這篇文章主要為大家展示了“python中如何對(duì)微信好友進(jìn)行數(shù)據(jù)分析”，內(nèi)容簡(jiǎn)而易懂，條理清晰，希望能夠幫助大家解決疑惑，下面讓小編帶領(lǐng)大家一起研究并學(xué)習(xí)一下“python中如何對(duì)微信好友進(jìn)行數(shù)據(jù)分析”這篇文章吧。
效果：
直接上代碼，建三個(gè)空文本文件stopwords.txt，newdit.txt、unionWords.txt，下載字體simhei.ttf或刪除字體要求的代碼，就可以直接運(yùn)行。
重慶分公司
重慶分公司
#wxfriends.py 2018-07-09
import itchat
import sys
import pandas as pd
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']#繪圖時(shí)可以顯示中文
plt.rcParams['axes.unicode_minus']=False#繪圖時(shí)可以顯示中文
import jieba
import jieba.posseg as pseg
from scipy.misc import imread
from wordcloud import WordCloud
from os import path
#解決編碼問題
non_bmp_map = dict.fromkeys(range(0x10000, sys.maxunicode + 1), 0xfffd)
#獲取好友信息
def getFriends():
friends = itchat.get_friends(update=True)[0:]
flists = []
for i in friends:
fdict={}
fdict['NickName']=i['NickName'].translate(non_bmp_map)
if i['Sex'] == 1:
fdict['Sex']='男'
elif i['Sex'] == 2:
fdict['Sex']='女'
else:
fdict['Sex']='雌雄同體'
if i['Province'] == '':
fdict['Province'] ='未知'
else:
fdict['Province']=i['Province']
fdict['City']=i['City']
fdict['Signature']=i['Signature']
flists.append(fdict)
return flists
#將好友信息保存成CSV
def saveCSV(lists):
df = pd.DataFrame(lists)
try:
df.to_csv("wxfriends.csv",index = True,encoding='gb18030')
except Exception as ret:
print(ret)
return df
#統(tǒng)計(jì)性別、省份字段
def anysys(df):
df_sex = pd.DataFrame(df['Sex'].value_counts())
df_province = pd.DataFrame(df['Province'].value_counts()[:15])
df_signature = pd.DataFrame(df['Signature'])
return df_sex,df_province,df_signature
#繪制柱狀圖，并保存
def draw_chart(df_list,x_feature):
try:
x = list(df_list.index)
ylist = df_list.values
y = []
for i in ylist :
for j in i:
y.append(j)
plt.bar(x,y,label=x_feature)
plt.legend()
plt.savefig(x_feature)
plt.close()
except:
print("繪圖失敗")
#解析取個(gè)性簽名構(gòu)成列表
def getSignList(signature):
sig_list = []
for i in signature.values:
for j in i:
sig_list.append(j.translate(non_bmp_map))
return sig_list
#分詞處理，并根據(jù)需要填寫停用詞、自定義詞、合并詞替換
def segmentWords(txtlist):
stop_words = set(line.strip() for line in open('stopwords.txt', encoding='utf-8'))
newslist = []
#新增自定義詞
jieba.load_userdict("newdit.txt")
for subject in txtlist:
if subject.isspace():
continue
word_list = pseg.cut(subject)
for word, flag in word_list:
if not word in stop_words and flag == 'n' or flag == 'eng' and word !='span' and word !='class':
newslist.append(word)
#合并指定的相似詞
for line in open('unionWords.txt', encoding='utf-8'):
newline = line.encode('utf-8').decode('utf-8-sig') #解決\ufeff問題
unionlist = newline.split("*")
for j in range(1,len(unionlist)):
#wordDict[unionlist[0]] += wordDict.pop(unionlist[j],0)
for index,value in enumerate(newslist):
if value == unionlist[j]:
newslist[index] = unionlist[0]
return newslist
#高頻詞統(tǒng)計(jì)
def countWords(newslist):
wordDict = {}
for item in newslist:
wordDict[item] = wordDict.get(item,0) + 1
itemList = list(wordDict.items())
itemList.sort(key=lambda x:x[1],reverse=True)
for i in range(100):
word, count = itemList[i]
print("{}:{}".format(word,count))
#繪制詞云
def drawPlant(newslist):
d = path.dirname(__file__)
mask_image = imread(path.join(d, "timg.png"))
content = ' '.join(newslist)
wordcloud = WordCloud(font_path='simhei.ttf', background_color="white",width=1300,height=620, max_words=200).generate(content) #mask=mask_image,
# Display the generated image:
plt.imshow(wordcloud)
plt.axis("off")
wordcloud.to_file('wordcloud.jpg')
plt.show()
def main():
#登陸微信
itchat.auto_login() # 登陸后不需要掃碼 hotReload=True
flists = getFriends()
fdf = saveCSV(flists)
df_sex,df_province,df_signature = anysys(fdf)
draw_chart(df_sex,"性別")
draw_chart(df_province,"省份")
wordList = segmentWords(getSignList(df_signature))
countWords(wordList)
drawPlant(wordList)
main()以上是“python中如何對(duì)微信好友進(jìn)行數(shù)據(jù)分析”這篇文章的所有內(nèi)容，感謝各位的閱讀！相信大家都有了一定的了解，希望分享的內(nèi)容對(duì)大家有所幫助，如果還想學(xué)習(xí)更多知識(shí)，歡迎關(guān)注創(chuàng)新互聯(lián)行業(yè)資訊頻道！
