wordcloud词云分析及词频统计绘图

阳光穿透心脏的1/2处 2022-06-07 13:57 254阅读 0赞

#!/usr/bin/env python
    # -*- coding: utf-8 -*-
    # @Date    : 2017-10-18 17:52:25
    # @Author  : awakeljw 
    # @Link    : http://blog.csdn.net/awakeljw/
    # @Version : $Id$
    
    
    from wordcloud import WordCloud
    import jieba
    import PIL
    import matplotlib.pyplot as plt
    import numpy as np
    from collections import Counter
    import matplotlib
    from pylab import mpl
    mpl.rcParams['font.sans-serif'] = ['SentyTang'] # 指定默认字体
    mpl.rcParams['axes.unicode_minus'] = False  
    matplotlib.rc('xtick', labelsize=14)
    matplotlib.rc('ytick', labelsize=14)
    def wordcloudplot(txt):
        path='字体文件'
    #    path=unicode(path, 'utf8').encode('gb18030')
        alice_mask = np.array(PIL.Image.open('图片文件'))
        wordcloud = WordCloud(font_path=path, 
                              background_color="white",   
                              margin=5, width=1800, height=800,mask=alice_mask,max_words=2000,max_font_size=60,random_state=42) 
        wordcloud = wordcloud.generate(txt)
        wordcloud.to_file('输出文件')
        plt.imshow(wordcloud)
        plt.axis("off")
        plt.show()
    
    rem = ['，','、','。','的','和','\u3000','图','串','“','”',' ','与','是','端','在','中','了','\n']    
    def main():
        a=[]
        f=open(r'I:\tensorflow\ciyun\paper.txt','r',encoding='gb18030').read()
        words=list(jieba.cut(f))
        tongji = Counter(words).most_common(20)
    
        d = {key: value for (key, value) in tongji}  
    
        for i in list(d.keys()):
    	    if i in rem:
    		    d.pop(i) 
        print (d)
        label = list(d.keys())
        y = list(d.values())
        idx = np.arange(len(y))
        plt.barh(idx,y)
        plt.yticks(idx+0.4,label) 
        plt.xlabel('出现次数',fontsize = 20,labelpad = 5)
        plt.ylabel('关键词',fontsize= 20,labelpad = 5)
        plt.title('涡流发生器对激波串振荡的控制',fontsize= 25)
        plt.savefig('输出词频图标')
        #plt.show()
        #绘制pie chart on polar axis
        N = len(d)
        theta = np.arange(0.0, 2*np.pi,2*np.pi/N)
        radii = y
        width = np.pi/6
        ax = plt.subplot(111,projection='polar')
        bars = ax.bar(theta, radii, width = width, bottom = 0.0)
        plt.xticks(theta+np.pi/12,label)
        for r, bar in zip(radii, bars):
            bar.set_facecolor(plt.cm.viridis(r / 10.))
            bar.set_alpha(0.5)
    
        plt.savefig('输出pie极坐标图')
        plt.show()
    
        for word in words:
            if len(word)>1:
                a.append(word)
        txt=r' '.join(a)
        wordcloudplot(txt)#输出词云
    
    if __name__=='__main__':
        main()

1.安装wordcloud，jieba  
http://www.lfd.uci.edu/~gohlke/pythonlibs/\#wordcloud下载对应的python版本，在cmd中输入pip install I:/wordcloud-1.3.2-cp35-cp35m-win\_amd64.whl安装即可  
jieba：pip install jieba  
2.修改字体文件  
找到python安装位置：C:\\Anaconda3\\Lib\\site-packages\\matplotlib\\mpl-data\\fonts\\ttf添加自己下载的中文字体，  
删除个人用户下的.matplotlib文件  
3.添加字体文件和图片  
4.更改代码中的文件和图片路径  
5.运行调试  
\#\#\#结果展示  
![这里写图片描述][format_png]  
![这里写图片描述][format_png 1]  
![这里写图片描述][format_png 2]

[format_png]: /images/20220607/ab6f3a751d11457d9558a9a4ae6eb358.png
[format_png 1]: /images/20220607/e7d8ecab9c2546eab7b80e9f1b51beef.png
[format_png 2]: /images/20220607/c894792b9e7e4cc2b5c29c6341532324.png