示例:
- 1.建表
create table t_dml (detail_id bigint,sale_date date,province string,city string,product_id bigintcnt double,amt double,
)row format delimited
fields terminated by ','; //列分隔符
create table t_product(product_id bigint,product_name string,category_id bigint,category_name string,price double
)row format delimited
fields terminated ',';
- 2.加载数据
load data local inpath '/opt/data/t_dml.csv' into table t_dml;
load data local inpath '/opt/data/t_product.csv' into table t_product;
- 3.常见SQL语句
查询销售记录的时间段:
select max(sale_date),min(sale_date) form t_dml;
查询各商品类别的总销售额
select t.category_name, sum(t.amt) as total_money
from
(select a.product_id, a.amt, b.category_name
from t_dml a
join t_product b
on a.product_id == b.product_id
) t
group by t.category_name;
查询销售量排行榜
select a.product_name, t.cnt_total, rank() over(order by t.cnt_total desc) as rk
(select product_id, sum(cnt) as cnt_total
from t_dml
group by product_id
order by cnt_total desc
limit 10
) t
join t_product a
on a.product_id == t.product_id;
想知道各个市县的购买力,同时自己的商品在哪个地区最热卖,通过创建中间表,优化查询
- 创建中间表
create table t_city_amt(province string,city string,total_money double
);
create table t_city_prod
(province string,city string,product_id bigint,product_name string,category_id bigint,cnt bigint
);
- 插入数据
insert into t_city_amt
select province,city,sum(amt)
form t_dml
group by province,city
insert into t_city_prod
select t.province, t.city, t.product_id, t.product_name, sum(t.cnt)
from
(
select a.product_id, b.product_name, a.cnt, a.province, a.city
form t_dml a join t_product b
on a.product_id = b.product_id
) t
group by t.province, t.city, t.product_id, t.product_name
- 基于中间表进行查询
select
form
(select province, city, product_id, product_name,from t_city_prod
) t