python6

第一部分

代码1

import pandas as pdfrom sqlalchemy import create_engineengine = create_engine('mysql+pymysql://root:102011@localhost/test?charset=utf8')sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)'''用create_engine建立连接，连接地址的意思依次为“数据库格式（mysql）+程序名（pymysql）+账号密码@地址端口/数据库名（test）”，最后指定编码为utf8；all_gzdata是表名，engine是连接数据的引擎，chunksize指定每次读取1万条记录。这时候sql是一个容器，未真正读取数据。'''

代码2

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0counts['type'] = counts['index'].str.extract('(\d{3})') #提取前三个数字作为类别idcounts_ = 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())*100print(counts_)

type  numpercentage101  411665 49.15696510217357  2.0726011031715  0.2047881063957  0.472506107  182900 21.840110199  201426 24.05230230118430  2.200728

代码3

#统计107类别的情况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'  retu 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())*100res107.reset_index(inplace = True)print(res107)

知识内容页164243知识列表页  9656知识首页9001Name: type, dtype: int64107类型 num 比例0  知识内容页  164243 89.7993441  知识列表页9656  5.2793882知识首页 9001  4.921268

代码4

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retu j#engine = create_engine('mysql+pymysql://root:123456@127.0.0.1:3306/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()*100df1.sort_values(by='fullURLId',ascending=False,inplace=True)print(df1.round(4))

1010034710200225107001346199900164718301001356Name: fullURLId, dtype: int64 fullURLId perc1999001  64718  98.8182301001 3560.5436107001 3460.5283101003  470.0718102002  250.0382

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'  retu 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:123456@127.0.0.1:3306/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() * 100df1_.sort_values(by='type', ascending=False, inplace=True)print(df1_)

法律快车-律师助手49894法律快车法律咨询  6421咨询发布成功 5220快搜1943法律快车  818其他 359法律快车法律经验59空 4Name: type, dtype: int64fullURL  \2631  http://www.lawtime.cn/spelawyer/index.php?py=g...2632  http://www.lawtime.cn/spelawyer/index.php?py=g...1677  http://m.baidu.com/from=844b/bd_page_type=1/ss...4303  http://m.baidu.com/from=0/bd_page_type=1/ssid=...3673  http://www.lawtime.cn/lawyer/lll25879862593080...... ...4829  http://www.lawtime.cn/spelawyer/index.php?m=se...4837  http://www.lawtime.cn/spelawyer/index.php?m=se...4842  http://www.lawtime.cn/spelawyer/index.php?m=se...8302  http://www.lawtime.cn/spelawyer/index.php?m=se...5034  http://www.baidu.com/link?url=O7iBD2KmoJdkHWTZ...pageTitle type  2631个旧律师成功案例 - 法律快车提供个旧知名律师、优秀律师、专业律师的咨询和推荐其他  2632个旧律师成功案例 - 法律快车提供个旧知名律师、优秀律师、专业律师的咨询和推荐其他  1677  婚姻法论文 - 法律快车法律论文  其他  4303什么是机动车？什么是非机动车？ - 法律快车交通事故其他  3673  404错误提示页面 - 法律快车 其他  ......  ...  4829  律师搜索,律师查找 - 法律快车提供全国知名律师、优秀律师、专业律师的咨询和推荐其他  4837  律师搜索,律师查找 - 法律快车提供全国知名律师、优秀律师、专业律师的咨询和推荐其他  4842  律师搜索,律师查找 - 法律快车提供全国知名律师、优秀律师、专业律师的咨询和推荐其他  8302  律师搜索,律师查找 - 法律快车提供全国知名律师、优秀律师、专业律师的咨询和推荐其他  5034 离婚协议书范本（2015年版） - 法律快车婚姻法其他  [359 rows x 3 columns] type 1999001 总数perc法律快车-律师助手4989477.094471法律快车法律咨询 6421 9.921506咨询发布成功5220 8.065762快搜1943 3.002256法律快车 818 1.263945其他359 0.554714法律快车法律经验59 0.091165空4 0.006181

代码6

#6无目的用户def xiaguang(i):  # 自定义统计函数  j = i.loc[(i['fullURL'].str.contains('\.html')) == False,  ['fullURL', 'fullURLId', 'pageTitle']]  retu 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:102011@127.0.0.1:3306/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() * 100xg_.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idxgs_ = 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() * 100print(xgs_.round(4))

1999001117124107001  17843102002  1202110100156031060013957102001212910200312353010011018101009854102007538102008404101008378102004361102005271102009214102006184101004125101006107101005 63Name: fullURLId, dtype: int64type num percentage199117124 71.2307107 17843 10.8515102 17357 10.5559101  7130  4.3362106  3957  2.4065301  1018  0.6191

代码7

# 分析网页点击次数# 统计点击次数engine = create_engine('mysql+pymysql://root:102011@127.0.0.1:3306/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1hit_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)82033 295502 1103182111601021362061 ..4294809358242948111501429485215434294865422242949176901Name: realIP, Length: 230149, dtype: int64 用户数  用户比例11321190.5740592441750.1919413175730.0763554101560.0441285 59520.0258626 41320.0179547 26320.0114367次以上134100.058267

代码8

# 分析浏览一次的用户行为engine = create_engine('mysql+pymysql://root:102011@127.0.0.1:3306/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.valuesURL_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)count比例101003102560 0.64901110700119443 0.12303719990019381 0.059364301001  515 0.003259其他26126 0.165328

代码9

# 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))count  \fullURL http://www.lawtime.cn/info/shuifa/slb/201211197...1013http://www.lawtime.cn/info/hunyin/lhlawlhxy/201...501http://www.lawtime.cn/ask/question_925675.html423http://www.lawtime.cn/info/shuifa/slb/201211197...367http://www.lawtime.cn/ask/exp/13655.html  301http://www.lawtime.cn/ask/exp/8495.html241http://www.lawtime.cn/ask/exp/13445.html  199http://www.lawtime.cn/guangzhou177http://www.lawtime.cn/ask/exp/17357.html  171http://www.lawtime.cn/citylist.php117 fullURL  fullURLhttp://www.lawtime.cn/info/shuifa/slb/201211197...  http://www.lawtime.cn/info/shuifa/slb/20121119...  http://www.lawtime.cn/info/hunyin/lhlawlhxy/201...  http://www.lawtime.cn/info/hunyin/lhlawlhxy/20...  http://www.lawtime.cn/ask/question_925675.html http://www.lawtime.cn/ask/question_925675.html  http://www.lawtime.cn/info/shuifa/slb/201211197...  http://www.lawtime.cn/info/shuifa/slb/20121119...  http://www.lawtime.cn/ask/exp/13655.html http://www.lawtime.cn/ask/exp/13655.html  http://www.lawtime.cn/ask/exp/8495.htmlhttp://www.lawtime.cn/ask/exp/8495.html  http://www.lawtime.cn/ask/exp/13445.html http://www.lawtime.cn/ask/exp/13445.html  http://www.lawtime.cn/guangzhouhttp://www.lawtime.cn/guangzhou  http://www.lawtime.cn/ask/exp/17357.html http://www.lawtime.cn/ask/exp/17357.html  http://www.lawtime.cn/citylist.php http://www.lawtime.cn/citylist.php

第二部分

代码10

import osimport reimport pandas as pdimport pymysql as pmfrom 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 0info1 = info.loc[index,:]print(info1.head())realIPfullURL02683657840  http://www.lawtime.cn/info/hunyin/hunyinfagui/...42683657840  http://www.lawtime.cn/info/hunyin/hunyinfagui/...91275347569  http://www.lawtime.cn/info/hunyin/lhlawlhxy/20...62  1531496412  http://www.lawtime.cn/info/hunyin/hunyinfagui/...86838215995  http://www.lawtime.cn/info/hunyin/lhlawlhxy/20...

代码11

# 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)

代码12

# 筛选满足一定浏览次数的IPIP_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 = 2index = IP_count.loc[:,'count']>nIP_index = IP_count.loc[index,'IP']print(IP_index.head())02609113527138124107442 2258966313 24267384741190924814Name: IP, dtype: object

代码13

# 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.sampleindex_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IPurl_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)

代码14

# 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']]==1else:Res.loc[i,'T/F'] = False# 保存推荐结果Res.to_csv('D:/python123/Res.csv',index=False,encoding='utf8')

代码15

# 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)