使用wxBot和Python做微信好友数据分析

喜欢ヅ旅行 2022-05-01 12:06 277阅读 0赞

为了拿pandas练手，做了这个东西，分享一下给大家，有需要的可以参考，不喜勿喷

1.使用[wxBot][]获取到微信好友列表

2.下载好wxBot后根据文档提示运行起来，登录微信

3.在当前目录下 找到 temp/contact\_list.json

4.在 [json-csv网站][json-csv] 把Json文件转换成CSV文件

# -*- coding: utf-8 -*-
    #导入库
    import re
    import pandas as pd
    import matplotlib.pyplot as plt
    
    import jieba.analyse
    from snownlp import SnowNLP
    from wordcloud import WordCloud
    
    def readFile(filePath):
      return pd.read_csv(filePath)
     
    if __name__ == "__main__":
      #Mac下设置Plot的中文显示，如果不设置，中文就显示成方块
      plt.rcParams['font.sans-serif']=['SimHei']
      df = readFile('./contact_list.csv')
    
      #处理空数据设置成默认数据
      df.Province= df.Province.fillna('未知')
      df.City= df.City.fillna('未知')
    
      showAreaBar(df,'Province','按省分布',5)
      showAreaBar(df,'City','按市分布',3)
    
      showGenderPie(df)
    
      analyseSignature(df['Signature'])
    复制代码

--------------------

展示地区分布的柱状图，按City分布的截图就不放上去了

def showAreaBar(datas, area, title, limit):
      plt.figure(figsize=(8,10))
      area_group = datas['PYQuanPin'].groupby(datas[area])
      name_list = []
      num_list = []
      less = 0
      lessLimit = limit
      for name, group in area_group:
        if group.size < lessLimit:
          less += group.size
        else:
          name_list.append(name)
          num_list.append(group.size)
    
      name_list.append('少于{}人'.format(lessLimit))
      num_list.append(less)
    
      # plt.subplot(221)
      plt.title(title)
      plt.barh(range(len(num_list)), num_list,color='rgb',tick_label=name_list) 
      #必须要先Save
      plt.savefig(area + ".jpg")
      plt.show()
    
      plt.title('我的微信好友地区分布')
      plt.pie(x=num_list, labels=name_list,autopct='%3.1f %%',
            shadow=False, labeldistance=1.2, startangle = 90,pctdistance = 0.6
            )
      plt.savefig(area + '_Pie.jpg')
      plt.show()
    复制代码

--------------------

好友中性别比例的饼状图

def showGenderPie(datas,):
      # print (df[df.Sex == 2])
      males = datas[datas.Sex == 1]
      females = datas[datas.Sex == 2]
      unknowns = datas[datas.Sex == 0]
    
      labels = ['男', '女', '未知']
      fracs = [males.size, females.size,unknowns.size]
      explode = [0, 0,0.1] # 0.1 凸出这部分，
    
      plt.title('我的微信好友性别比例')
      plt.pie(x=fracs, labels=labels,explode=explode,autopct='%3.1f %%',
            shadow=False, labeldistance=1.1, startangle = 90,pctdistance = 0.6
            )
      plt.savefig('gender.jpg')
      plt.show()
    复制代码

--------------------

微信好友签名信息情感分析

def analyseSignature(signatureList):
        signatures = ''
        emotions = []
        for signature in signatureList:
            if(isinstance(signature,str) and signature != None):
                signature = signature.strip().replace('span', '').replace('class', '').replace('emoji', '')
                signature = re.sub(r'1f(\d.+)','',signature)
                if(len(signature)>0):
                    nlp = SnowNLP(signature)
                    emotions.append(nlp.sentiments)
                    signatures += ' '.join(jieba.analyse.extract_tags(signature,5))
        with open('signatures.txt','wt',encoding='utf-8') as file:
             file.write(signatures)
    
        # Sinature WordCloud
        # back_coloring = np.array(Image.open('flower.jpg'))
        font_path="/System/Library/fonts/PingFang.ttc"
        wordcloud = WordCloud(
            font_path=font_path,
            background_color="white",
            max_words=1200,
            # mask=back_coloring, 
            max_font_size=75,
            random_state=45,
            width=960, 
            height=720, 
            margin=15
        )
        wordcloud.generate(signatures)
        plt.imshow(wordcloud)
        plt.axis("off")
        plt.show()
        wordcloud.to_file('signatures.jpg')
    
        # Signature Emotional Judgment
        count_good = len(list(filter(lambda x:x>0.66,emotions)))
        count_normal = len(list(filter(lambda x:x>=0.33 and x<=0.66,emotions)))
        count_bad = len(list(filter(lambda x:x<0.33,emotions)))
        labels = [u'负面消极',u'中性',u'正面积极']
        values = (count_bad,count_normal,count_good)
        plt.rcParams['font.sans-serif'] = ['simHei'] 
        plt.rcParams['axes.unicode_minus'] = False
        plt.xlabel(u'情感判断')
        plt.ylabel(u'频数')
        plt.xticks(range(3),labels)
        plt.legend(loc='upper right',)
        plt.bar(range(3), values, color = 'rgb')
        plt.title(u'微信好友签名信息情感分析')
        plt.show()
    复制代码

转载于:https://juejin.im/post/5cdccf135188256964773d99

[wxBot]: https://link.juejin.im?target=https%3A%2F%2Fgithub.com%2Fliuwons%2FwxBot
[json-csv]: https://link.juejin.im?target=https%3A%2F%2Fjson-csv.com%2F