userId visitDate visitCount
u01 2017/1/21 5
u02 2017/1/23 6
u03 2017/1/22 8
u04 2017/1/20 3
u01 2017/1/23 6
u01 2017/2/21 8
U02 2017/1/23 6
U01 2017/2/22 4
要求使用SQL统计出每个用户的累积访
问次数,如下表所示:
用户id 月份 小计 累积
u01 2017-01 11 110
u01 2017-02 12 23
u02 2017-01 12 12
u03 2017-01 8 8
u04 2017-01 3 3
建表:
create table visit (userId String not null,
visitDate String not null,
visitCount int not null)
row format delimited fields terminated by "\t";
插入数据:
insert into table visit values('u01','2017/1/21',5)
insert into table visit values('u02','2017/1/23',6)
insert into table visit values('u03','2017/1/22',8)
insert into table visit values('u04','2017/1/20',3)
insert into table visit values('u01','2017/1/23',6)
insert into table visit values('u01','2017/1/21',8)
insert into table visit values('u02','2017/1/23',6)
insert into table visit values('u01','2017/1/22',4);
查询数据:
(1)修改数据格式
select
userId,
regexp_replace(visitDaate,'/','-') dt,
visitCount
from
visit;t1
(2) 每个用户按照月份对范文次数进行聚合,即前三列内容
select
userId,
date_format(dt,'yyyy-mm') mm,
sum(visitCount) sum_ct
from
t1
group by
userId,date_format(dt,'yyyy-mm');t2
(3)统计累计数据
select
userId,
mm,
sum_ct
sum(sum_ct) over(partition by userId order by mm)
from
t2;