词云图——图片

#!/usr/bin/Python
# -*- coding: utf-8 -*-
from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import jieba
from wordcloud import WordCloud, STOPWORDS


###当前文件路径
d = path.dirname(__file__)

# Read the whole text.
file = open("D:/jupyter/临时/keywordlist1.csv", 'r', encoding='utf-8').read()
##进行分词
#刚开始是分完词放进txt再打开却总是显示不出中文很奇怪
default_mode =jieba.cut(file)
text = " ".join(default_mode)
alice_mask = np.array(Image.open("13717038-ce84e01daf1319ca.png"))
stopwords = set(STOPWORDS)
stopwords.add("said")
wc = WordCloud(  
    #设置字体,不指定就会出现乱码,这个字体文件需要下载
    font_path='SimHei.ttf',  
    background_color="white",   
    max_words=2000,   
    mask=alice_mask,  
    stopwords=stopwords)  
# generate word cloud
wc.generate(text)

# store to file
wc.to_file(path.join(d, "yinsi.jpg"))

# 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()

 

 

 

 

posted on 2022-03-25 20:05  cookie的笔记簿  阅读(73)  评论(0编辑  收藏  举报