Python数据挖掘05--词云(wordcloud)找出老九门中热门词语

注意
window系统安装wordcloud模块时可能会出现需要安装C++等错误，此时使用https://www.lfd.uci.edu/~gohlke/pythonlibs/#scipy网站的whl自己进行安装将不会再报错

---

资料中所用到老九门文件和图片，点击下载

import wordcloud as wc  # 词云模块
import matplotlib.pylab as plb
import pandas as pda
import jieba  # jieba模块 分解词语
from PIL import Image
from numpy import array


path = "C:/Users/Administrator/Desktop/老九门.txt"
data = open(path, "r", encoding="gbk").read()  # 读取txt小说文件 
cutdata = jieba.cut(data)  # 将文本分割成词语

alldata = "" 
for i in cutdata:  # 词语进行循环拼接
    alldata = alldata + " " + str(i)


font = r"C:\WINDOWS\Fonts\simhei.ttf"  
# 打开图片
cat = Image.open("C:/Users/Administrator/Desktop/cat.png")
catarray = array(cat)  # 将读取的图片转化成数组

# 使用WordCloud方法
oldwc = wc.WordCloud(mask=catarray, collocations=False,  # mask展示形状，background_color背景颜色
                     font_path=font, background_color="white"
                     ).generate(data)  
plb.imshow(oldwc)
plb.show()

最终展示结果