Hive案例04-员工部门表综合案例

1. 数据说明

(1) dept表

hive> select * from dept;

# deptno(部门编号)     dname(部门名称)          loc(部门所在地区)
  10                   ACCOUNTING               NEW YORK
  20                   RESEARCH                 DALLAS
  30                   SALES                    CHICAGO
  40                   OPERATIONS               BOSTON

(2) emp表

hive> select * from emp;

# 员工编号   员工姓名    职务        领导编号     入职日期     工资    奖金    部门编号    
# empno     ename       job         mgr         hiredate    sal    comm    deptno
  7369      SMITH       CLERK       7902        1980-12-17  800.0   0.0    20
  7499      ALLEN       SALESMAN    7698        1981-02-20  1600.0  300.0  30
  7521      WARD        SALESMAN    7698        1981-02-22  1250.0  500.0  30
  7566      JONES       MANAGER     7839        1981-04-02  2975.0  0.0    20
  7654      MARTIN      SALESMAN    7698        1981-09-28  1250.0  1400.0 30
  7698      BLAKE       MANAGER     7839        1981-05-01  2850.0  0.0    30
  7782      CLARK       MANAGER     7839        1981-06-09  2450.0  0.0    10
  7788      SCOTT       ANALYST     7566        1987-07-13  3000.0  0.0    20
  7839      KING        PRESIDENT   NULL        1981-11-07  5000.0  0.0    10
  7844      TURNER      SALESMAN    7698        1981-09-08  1500.0  0.0    30
  7876      ADAMS       CLERK       7788        1987-07-13  1100.0  0.0    20
  7900      JAMES       CLERK       7698        1981-12-03  950.0   0.0    30
  7902      FORD        ANALYST     7566        1981-12-03  3000.0  0.0    20
  7934      MILLER      CLERK       7782        1982-01-23  1300.0  0.0    10

2. SQL查询练习题目

(1) 查询总员工数

select count(distinct empno) from emp;

# 14

(2) 查询总共有多少个职位

select count(distinct job) from emp;

# 5

(3) 统计每个职位有多少个员工，并且按照数量从大到小排序

select job, count(distinct empno) as count_emp from emp
group by job
order by count_emp desc;

# 结果
job         count_emp
SALESMAN    4
CLERK       4
MANAGER     3
ANALYST     2
PRESIDENT   1

(4) 查询入职最早的员工

select emp.ename, emp.hiredate from emp 
join (select min(hiredate) as min_date from emp) tmp
on emp.hiredate = tmp.min_date;

# 结果
SMITH   1980-12-17

# 注意，以下SQL在hive中不能执行
select ename from emp 
where hiredate = (select min(hiredate) from emp);

(5) 统计出每个岗位的最高工资和平均工资

select job, max(sal), avg(sal)
from emp
group by job;

# 结果
ANALYST     3000.0      3000.0
CLERK       1300.0      1037.5
MANAGER     2975.0      2758.3333333333335
PRESIDENT   5000.0      5000.0
SALESMAN    1600.0      1400.0

(6) 查询出每个地区工资最高的员工

select emp.ename, tmp2.max_sal, tmp2.loc from emp 
join 
(select tmp1.loc loc, max(tmp1.sal) max_sal from
(select emp.ename ename, emp.sal sal, dept.loc loc from emp
join dept on emp.deptno = dept.deptno) tmp1
group by tmp1.loc) tmp2
on emp.sal = tmp2.max_sal;

# 结果
BLAKE   2850.0  CHICAGO
SCOTT   3000.0  DALLAS
FORD    3000.0  DALLAS
KING    5000.0  NEW YORK

(7) 查询上半年入职员工最多的地区

create table e1 as
select emp.ename ename, substring(emp.hiredate, 6, 2) as hiremonth, dept.loc loc
from emp join dept on emp.deptno = dept.deptno;

/*
SMITH   12  DALLAS
ALLEN   02  CHICAGO
WARD    02  CHICAGO
JONES   04  DALLAS
MARTIN  09  CHICAGO
BLAKE   05  CHICAGO
CLARK   06  NEW YORK
SCOTT   07  DALLAS
KING    11  NEW YORK
TURNER  09  CHICAGO
ADAMS   07  DALLAS
JAMES   12  CHICAGO
FORD    12  DALLAS
MILLER  01  NEW YORK
*/

create table e2 as
select ename,
case when hiremonth <= '06' then 'first_half_year' else 'last_half_year' end as hire_year,
loc 
from e1;

/*
SMITH   last_half_year  DALLAS
ALLEN   first_half_year CHICAGO
WARD    first_half_year CHICAGO
JONES   first_half_year DALLAS
MARTIN  last_half_year  CHICAGO
BLAKE   first_half_year CHICAGO
CLARK   first_half_year NEW YORK
SCOTT   last_half_year  DALLAS
KING    last_half_year  NEW YORK
TURNER  last_half_year  CHICAGO
ADAMS   last_half_year  DALLAS
JAMES   last_half_year  CHICAGO
FORD    last_half_year  DALLAS
MILLER  first_half_year NEW YORK
*/

select loc, count(ename) as count 
from e2
where hire_year = 'first_half_year'
group by loc
order by count desc
limit 1;

/*
CHICAGO 3
*/