大数据入门到精通16--hive 的条件语句和聚合函数


一。条件表达

case when ... then when .... then ... when ... then ...end

select film_id,rpad(title,20," "),case when rating in ("G","PG","PG-13") then "YOUNG" WHEN RATING=="NC-17" THEN "17 AND UP" WHEN RATING="R" THEN "Mature" else "Unrated" end from film;

isnull() 函数


nvl(field ,field/date)
函数如果是空的话用后面的数据或者另外一个字段填空

二聚合函数

//聚合函数和join操作
select concat_ws(" ",a.first_name,a.last_name) abc ,count(*) counts
from actor a join film_actor fa on fa.actor_id=a.actor_id
join inventory i on i.film_id = fa.film_id
join rental r on r.inventory_id = i.inventory_id
group by concat_ws(" ",a.first_name,a.last_name)
order by counts
limit 10;

计算每个电影的类别出租的费用之和。

select rpad(c.name,15," "),sum(p.amount) sums from category c
join film_category fc on fc.category_id=c.category_id
join inventory i on i.film_id = fc.film_id
join rental r on r.inventory_id=i.inventory_id
join payment p on p.rental_id=r.rental_id
group by c.name
order by sums desc;

//支持从select语句形成的子表做select和聚合

select avg(counts) from (select inventory_id,count(inventory_id) as counts from rental group by inventory_id) s;

select concat_ws(" ",a.first_name,a.last_name) name ,sum(p.amount)
earning ,avg(p.amount) avgearning from actor a join film_actor fa on fa.actor_id= a.actor_id
join inventory i on i.film_id = fa.film_id
join rental r on r.inventory_id= i.inventory_id
join payment p on p.rental_id=r.rental_id
group by i.film_id, concat_ws(" ",a.first_name,a.last_name)
order by name,avgearning ;

//group by  和 order by 都可以是多个字段

相关