千家信息网

Hive Sum MAX Over Demo(单月访问次数和总访问次数)

发表于:2024-11-22 作者:千家信息网编辑
千家信息网最后更新 2024年11月22日,A,2015-01,5A,2015-01,15B,2015-01,5A,2015-01,8B,2015-01,25A,2015-01,5A,2015-02,4A,2015-02,6B,2015-02,
千家信息网最后更新 2024年11月22日Hive Sum MAX Over Demo(单月访问次数和总访问次数)

A,2015-01,5
A,2015-01,15
B,2015-01,5
A,2015-01,8
B,2015-01,25
A,2015-01,5
A,2015-02,4
A,2015-02,6
B,2015-02,10
B,2015-02,5
A,2015-03,16
A,2015-03,22
B,2015-03,23
B,2015-03,10
B,2015-03,1

求每个用户单月的访问次数和总访问次数
create external table if not exists t_access(
uname string comment '用户名',
umonth string comment '月份',
ucount int comment '访问次数'
) comment '用户访问表'
row format delimited fields terminated by ","
location "/user/hive/t_access";

load data local inpath "/root/tmonthcount.txt" into table t_access;

select tba.*,tbb.allCount
from
(
select uname,umonth,sum(ucount) as tuconut
from t_access
group by uname,umonth) tba
join (select uname,sum(ucount) as allCount from t_access group by uname) tbb on tbb.uname=tba.uname
;

select uname,umonth,ucount,sum(ucount) over(partition by uname,umonth) as tuconut,sum(ucount) over(partition by uname) as allCount
from t_access;

A 2015-01 33 81
A 2015-02 10 81
A 2015-03 38 81
B 2015-01 30 79
B 2015-02 15 79
B 2015-03 34 79

每个用户截止到每月为止的最大单月访问次数和累计到该月的总访问次数,结果数据格式如下

select tmp.*
,max(tmp.tuconut) over(partition by tmp.uname order by tmp.umonth rows between unbounded preceding and current row) as maxCount
,sum(tmp.tuconut) over(partition by tmp.uname order by tmp.umonth rows between unbounded preceding and current row) as allCount
from
(select uname,umonth,sum(ucount) as tuconut
from t_access
group by uname,umonth) tmp;

A 2015-01 33 33 33
A 2015-02 10 33 43
A 2015-03 38 38 81
B 2015-01 30 30 30
B 2015-02 15 30 45
B 2015-03 34 34 79

0