第一道SQL
我们有如下的用户访问数据
userId | visitDate | visitCount |
u01 | 2019/1/21 | 5 |
u02 | 2019/1/23 | 6 |
u03 | 2019/1/22 | 8 |
u04 | 2019/1/20 | 3 |
u01 | 2019/1/23 | 6 |
u01 | 2019/2/21 | 8 |
u02 | 2019/1/23 | 6 |
u01 | 2019/2/22 | 4 |
要求使用SQL统计出每个用户每月的累积访问次数,如下表所示:
用户id | 月份 | 小计 | 累积 |
u01 | 2019-01 | 11 | 11 |
u01 | 2019-02 | 12 | 23 |
u02 | 2019-01 | 12 | 12 |
u03 | 2019-01 | 8 | 8 |
u04 | 2019-01 | 3 | 3 |
数据:
u01 2019/1/21 5
u02 2019/1/23 6
u03 2019/1/22 8
u04 2019/1/20 3
u01 2019/1/23 6
u01 2019/2/21 8
u02 2019/1/23 6
u01 2019/2/22 4
1)创建表
create table action
(userId string,
visitDate string,
visitCount int)
row format delimited fields terminated by "\t";
1)修改数据格式
select
userId,
date_format(regexp_replace(visitDate,'/','-'),'yyyy-MM') mn,
visitCount
from
action;t1
2)计算每人单月访问量
select
userId,
mn,
sum(visitCount) mn_count
from
t1
group by userId,mn;t2
3)按月累计访问量
select
userId,
mn,
mn_count,
sum(mn_count) over(partition by userId order by mn)
from t2;
最终SQL
SELECT
userId,
mn,
mn_count,
sum( mn_count ) over ( PARTITION BY userId ORDER BY mn )
FROM
(
SELECT
userId,
mn,
sum( visitCount ) mn_count
FROM
( SELECT userId, date_format( regexp_replace ( visitDate, '/', '-' ), 'yyyy-MM' ) mn, visitCount FROM action ) t1
GROUP BY
userId,
mn
) t2;
第二道SQL
有50W个京东店铺,每个顾客访客访问任何一个店铺的任何一个商品时都会产生一条访问日志,访问日志存储的表名为Visit,访客的用户id为user_id,被访问的店铺名称为shop,请统计:
u1 a
u2 b
u1 b
u1 a
u3 c
u4 b
u1 a
u2 c
u5 b
u4 b
u6 c
u2 c
u1 b
u2 a
u2 a
u3 a
u5 a
u5 a
u5 a
建表:
create table visit(user_id string,shop string) row format delimited fields terminated by '\t';
load data local inpath '/opt/module/datas/visit.txt' into table visit;
1)每个店铺的UV(访客数)
select shop,count(distinct user_id) from visit group by shop;
2)每个店铺访问次数top3的访客信息。输出店铺名称、访客id、访问次数
(1)查询每个店铺被每个用户访问次数
select shop,user_id,count(*) ct
from visit
group by shop,user_id;t1
(2)计算每个店铺被用户访问次数排名
select shop,user_id,ct,rank() over(partition by shop order by ct) rk
from t1;t2
(3)取每个店铺排名前3的
select shop,user_id,ct
from t2
where rk<=3;
(4)最终SQL
select
shop,
user_id,
ct
from
(select
shop,
user_id,
ct,
rank() over(partition by shop order by ct) rk
from
(select
shop,
user_id,
count(*) ct
from visit
group by
shop,
user_id)t1
)t2
where rk<=3;