电子商务网站用户行为分析
# -*- coding: utf-8 -*- # 代码11-1 import os import pandas as pd # 修改工作路径到指定文件夹 #os.chdir("D:/chapter11/demo") os.chdir("D:\\大三下\\大数据实验课\\data\\Unit11") # 第一种连接方式 # from sqlalchemy import create_engine # engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8') # sql = pd.read_sql('all_gzdata', engine, chunksize = 10000) # 第二种连接方式 import pymysql as pm
con = pm.connect(host='localhost',user='root',password='123456',database='test',charset='utf8') data = pd.read_sql('select * from all_gzdata',con=con) con.close() #关闭连接 # 保存读取的数据 data.to_csv("D:\\大三下\\大数据实验课\\data\\Unit11\\all_gzdata.csv", index=False, encoding='utf-8')
网页类型设计
# 代码11-2 网页类型设计 import pandas as pd from sqlalchemy import create_engine engine = create_engine('mysql+pymysql://root:[email protected]:3306/test?charset=utf8') sql = pd.read_sql('all_gzdata', engine, chunksize = 10000) # 分析网页类型 counts = [i['fullURLId'].value_counts() for i in sql] #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(by='num', ascending=False, inplace=True) # 降序排列 counts_['ratio'] = counts_.iloc[:,0] / counts_.iloc[:,0].sum() print(counts_)
# 代码11-3 知识类型内部统计 # 因为只有107001一类,但是可以继续细分成三类:知识内容页、知识列表页、知识首页 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/.+?/')]= '知识首页' j['type'][j['fullURL'].str.contains('info/.+?/.+?')]= '知识列表页' j['type'][j['fullURL'].str.contains('/\d+?_*\d+?\.html')]= '知识内容页' return j['type'].value_counts() # 注意:获取一次sql对象就需要重新访问一下数据库(!!!) 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= '107类型' res107.rename(columns={'type':'num'}, inplace=True) res107['比例'] = res107['num'] / res107['num'].sum() res107.reset_index(inplace = True) print(res107)
# 代码11-4 统计带“?”的数据 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 # 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) 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))
# 代码11-5 统计199类型中的具体类型占比 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_)
# 代码11-6 统计无目的浏览用户中各个类型占比 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11-7 统计用户浏览网页次数的情况 # 统计点击次数 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)
# 代码11-8 分析浏览一次的用户行为 # 初始化数据库连接: engine = create_engine('mysql+pymysql://root:123456@localhost:3306/test?charset=utf8') sql = pd.read_sql('all_gzdata', engine, chunksize=1024 * 5) # 分块统计各个IP的点击次数 result = [i['realIP'].value_counts() for i in sql] click_count = pd.concat(result).groupby(level=0).sum() click_count = click_count.reset_index() click_count.columns = ['realIP', 'times'] # 筛选出来点击一次的数据 click_one_data = click_count[click_count['times'] == 1] # 这里只能再次读取数据 因为sql是一个生成器类型,所以在使用过一次以后,就不能继续使用了。必须要重新执行一次读取。 sql = pd.read_sql('all_gzdata', engine, chunksize=1024 * 5) # 取出这三列数据 data = [i[['fullURLId', 'fullURL', 'realIP']] for i in sql] data = pd.concat(data) # 和并数据 我以click_one_data为基准 按照realIP合并过来,目的方便查看点击一次的网页和realIP merge_data = pd.merge(click_one_data, data, on='realIP', how='left') # 点击一次的数据统计 写入数据库 以方便读取 校准无误 写入后就可以注释掉此句代码 #erge_data.to_sql('click_one_count', engine, if_exists='append') print(merge_data) # 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)
# 代码11-9 统计单用户浏览次数为一次的网页 # 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 # 网页类型ID统计 fullURLId_count = merge_data['fullURLId'].value_counts() fullURLId_count = fullURLId_count.reset_index() fullURLId_count.columns = ['fullURLId', 'count'] fullURLId_count['percent'] = fullURLId_count['count'] / fullURLId_count['count'].sum() * 100 print('*****' * 10) print(fullURLId_count) # 用户点击一次 浏览的网页统计 fullURL_count = merge_data['fullURL'].value_counts() fullURL_count = fullURL_count.reset_index() fullURL_count.columns = ['fullURL', 'count'] fullURL_count['percent'] = fullURL_count['count'] / fullURL_count['count'].sum() * 100 print('*****' * 10) print(fullURL_count)
# 代码11-10 删除不符合规则的网页 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:\\大三下\\大数据实验课\\data\\Unit1\\FileRecv") # 读取数据 con = pm.connect(host='localhost',user='root',password='123456',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)
# 代码11-11 还原翻译网址 # 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]]print(info3) len(info3)
# 代码11-12 筛选浏览次数不满两次的用户 # 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})print(IP_count) # 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)
# 代码11-13 划分数据集 # 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)标签:count,index,电子商务,网站,IP,用户,pd,sql,fullURL From: https://www.cnblogs.com/panlongcong/p/17371877.html