seg_generator if i not in stopwords]
seg_list = [i for i in seg_list if i != u' ']
return(seg_list)

# 定义中文词云函数
def wordcloudplot(txt):
wordcloud = WordCloud(font_path=r'D:/wordcloud/msyh.ttf',
background_color="white", #可以选择blackwhite
margin=5, width=1800, height=800) # 长宽度控制清晰程度​
wordcloud = wordcloud.generate(txt)
# Open a plot of the generated image.
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
def plotTitleCloud(txtlist):
txt = r' '.join(txtlist)
seg_list = cleancntxt(txt, stopwords)
#seg_list = jieba.cut(txt, cut_all=False)
txt = r' '.join(seg_list)
wordcloudplot(txt)
with open('e:/testandtry/cloudword.txt') as f:
t1 = f.readlines()
plotTitleCloud(t1)

TAG: Python python 编程

 

评分:0

我来说两句

Open Toolbar