HiveSQL语法练习及答案（三）

Hive数据表练习

建表语句

员工信息表emp：
字段：员工id,员工名字,工作岗位,部门经理,受雇日期,薪水,奖金,部门编号
英文名：EMPNO,ENAME,JOB,MGR,HIREDATE,SAL,BONUS,DEPTNO
create table emp(
    EMPNO int
    ,ENAME string
    ,JOB string
    ,MGR int
    ,HIREDATE string
    ,SAL int
    ,BONUS int
    ,DEPTNO int
) 
row format delimited
fields terminated by ',';

7369,SMITH,CLERK,7902,1980-12-17,800,null,20
7499,ALLEN,SALESMAN,7698,1981-02-20,1600,300,30
7521,WARD,SALESMAN,7698,1981-02-22,1250,500,30
7566,JONES,MANAGER,7839,1981-04-02,2975,null,20,
7654,MARTIN,SALESMAN,7698,1981-09-28,1250,1400,30
7698,BLAKE,MANAGER,7839,1981-05-01,2850,null,30
7782,CLARK,MANAGER,7839,1981-06-09,2450,null,10
7788,SCOTT,ANALYST,7566,1987-04-19,3000,null,20
7839,KING,PRESIDENT,null,1981-11-17,5000,null,10
7844,TURNER,SALESMAN,7698,1981-09-08,1500,0,30
7876,ADAMS,CLERK,7788,1987-05-23,1100,null,20
7900,JAMES,CLERK,7698,1981-12-03,950,null,30
7902,FORD,ANALYST,7566,1981-12-03,3000,null,20
7934,MILLER,CLERK,7782,1982-01-23,1300,null,10

部门信息表dept：
字段：部门编号,部门名称,部门地点
英文名：DEPTNO,DEPTNAME,DEPTADDR
create table dept(
    DEPTNO int
    ,DEPTNAME string
    ,DEPTADDR string
) 
row format delimited
fields terminated by ',';

部门编号,部门名称,部门地点
10,ACCOUNTING,NEW YORK
10,ACCOUNTING,shanghai
20,RESEARCH,DALLAS
30,SALES,CHICAGO
40,OPERATIONS,BOSTON

SQL练习

1． 列出至少有一个员工的所有部门。

#列出多于1个员工的所有部门编号及人数
SELECT DEPTNO,COUNT(*) AS num FROM emp GROUP BY DEPTNO HAVING num > 0;
# 连表 得到部门编号及名称
SELECT distinct s.DEPTNO,dept.DEPTNAME FROM (SELECT DEPTNO,COUNT(*) AS num FROM emp GROUP BY DEPTNO HAVING num > 0) AS s LEFT JOIN  dept ON s.DEPTNO=dept.DEPTNO;

2． 列出薪金比“SMITH”多的所有员工。

#mysql
SELECT  ENAME,SAL FROM emp WHERE SAl>(SELECT SAL FROM emp WHERE ENAME="SMITH");

hive 不支持子查询

1.(select ENAME,SAL,1 as cid from emp) as e1
2.(select SAL,1 as cid from emp where ENAME='SMITH') as e2
#将1,2连表
select e1.ename,e1.sal from (select ENAME,SAL,1 as cid from emp) as e1 left join (select SAL,1 as cid from emp where ENAME='SMITH') as e2 on e1.cid=e2.cid where e1.sal > e2.sal;

3． 列出所有员工的姓名及其直接上级的姓名。

SELECT emp1.ename,emp.ename mgrname FROM emp AS emp1 INNER JOIN
emp ON emp1.mgr=emp.empno;

4． 列出受雇日期早于其直接上级的所有员工。

SELECT e.empno,e.ename FROM emp AS e LEFT JOIN emp ON  e.MGR = emp.EMPNO WHERE e.HIREDATE<emp.HIREDATE;

5． 列出部门名称和这些部门的员工信息，同时列出那些没有员工的部门。

SELECT DEPTNAME,ENAME FROM dept LEFT JOIN emp ON  dept.`DEPTNO`=emp.DEPTNO ORDER BY DEPTNAME;

6． 列出所有“CLERK”（办事员）的姓名及其部门名称。

先连表再筛选
SELECT ENAME,DNAME,JOB FROM dept LEFT JOIN emp ON  dept.`DEPTNO`=emp.DEPTNO WHERE JOB="CLERK";
先筛选再连表
select a.ename,a.job,dept.deptname from (select * from emp where JOB = "CLERK" ) as a left join dept ON a.DEPTNO=dept.DEPTNO;

7． 列出最低薪金大于1500的各种工作。

select job,min(sal) as minsal from emp group by job having minsal>1500;

8． 列出在部门“SALES”（销售部）工作的员工的姓名，假定不知道销售部的部门编号

# mysql
SELECT ENAME FROM dept LEFT JOIN emp ON dept.`DEPTNO`=emp.DEPTNO WHERE DEPTNAME = "SALES";
求编号（where不支持子查询，支持 in）
SELECT ENAME FROM emp WHERE DEPTNO in (SELECT DEPTNO FROM dept WHERE DEPTNAME = "SALES");

9． 列出薪金高于公司平均薪金的所有员工。

# mysql
select ename from emp where sal > (select avg(sal) from emp);
//hive需要连表
1. select ename,1 as cid from emp;
2. select avg(sal),1 as cid  from emp;
连表
select e1.ename from 
(select *,1 as cid from emp) as e1 
left join 
(select avg(sal) as avgsal,1 as cid  from emp) as e2 
on e1.cid = e2.cid where e1.sal>e2.avgsal;

10．列出与“SCOTT”从事相同工作的所有员工。

#查看scott的工作
select job from emp where ename="SCOTT";
#使用in
select e1.ename from emp as e1 where job in (select e2.job from emp as e2 where ename="SCOTT") and e1.ename != "SCOTT";

11．列出薪金等于部门30中员工的薪金的所有员工的姓名和薪金。

SELECT ename,sal FROM emp as e1 WHERE sal IN (SELECT sal FROM emp as e2 WHERE deptno=30);

12．列出薪金高于在部门30工作的所有员工的薪金的员工姓名和薪金。

# mysql
SELECT ENAME,SAL FROM emp WHERE SAL > (SELECT MAX(SAL) FROM emp WHERE DEPTNO=30);
# hive连表
select e1.ename,e1.sal from (select *,1 as cid from emp) as e1 
left join (SELECT MAX(SAL) as maxsal,1 as cid FROM emp WHERE DEPTNO=30) as e2 
on e1.cid = e2.cid where e1.sal>e2.maxsal;

13．列出在每个部门工作的员工数量、平均工资和平均服务期限。

SELECT DEPTNO,COUNT(*),AVG(SAL),AVG(DATEDIFF(CURRENT_DATE,HIREDATE)) FROM emp GROUP BY DEPTNO;

14．列出所有员工的姓名、部门名称和工资。

SELECT distinct ENAME,SAL ,DEPTNAME FROM emp LEFT JOIN dept ON emp.`DEPTNO`=dept.`DEPTNO`;

15．列出所有部门的详细信息和部门人数。

#求出部门人数
 SELECT DEPTNO,COUNT(*) FROM emp GROUP BY DEPTNO;
 //hive
with tmp AS (SELECT * FROM dept LEFT JOIN (SELECT DEPTNO AS dno,COUNT(*) AS num FROM emp GROUP BY DEPTNO) AS d ON d.dno=dept.`DEPTNO`)
SELECT DEPTNO,DEPTNAME,DEPTADDR,num FROM tmp;

16．列出各种工作的最低工资。

select job,min(sal) from emp group by job;

17．列出各个部门的MANAGER（经理）的最低薪金。

select deptno,min(sal) from emp where job = "MANAGER" group by deptno; 

18．列出所有员工的年工资,按年薪从低到高排序。

1. SELECT ENAME,SAL*12 + CASE WHEN BONUS IS NULL THEN 0 ELSE BONUS END AS yearSAL FROM emp ORDER BY yearSAL;
2. select ENAME,SAL*12 + nvl(BONUS,0) as yearSAL from emp order by yearSAL;

19. 列出每个部门薪水前两名最高的人员名称以及薪水。

 # mysql
 SELECT * FROM emp
 WHERE 2>(
 SELECT COUNT(*) FROM emp AS e WHERE emp.DEPTNO=e.deptno AND emp.sal<e.sal);
 # hive开窗
 with tmp as (select ename,sal,deptno,row_number() over (partition by deptno order by sal desc ) as num from emp)
 select ename,sal deptno from tmp where num < 3;

20. 列出每个员工从受雇开始到2018-12-12 为止共受雇了多少天。

 select ename,DATEDIFF('2018-12-12',HIREDATE) from emp;