02、Hive数据仓库——SQL员工练习题

Hive数据仓库——SQL员工练习题

一：将下列数据加载hive表。

• test_emp数据库

create database test_emp;

use test_emp;

• 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 ',';

• 员工表数据

在/usr/local/soft/data目录下创建testemp.txt文件将下方数据复制进去。

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

• 加载员工表数据

load data local inpath '/usr/local/soft/data/testemp.txt' into table emp;

• 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 ',';

• 部门信息表数据

在/usr/local/soft/data目录下创建testdept.txt文件将下方数据复制进去。

10,ACCOUNTING,NEW YORK
10,ACCOUNTING,shanghai
20,RESEARCH,DALLAS
30,SALES,CHICAGO
40,OPERATIONS,BOSTON

• 加载部门信息表数据

load data local inpath '/usr/local/soft/data/testdept.txt' into table dept;

---

二：使用HQL完成下面需求

1． 列出至少有一个员工的所有部门。

• 注意distinct

select t1.deptno
       ,t1.DEPTNAME
       ,t1.DEPTADDR
       ,t2.cnt
from dept t1
join (
    select deptno
    ,count(distinct EMPNO) as cnt
    from emp
    group by deptno
)t2
on t1.deptno = t2.deptno;

2． 列出薪金比“SMITH”多的所有员工。

• Hive中的where条件不支持不等式的子查询，可通过join实现

select  t1.EMPNO
        ,t1.ENAME
        ,t1.sal_bonus
from (
    select  EMPNO
            ,ENAME
            ,12*SAL+nvl(BONUS,0) as sal_bonus
            ,1 as tmp_id
    from emp
) t1 
join (
    select  12*SAL+nvl(BONUS,0) as sal_bonus
            ,1 as tmp_id
    from emp
    where ENAME = 'SMITH'
) t2 on t1.tmp_id = t2.tmp_id
where t1.sal_bonus > t2.sal_bonus;

3． 列出所有员工的姓名及其直接上级的姓名。

select t1.EMPNO
       ,t2.ENAME as leader_name
from emp t1 join emp t2
on t1.MGR = t2.EMPNO;

4． 列出受雇日期早于其直接上级的所有员工。

select distinct
       t1.DEPTNO
       ,t1.DEPTNAME
       ,t2.EMPNO
       ,t2.ENAME
from dept t1
left join emp t2
on t1.DEPTNO = t2.DEPTNO;

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 distinct
       t1.DEPTNO
       ,t1.DEPTNAME
       ,t2.EMPNO
       ,t2.ENAME
from dept t1
left join emp t2
on t1.DEPTNO = t2.DEPTNO;

6． 列出所有“CLERK”（办事员）的姓名及其部门名称。

select t1.ENAME
       ,t2.DEPTNAME
from (
    select ENAME
           ,DEPTNO
    from emp
    where JOB = 'CLERK'       
) t1
join (
    select distinct
           DEPTNO
           ,DEPTNAME
    from dept       
) t2
on t1.DEPTNO = t2.DEPTNO;

7． 列出最低薪金大于1500的各种工作。

select t1.JOB
       ,t1.min_sal
from (
    select JOB
           ,min(SAL) as min_sal
    from emp
    group by JOB       
) t1
where t1.min_sal > 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。

select EMPNO
       ,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。

select t1.EMPNO
       ,t1.ENAME
       ,t1.sal_bonus
from (
    select EMPNO
           ,ENAME
           ,12*SAL+nvl(BONUS,0) as sal_bonus
           ,1 as tmp_id
    from emp       
) t1 join (
    select round(avg(12*SAL+nvl(BONUS,0)),2) as avg_sal_bonus
           ,1 as tmp_id
    from emp       
) t2
on t1.tmp_id = t2.tmp_id
where t1.sal_bonus > t2.avg_sal_bonus;

10．列出与“SCOTT”从事相同工作的所有员工。

select EMPNO
       ,t1.ENAME
       ,JOB
from emp t1
where t1.ENAME != 'SCOTT'
and exists (
    select JOB
    from emp t2
    where ENAME = 'SCOTT' and t1.JOB=t2.JOB
);

select EMPNO
       ,t1.ENAME
       ,JOB
from emp t1
where t1.ENAME != 'SCOTT'
and JOB in (
    select JOB
    from emp
    where ENAME = 'SCOTT'
);

11．列出薪水等于部门30中员工的薪金的所有员工的姓名和薪水。

select t1.ENAME
        ,t1.SAL
from emp t1
where t1.DEPTNO !=30
and t1.SAL in (
    select SAL
    from emp
    where DEPTNO = 30
);

没有相关的信息

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。

select t1.ENAME
       ,t1.sal_bonus
       ,t2.max_sal_bonus
from (
    select t1.ENAME
           ,12*t1.SAL+nvl(t1.BONUS,0) as sal_bonus
    from emp t1
    where t1.EMPNO !=30
) t1
join (
    select max(12*SAL+nvl(BONUS,0)) as max_sal_bonus
    from emp
    where DEPTNO = 30
) t2
on 1=1
where t1.sal_bonus > t2.max_sal_bonus;

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(distinct EMPNO) as cnt
       ,round(avg(12*SAL+nvl(BONUS,0)),2) as avg_sal_bonus
       ,round(avg(datediff(current_date(),HIREDATE)),2) as avg_work_days
from emp
group by DEPTNO;

14．列出所有员工的姓名、部门名称和工资。

select t1.ENAME
       ,t1.SAL
       ,t2.DEPTNAME
       ,t2.DEPTADDR
from emp t1
join dept t2
on t1.DEPTNO = t2.DEPTNO;

15．列出所有部门的详细信息和部门人数。

select t2.DEPTNO
       ,t2.DEPTNAME
       ,t2.DEPTADDR
       ,t1.cnt
from (
    select DEPTNO
           ,count(distinct EMPNO) as cnt
    from emp
    group by DEPTNO       
)t1 right join dept t2
on t1.DEPTNO = t2.DEPTNO;

16．列出各种工作的最低工资。

select JOB
       ,min(SAL) as min_sal
from emp
group by JOB;

17．列出各个部门的MANAGER（经理）的最低薪金。

select t1.DEPTNO
       ,min(12*SAL+nvl(BONUS,0)) as min_sal_bonus
from (
    select DEPTNO
           ,SAL
           ,BONUS
    from emp
    where JOB = 'MANAGER'
)t1
group by t1.DEPTNO;

18．列出所有员工的年工资,按年薪从低到高排序。

select EMPNO
       ,ENAME
       ,12*SAL+nvl(BONUS,0) as year_sal
from emp
order by year_sal;

19. 列出每个部门薪水前两名最高的人员名称以及薪水。

select t1.DEPTNO
       ,t1.ENAME
       ,t1.SAL
       ,t1.rn
from (
    select DEPTNO
           ,ENAME
           ,SAL
           ,row_number() over (partition by DEPTNO ORDER by SAL DESC) as rn
    from emp
) t1
where t1.rn <= 2;

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 EMPNO
       ,ENAME
       ,datediff('2018-12-12',HiREDATE) as days
from emp;

---

到底啦！关注靓仔学习大数据！