Python生成词云图

淩亂°似流年 2023-02-10 05:08 7阅读 0赞

代码如下：  
  
from os import path  
  
from wordcloud import WordCloud  
  
import matplotlib  
  
matplotlib.use('TkAgg')  
  
\# 获取目录地址，读取文本  
  
d = path.dirname(\_\_file\_\_)  
  
text = open(path.join(d, 'haha.txt')).read()  
  
\# 生成一个词云图像  
  
wordcloud = WordCloud().generate(text)  
  
\# pil方式展示生成的词云图像  
  
image = wordcloud.to\_image()  
  
image.show()  
  
from os import path  
  
from PIL import Image  
  
import numpy as np  
  
import matplotlib  
  
matplotlib.use('TkAgg')  
  
from wordcloud import WordCloud, STOPWORDS  
  
d = path.dirname(\_\_file\_\_)  
  
\# 读取整个文本.  
  
text = open(path.join(d, 'haha.txt')).read()  
  
\#读取图片  
  
alice\_mask = np.array(Image.open(path.join(d, "heart.png")))  
  
\#添加停用词  
  
stopwords = set(STOPWORDS)  
  
stopwords.add("HaHa")  
  
\#设置词云的一些属性  
  
wc = WordCloud(background\_color="black", max\_words=2000, mask=alice\_mask,  
  
stopwords=stopwords)  
  
\# 生成词云  
外汇赠金活动http://www.fx61.com/activities  
  
wc.generate(text)  
  
\# pil方式展示生成的词云图像(如果你没有matplotlib)  
  
image = wc.to\_image()  
  
image.show()  
  
from os import path  
  
from PIL import Image  
  
import numpy as np  
  
import matplotlib  
  
matplotlib.use('TkAgg')  
  
import matplotlib.pyplot as plt  
  
from wordcloud import WordCloud, STOPWORDS  
  
import jieba  
  
d = path.dirname(\_\_file\_\_)  
  
\#  
  
\# \# 读取整个文本.  
  
text = open(path.join(d, '中文.txt')).read()  
  
\#  
  
\# print text  
  
\# \#读取图片  
  
alice\_mask = np.array(Image.open(path.join(d, "dog.jpeg")))  
  
stopwords\_path = 'stopwords.txt' \# 停用词词表  
  
my\_words\_list = \['碌碌无为'\] \# 在结巴的词库中添加新词  
  
\# 添加自己的词库分词  
  
def add\_word(list):  
  
for items in list:  
  
jieba.add\_word(items)  
  
add\_word(my\_words\_list)  
  
\# 结巴分词  
  
wordlist = jieba.cut(text, cut\_all=False)  
  
wl = " ".join(wordlist)  
  
\# print(wl)\#输出分词之后的txt  
  
\# 去掉停用词  
  
mywordlist = \[\]  
  
f\_stop = open(stopwords\_path)  
  
try:  
  
f\_stop\_text = f\_stop.read()  
  
f\_stop\_text = unicode(f\_stop\_text, 'utf-8')  
  
\# print f\_stop\_text  
  
finally:  
  
f\_stop.close()  
  
f\_stop\_seg\_list = f\_stop\_text.split('\\n')  
  
for myword in wl.split(" "):  
  
for stopword in f\_stop\_seg\_list:  
  
if (myword.strip() == stopword) or len(myword.strip()) <= 1:  
  
break;  
  
else :  
  
mywordlist.append(myword)  
  
mywordlist = " ".join(mywordlist)  
  
\# stopwords = set(STOPWORDS)  
  
\# stopwords.add("这样")  
  
\# 设置词云  
  
wc = WordCloud(background\_color="black", \# 设置背景颜色  
  
mask=alice\_mask, \#设置背景图片  
  
max\_words=2000, \# 设置最大显示的字数  
  
\# font\_path="fangsong\_GB2312.ttf",  
  
font\_path="华文宋体.ttf",  
  
max\_font\_size=50, \# 设置字体最大值  
  
random\_state=30, \# 设置有多少种随机生成状态，即有多少种配色方案  
  
)  
  
\# wc = WordCloud(background\_color="black", max\_words=2000, mask=alice\_mask,font\_path="华文宋体.ttf",  
  
\# stopwords=stopwords)  
  
myword = wc.generate(mywordlist) \# 生成词云  
  
\# 展示词云图  
  
plt.imshow(myword)  
  
plt.axis("off")  
  
plt.show()  
  
词云图模糊怎么解决?  
  
默认的参数图片分辨率较低，设置scale参数，参数越大，分辨率越高。  
  
词云图重复怎么解决?  
  
默认collocations=True，我们将它设置为False就行了，具体原理，好像是把相邻的两词算作一个词。collocations=False \#对于关键词重复的问题，我们可以使用collocations参数来解决  
  
其他  
  
python展示中文字符串列表，直接输出会展示为unicode编码后的格式。  
  
import json  
  
print json.dumps(f\_stop\_seg\_list, encoding=“UTF-8”, ensure\_ascii=False)