首页 > 其他分享 >电子商务网站用户行为分析及服务推荐

电子商务网站用户行为分析及服务推荐

时间:2023-04-13 16:59:55浏览次数:32  
标签:count index 电子商务 loc 网站 IP tr 用户 pd

 

import pandas as pd
from sqlalchemy import create_engine

engine = create_engine('mysql+pymysql://root:102011@localhost/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)

counts = [ i['fullURLId'].value_counts() for i in sql] #按次10000存取,逐块统计
counts = counts.copy()
counts = pd.concat(counts).groupby(level=0).sum() #合并统计结果,把相同的统计项合并(即按index分组并求和)
counts = counts.reset_index() #重新设置index,将原来的index作为counts的一列。
counts.columns = ['index', 'num'] #重新设置列名,主要是第二列,默认为0
counts['type'] = counts['index'].str.extract('(\d{3})') #提取前三个数字作为类别id
counts_ = counts[['type', 'num']].groupby('type').sum() #按类别合并
counts_.sort_values('num', ascending = False) #降序排列
counts_['percentage'] = (counts_['num']/counts_['num'].sum())*100
print(counts_)

 

def count107(i): #自定义统计函数
  j = i[['fullURL']][i['fullURLId'].str.contains('107')].copy() #找出类别包含107的网址
  j['type'] = None #添加空列
  j['type'][j['fullURL'].str.contains('info/.+?/')] = u'知识首页' #info以/结尾
  j['type'][j['fullURL'].str.contains('info/.+?/.+?')] = u'知识列表页'
  j['type'][j['fullURL'].str.contains('/\d+?_*\d+?\.html')] = u'知识内容页'
  return j['type'].value_counts()

engine = create_engine('mysql+pymysql://root:102011@localhost/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)

counts2 = [count107(i) for i in sql] #逐块统计
counts2 = pd.concat(counts2).groupby(level=0).sum() #合并统计结果
print(counts2)
#计算各个部分的占比
res107 = pd.DataFrame(counts2)
# res107.reset_index(inplace=True)
res107.index.name= u'107类型'
res107.rename(columns={'type':'num'},inplace=True)
res107[u'比例'] = (res107['num']/res107['num'].sum())*100
res107.reset_index(inplace = True)
print(res107)

 

 

def countquestion(i):  # 自定义统计函数
    j = i[['fullURLId']][i['fullURL'].str.contains('\?')].copy()  # 找出类别包含107的网址
    return j

#engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)

counts3 = [countquestion(i)['fullURLId'].value_counts() for i in sql]
counts3 = pd.concat(counts3).groupby(level=0).sum()
print(counts3)

# 求各个类型的占比并保存数据
df1 =  pd.DataFrame(counts3)
df1['perc'] = df1['fullURLId']/df1['fullURLId'].sum()*100
df1.sort_values(by='fullURLId',ascending=False,inplace=True)
print(df1.round(4))

 

def page199(i):  # 自定义统计函数
  j = i[['fullURL', 'pageTitle']][(i['fullURLId'].str.contains('199')) &
                                  (i['fullURL'].str.contains('\?'))]
  j['pageTitle'].fillna('空', inplace=True)
  j['type'] = '其他'  # 添加空列
  j['type'][j['pageTitle'].str.contains('法律快车-律师助手')] = '法律快车-律师助手'
  j['type'][j['pageTitle'].str.contains('咨询发布成功')] = '咨询发布成功'
  j['type'][j['pageTitle'].str.contains('免费发布法律咨询')] = '免费发布法律咨询'
  j['type'][j['pageTitle'].str.contains('法律快搜')] = '快搜'
  j['type'][j['pageTitle'].str.contains('法律快车法律经验')] = '法律快车法律经验'
  j['type'][j['pageTitle'].str.contains('法律快车法律咨询')] = '法律快车法律咨询'
  j['type'][(j['pageTitle'].str.contains('_法律快车')) |
            (j['pageTitle'].str.contains('-法律快车'))] = '法律快车'
  j['type'][j['pageTitle'].str.contains('空')] = '空'

  return j


# 注意:获取一次sql对象就需要重新访问一下数据库
# engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize=10000)  # 分块读取数据库信息
# sql = pd.read_sql_query('select * from all_gzdata limit 10000', con=engine)

counts4 = [page199(i) for i in sql]  # 逐块统计
counts4 = pd.concat(counts4)
d1 = counts4['type'].value_counts()
print(d1)
d2 = counts4[counts4['type'] == '其他']
print(d2)
# 求各个部分的占比并保存数据
df1_ = pd.DataFrame(d1)
df1_['perc'] = df1_['type'] / df1_['type'].sum() * 100
df1_.sort_values(by='type', ascending=False, inplace=True)
print(df1_)

 

 

def xiaguang(i):  # 自定义统计函数
  j = i.loc[(i['fullURL'].str.contains('\.html')) == False,
  ['fullURL', 'fullURLId', 'pageTitle']]
  return j

# 注意获取一次sql对象就需要重新访问一下数据库
engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize=10000)  # 分块读取数据库信息

counts5 = [xiaguang(i) for i in sql]
counts5 = pd.concat(counts5)

xg1 = counts5['fullURLId'].value_counts()
print(xg1)
# 求各个部分的占比
xg_ = pd.DataFrame(xg1)
xg_.reset_index(inplace=True)
xg_.columns = ['index', 'num']
xg_['perc'] = xg_['num'] / xg_['num'].sum() * 100
xg_.sort_values(by='num', ascending=False, inplace=True)

xg_['type'] = xg_['index'].str.extract('(\d{3})')  # 提取前三个数字作为类别id

xgs_ = xg_[['type', 'num']].groupby('type').sum()  # 按类别合并
xgs_.sort_values(by='num', ascending=False, inplace=True)  # 降序排列
xgs_['percentage'] = xgs_['num'] / xgs_['num'].sum() * 100

print(xgs_.round(4))

 

代码七:统计用户浏览网页次数情况

engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)# 分块读取数据库信息

counts1 = [i['realIP'].value_counts() for i in sql] # 分块统计各个IP的出现次数
counts1 = pd.concat(counts1).groupby(level=0).sum() # 合并统计结果,level=0表示按照index分组
print(counts1)

counts1_ = pd.DataFrame(counts1)
counts1_
counts1['realIP'] = counts1.index.tolist()

counts1_[1]=1  # 添加1列全为1
hit_count = counts1_.groupby('realIP').sum()  # 统计各个“不同点击次数”分别出现的次数
# 也可以使用counts1_['realIP'].value_counts()功能
hit_count.columns=['用户数']
hit_count.index.name = '点击次数'

# 统计1~7次、7次以上的用户人数
hit_count.sort_index(inplace = True)
hit_count_7 = hit_count.iloc[:7,:]
time = hit_count.iloc[7:,0].sum()  # 统计点击次数7次以上的用户数
hit_count_7 = hit_count_7.append([{'用户数':time}], ignore_index=True)
hit_count_7.index = ['1','2','3','4','5','6','7','7次以上']
hit_count_7['用户比例'] = hit_count_7['用户数'] / hit_count_7['用户数'].sum()
print(hit_count_7)

 

 

engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8')
all_gzdata = pd.read_sql_table('all_gzdata', con = engine)  # 读取all_gzdata数据

#对realIP进行统计
# 提取浏览1次网页的数据
real_count = pd.DataFrame(all_gzdata.groupby("realIP")["realIP"].count())
real_count.columns = ["count"]
real_count["realIP"] = real_count.index.tolist()
user_one = real_count[(real_count["count"] == 1)]  # 提取只登录一次的用户
# 通过realIP与原始数据合并
real_one = pd.merge(user_one, all_gzdata,right_on='realIP',left_index=True,how='left')

# 统计浏览一次的网页类型
URL_count = pd.DataFrame(real_one.groupby("fullURLId")["fullURLId"].count())
URL_count.columns = ["count"]
URL_count.sort_values(by='count', ascending=False, inplace=True)  # 降序排列
# 统计排名前4和其他的网页类型
URL_count_4 = URL_count.iloc[:4,:]
time = hit_count.iloc[4:,0].sum()  # 统计其他的
URLindex = URL_count_4.index.values
URL_count_4 = URL_count_4.append([{'count':time}], ignore_index=True)
URL_count_4.index = [URLindex[0], URLindex[1], URLindex[2], URLindex[3],
                     '其他']
URL_count_4['比例'] = URL_count_4['count'] / URL_count_4['count'].sum()
print(URL_count_4)
   

 

# 在浏览1次的前提下, 得到的网页被浏览的总次数
fullURL_count = pd.DataFrame(real_one.groupby("fullURL")["fullURL"].count())
fullURL_count.columns = ["count"]
fullURL_count["fullURL"] = fullURL_count.index.tolist()
fullURL_count.sort_values(by='count', ascending=False, inplace=True)  # 降序排列
print(fullURL_count.head(10))

 

import os
import re
import pandas as pd
import pymysql as pm
from random import sample

# 修改工作路径到指定文件夹
os.chdir("D:/python123")

# 读取数据
con = pm.connect(host='localhost',user='root',password='102011',database='test',charset='utf8')
data = pd.read_sql('select * from all_gzdata',con=con)
con.close()           #关闭连接

# 取出107类型数据
index107 = [re.search('107',str(i))!=None for i in data.loc[:,'fullURLId']]
data_107 = data.loc[index107,:]

# 在107类型中筛选出婚姻类数据
index = [re.search('hunyin',str(i))!=None for i in data_107.loc[:,'fullURL']]
data_hunyin = data_107.loc[index,:]

# 提取所需字段(realIP、fullURL)
info = data_hunyin.loc[:,['realIP','fullURL']]

# 去除网址中“?”及其后面内容
da = [re.sub('\?.*','',str(i)) for i in info.loc[:,'fullURL']]
info.loc[:,'fullURL'] = da     # 将info中‘fullURL’那列换成da
# 去除无html网址
index = [re.search('\.html',str(i))!=None for i in info.loc[:,'fullURL']]
index.count(True)   # True 或者 1 , False 或者 0
info1 = info.loc[index,:]
print(info1.head())

 

 

 

# 找出翻页和非翻页网址
index = [re.search('/\d+_\d+\.html',i)!=None for i in info1.loc[:,'fullURL']]
index1 = [i==False for i in index]
info1_1 = info1.loc[index,:]   # 带翻页网址
info1_2 = info1.loc[index1,:]  # 无翻页网址
# 将翻页网址还原
da = [re.sub('_\d+\.html','.html',str(i)) for i in info1_1.loc[:,'fullURL']]
info1_1.loc[:,'fullURL'] = da
# 翻页与非翻页网址合并
frames = [info1_1,info1_2]
info2 = pd.concat(frames)
# 或者
info2 = pd.concat([info1_1,info1_2],axis = 0)   # 默认为0,即行合并
# 去重(realIP和fullURL两列相同)
info3 = info2.drop_duplicates()
# 将IP转换成字符型数据
info3.iloc[:,0] = [str(index) for index in info3.iloc[:,0]]
info3.iloc[:,1] = [str(index) for index in info3.iloc[:,1]]
len(info3)

 

# 筛选满足一定浏览次数的IP
IP_count = info3['realIP'].value_counts()
# 找出IP集合
IP = list(IP_count.index)
count = list(IP_count.values)
# 统计每个IP的浏览次数,并存放进IP_count数据框中,第一列为IP,第二列为浏览次数
IP_count = pd.DataFrame({'IP':IP,'count':count})
# 3.3筛选出浏览网址在n次以上的IP集合
n = 2
index = IP_count.loc[:,'count']>n
IP_index = IP_count.loc[index,'IP']
print(IP_index.head())

 

# 划分IP集合为训练集和测试集
index_tr = sample(range(0,len(IP_index)),int(len(IP_index)*0.8))  # 或者np.random.sample
index_te = [i for i in range(0,len(IP_index)) if i not in index_tr]
IP_tr = IP_index[index_tr]
IP_te = IP_index[index_te]
# 将对应数据集划分为训练集和测试集
index_tr = [i in list(IP_tr) for i in info3.loc[:,'realIP']]
index_te = [i in list(IP_te) for i in info3.loc[:,'realIP']]
data_tr = info3.loc[index_tr,:]
data_te = info3.loc[index_te,:]
print(len(data_tr))
IP_tr = data_tr.iloc[:,0]  # 训练集IP
url_tr = data_tr.iloc[:,1]  # 训练集网址
IP_tr = list(set(IP_tr))  # 去重处理
url_tr = list(set(url_tr))  # 去重处理
len(url_tr)

 

# 利用训练集数据构建模型
UI_matrix_tr = pd.DataFrame(0,index=IP_tr,columns=url_tr)
# 求用户-物品矩阵
for i in data_tr.index:
UI_matrix_tr.loc[data_tr.loc[i,'realIP'],data_tr.loc[i,'fullURL']] = 1
# sum(UI_matrix_tr.sum(axis=1))

# 求物品相似度矩阵(因计算量较大,需要耗费的时间较久)
Item_matrix_tr = pd.DataFrame(0,index=url_tr,columns=url_tr)
for i in Item_matrix_tr.index:
for j in Item_matrix_tr.index:
a = sum(UI_matrix_tr.loc[:,[i,j]].sum(axis=1)==2)
b = sum(UI_matrix_tr.loc[:,[i,j]].sum(axis=1)!=0)
Item_matrix_tr.loc[i,j] = a/b

# 将物品相似度矩阵对角线处理为零
for i in Item_matrix_tr.index:
Item_matrix_tr.loc[i,i]=0

#利用测试集数据对模型评价
IP_te = data_te.iloc[:,0]
url_te = data_te.iloc[:,1]
IP_te = list(set(IP_te))
url_te = list(set(url_te))

# 测试集数据用户物品矩阵
UI_matrix_te = pd.DataFrame(0,index=IP_te,columns=url_te)
for i in data_te.index:
UI_matrix_te.loc[data_te.loc[i,'realIP'],data_te.loc[i,'fullURL']] = 1

# 对测试集IP进行推荐
Res = pd.DataFrame('NaN',index=data_te.index,columns=['IP','已浏览网址','推荐网址','T/F'])
Res.loc[:,'IP']=list(data_te.iloc[:,0])
Res.loc[:,'已浏览网址']=list(data_te.iloc[:,1])

# 开始推荐
for i in Res.index:
if Res.loc[i,'已浏览网址'] in list(Item_matrix_tr.index):
Res.loc[i,'推荐网址'] = Item_matrix_tr.loc[Res.loc[i,'已浏览网址'],:].idxmax()
if Res.loc[i,'推荐网址'] in url_te:
Res.loc[i,'T/F']=UI_matrix_te.loc[Res.loc[i,'IP'],Res.loc[i,'推荐网址']]==1
else:
Res.loc[i,'T/F'] = False

# 保存推荐结果
Res.to_csv('D:/python123/Res.csv',index=False,encoding='utf8')

 

 

# 读取保存的推荐结果
Res = pd.read_csv('D:/python123/Res.csv',keep_default_na=False, encoding='utf8')

# 计算推荐准确率
Pre = round(sum(Res.loc[:,'T/F']=='True') / (len(Res.index)-sum(Res.loc[:,'T/F']=='NaN')), 3)
print('推荐准确率:',Pre)

# 计算推荐召回率
Rec = round(sum(Res.loc[:,'T/F']=='True') / (sum(Res.loc[:,'T/F']=='True')+sum(Res.loc[:,'T/F']=='NaN')), 3)
print('推荐召回率:',Rec)

# 计算F1指标
F1 = round(2*Pre*Rec/(Pre+Rec),3)
print('推荐F1指标:',F1)

 

 

 

 

 

 

 



 

标签:count,index,电子商务,loc,网站,IP,tr,用户,pd
From: https://www.cnblogs.com/021128yc/p/17315380.html

相关文章

  • 电子商务网站行为分析及服务推荐
    #-*-coding:utf-8-*-#代码11-1importosimportpandasaspd##修改工作路径到指定文件夹#os.chdir("./")##第一种连接方式fromsqlalchemyimportcreate_engineengine=create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8',echo=T......
  • 【防止恶意用户注册】-- 手机在网状态 API 的防欺诈应用解析
     简介手机在网状态API支持传入手机号码,查询手机号在网状态,返回在网、在网不可用、不在网(销号/未启用/停机)等多种状态,查询手机号在网状态之后,可以根据具体的业务需求来进行不同的处理。 本文主要介绍手机在网状态API的工作原理、以及手机号码注册验证、金融服务、数据......
  • Docker MySql8 创建、删除、授权用户
    1、登录MySql8#登录数据库dockerexec-itmysql8mysql-uroot-proot123456#切换数据库实例usemysql;2、用户操作2.1、查看用户selecthost,user,authentication_string,pluginfromuser;2.2、创建本地用户#创建一个用户名为admin,密码为admin123456的......
  • 反欺诈(羊毛盾)API 实现用户行为分析的思路分析
    简介反欺诈(羊毛盾)API是一种用于识别和防范各种欺诈行为的技术解决方案。它可集成到各种应用程序和平台中,通过手机号码、手机IP进行异常检测,达到防范恶意注册、虚假评论、虚假交易等欺诈行为的目的。本文主要介绍反欺诈(羊毛盾)API的工作原理、以及在用户行为分析技术、地理位置......
  • ubuntu使用记录(5)ubuntu20.04 切换root用户
    ubuntu20.04使用root用户登录系统以普通用户登录系统,创建root用户的密码在终端输入命令:sudopasswdroot先输入当前普通用户(如用户coco)的密码,用于提权。......
  • JOB实现定时收集特定用户的统计信息
    --创建存储过程createprocedureanalyze_table_elan4is--analyze_table_elan4存储过程名,自定义begindbms_stats.gather_schema_stats(ownname=>'ELAN',--修改要收集统计信息的用户options=>'GATHER',estimate_percent=>dbms......
  • 微信小程序获取用户位置 getLocation
    首先在app.config.json中配置exportdefaultdefineAppConfig({pages:[],permission:{"scope.userLocation":{"desc":"你的位置信息将用于小程序位置接口的效果展示"}},})方法调用:constgetLocation=()=>{Taro.getLocation({......
  • h5使用高德获取用户当前位置信息
    在index.html文件中引入高德js文件:key需要从高德获取获取key<scripttype="text/javascript"src="https://webapi.amap.com/maps?v=1.4.15&key=f77da011880c2d55aeccba6446b85c78"></script>js文件我将方法写入了单独的js文件:locationService.jsimportAMapfr......
  • 力扣1127(MySQL)-用户购买平台(困难)
    题目:支出表:Spending这张表记录了用户在一个在线购物网站的支出历史,该在线购物平台同时拥有桌面端(‘desktop’)和手机端(‘mobile’)的应用程序。这张表的主键是(user_id,spend_date,platform)。平台列platform是一种ENUM,类型为(‘desktop’,‘mobile’)。问题写一段SQL......
  • 在dockerfile中使用非root用户
    16、在dockerfile中使用非root用户前言:当在运行容器时,默认都是以root的账号进行启动的,但这个root账号和宿主机的root账号的权限是不一样的,会受到capabilities的限制。那如果是非特权的容器,使用容器的root账号启动是否安全的呢。(1)启动一个centos-test的容器#dockerrun......