parent
685ee40a1e
commit
d24bfd85b9
@ -0,0 +1,36 @@
|
||||
import jieba
|
||||
from PIL import Image
|
||||
from wordcloud import WordCloud
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
#导入文本内容,删除换行符和空格
|
||||
text = open(r"弹幕.txt",encoding='utf-8').read()
|
||||
text = text.replace('\n',"").replace("\u3000","")
|
||||
|
||||
#将其分成一个个词
|
||||
text_cut = jieba.lcut(text)
|
||||
|
||||
#将分好的词用某个符号分隔开连成字符串
|
||||
text_cut = [word for word in text_cut if len(word) > 1]
|
||||
text_cut = ' '.join(text_cut)
|
||||
|
||||
#停用词
|
||||
#stop_words = set(["的","了","是","和",'这','吧','不','看','啊','我','就','也','那','我','还','吗','你','都'])
|
||||
#读取背景图
|
||||
background_image = np.array(Image.open('trophy.png'))
|
||||
|
||||
word_cloud = WordCloud(font_path="simsun.ttc",
|
||||
background_color = "white",
|
||||
mask=background_image,
|
||||
collocations = False,#防止词云图出现重复单词
|
||||
#stopwords=stop_words,
|
||||
max_font_size=100,
|
||||
max_words=200,
|
||||
min_font_size=10,
|
||||
colormap='viridis'
|
||||
)
|
||||
|
||||
word_cloud.generate(text_cut)
|
||||
image = word_cloud.to_image()
|
||||
image.show()
|
||||
word_cloud.to_file("词云图.png")
|
Loading…
Reference in new issue