Hive(27):分析网站uvpv等多指标综合案例

一、实现功能

1.分析网站日志，获得日期，uv，pv，登录人数，游客人数，平均访问时长，二跳率，独立ip数等关键信息。

其中：
登录：userid有值，会员，有账号登录
游客：userid无值，非登录人员
平均访问时长：在网页停留时间
二跳率：在一次会话中，同一个session点击的页面大于等于2的会话就是二跳（判断同一个session有多条记录的几率是多少）
独立ip数：统计ip去重

2.日志数据集

yhd_source.id   yhd_source.url  yhd_source.referer      yhd_source.keyword      yhd_source.type yhd_source.guidyhd_source.pageid        yhd_source.moduleid     yhd_source.linkid       yhd_source.attachedinfo yhd_source.sessionid    yhd_source.trackeru     yhd_source.trackertype  yhd_source.ip   yhd_source.trackersrc   yhd_source.cookie       yhd_source.ordercode    yhd_source.tracktime    yhd_source.enduserid    yhd_source.firstlink    yhd_source.sessionviewno        yhd_source.productid    yhd_source.curmerchantid        yhd_source.provinceid   yhd_source.cityid       yhd_source.fee  yhd_source.edmactivity  yhd_source.edmemail     yhd_source.edmjobid     yhd_source.ieversion    yhd_source.platform     yhd_source.internalkeyword      yhd_source.resultsum    yhd_source.currentpage  yhd_source.linkposition yhd_source.buttonposition       yhd_source.date
121508281810000000      http://www.yhd.com/?union_ref=7&cp=0                    3       PR4E9HWE38DMN4Z6HUG667SCJNZXMHSPJRER                                    VFA5QRQ1N4UJNS9P6MH6HPA76SXZ737P        10977119545            124.65.159.122           unionKey:10977119545            2015-08-28 18:10:00     50116447        http://image.yihaodianimg.com/virtual-web_static/virtual_yhd_iframe_index_widthscreen.html?randid=2015828       6              1000                                     Mozilla/5.0 (Windows NT 6.1; rv:40.0) Gecko/20100101 Firefox/40.0      Win32                                    lunbo_tab_3     2015082818
121508281810000001      http://my.yhd.com/order/finishOrder.do?orderCode=5435446505152  http://buy.yhd.com/checkoutV3/index.do          3       YJ25S3QAVPAS31PHSB3HFGZ1E5AYMKX9XUTX                                    6W26QM41DM6HHND3R4FP42YYXXE1NKGA                        222.73.202.251                          2015-08-28 18:10:00    85133152 http://www.haosou.com/s?src=new_isearch&q=1%E5%8F%B7%E5%BA%97   25      0                       1      Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36    Win32  MY_ORDERCOMPLETION_EDITADDRESS   2015082818
121508281810000002      http://list.yhd.com/p/c5072-b-a-s1-v0-p1-price-d0-pid-pt1086211-pl1171565-m0-k?tp=44.1086211.0.0.0.Kxnn54p-11-FFJKr     http://list.yhd.com/p/pt1086211-pl1171565?tp=44.1086211.1508.0.1.Kxnmyye-11-FFJKr               3       JRBWWU6ECXN15Q2Z5QT4TETNHKY7QHE3Y8B3            44.1086211.0.0.0.Kxnn54p-11-FFJKr      5Z5JZMYUGK9TP3QWHDDTU6G5T6PHEQRZ 4734            111.193.165.158         msessionid:DW6SB2FGG84ZZ2WD77DAZHFBXNV8D5776RQ4,uname:gaochentongxue,unionKey:4734,websiteId:A100215249         2015-08-28 18:10:00     116262550      http://www.yhd.com/?tracker_u=1624169&t=1440753050503    107                     2       1000                   Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36    Win32  107      1       search_navi_cat_4               2015082818

二、数据处理

1.数据采集加载到hive

create database yhd;
		
create table yhd_source(
id              string,
url             string,
referer         string,
keyword         string,
type            string,
guid            string,
pageId          string,
moduleId        string,
linkId          string,
attachedInfo    string,
sessionId       string,
trackerU        string,
trackerType     string,
ip              string,
trackerSrc      string,
cookie          string,
orderCode       string,
trackTime       string,
endUserId       string,
firstLink       string,
sessionViewNo   string,
productId       string,
curMerchantId   string,
provinceId      string,
cityId          string,
fee             string,
edmActivity     string,
edmEmail        string,
edmJobId        string,
ieVersion       string,
platform        string,
internalKeyword string,
resultSum       string,
currentPage     string,
linkPosition    string,
buttonPosition  string
)partitioned by (date string)
row format delimited fields terminated by "\t";

load data local inpath '/opt/datas/2015082818' into table yhd_source partition(date ='2015082818');

2.数据清洗

创建会话信息表：
create table session_info(
session_id string ,
guid string ,
trackerU string ,
landing_url string ,
landing_url_ref string ,
user_id string ,
pv string ,
stay_time string ,
min_trackTime string ,
ip string ,
provinceId string 
)
partitioned by (date string)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ;

3.创建两张临时表作为中间表

（1）两张临时表的结构关系

（2）创建第一张临时表：算出group才能得到的某些数值

create table session_tmp as
select 
sessionId session_id,
max(guid)  guid,
max(endUserId) user_id,
count(distinct url) pv,
(unix_timestamp(max(trackTime))-unix_timestamp(min(trackTime))) stay_time,
min(trackTime) min_trackTime,
max(ip) ip,
max(provinceId) provinceId
from yhd_source where date = '2015082818'
group by sessionId;

（3）创建第二张临时表

  备注：只是取关键字段，不需要任何处理。

create table track_tmp as
select 
sessionId session_id,
trackTime trackTime,
url landing_url,
trackerU trackerU,
referer landing_url_ref
from yhd_source where date='2015082818';

（4）两张临时表进行join

insert overwrite table session_info partition(date='2015082818')
select
a.session_id,
a.guid,
b.trackerU,
b.landing_url,
b.landing_url_ref,
a.user_id,
a.pv,
a.stay_time,
a.min_trackTime,
a.ip,
a.provinceId
from session_tmp a join track_tmp b
on a.session_id=b.session_id and a.min_trackTime=b.trackTime;

4.数据分析：结果表 

create table result2 as
select
date date,
sum(pv) PV,
count(distinct guid) UV,
count(distinct case when length(user_id)!=0  then user_id else null end) login_user,
count(distinct case when length(user_id)=0 then guid else null end) visitor,
avg(stay_time) avg_time,
count(case when pv>=2 then session_id else null end)/count(session_id) second_jump,
count(distinct ip) IP
from session_info where date='2015082818'
group by date;

结果

日期	      uv	    pv	    登录人数	  游客人数    平均访问时长	          二跳率	           独立ip数
2015082818	 23928	  37843.0	11411	      12367	       50.10636239012983	0.26695427788081605	     19174