数据准备

CREATE TABLE test.test2 (
user_id string,
shop string )
ROW format delimited FIELDS TERMINATED BY '\t';
INSERT INTO TABLE test.test2 VALUES
( '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' );

需求

– 请统计：
–（1）每个店铺的UV（访客数）
– (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

输入

输出

--（1）每个店铺的UV（访客数）
select shop,count(distinct user_id) cnt
from test.test2
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
with t1 as (
    select shop,user_id,count(1) as cnt,
       row_number() over (partition by shop order by shop , count(1) desc) as rn1
    from test.test2
    group by shop,user_id
)
select shop,user_id,cnt
from t1
where rn1<=3
order by shop,rn1;