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

hive> select * from ump;

# 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

select count(empno) from ump;

#Total MapReduce CPU Time Spent: 5 seconds 170 msec
#OK
#14

select count(distinct job) from  ump;

#Total MapReduce CPU Time Spent: 4 seconds 930 msec
#OK
#5

select job ,count (*)as emp_cnt
from ump
group by job
order by emp_cnt desc;


SALESMAN    4
CLERK    4
MANAGER    3
ANALYST    2
PRESIDENT    1

select ump.ename,ump.hiredate 
from ump
join
(select  min(hiredate) as hiredate from ump)t1
where ump.hiredate=t1.hiredate;

#SMITH    1980-12-17

select job ,max(sal)as max_sale,avg(sal)as min_sale
from ump 
group by job;

ANALYST 3000.0 3000.0
CLERK 950.0 1037.5
MANAGER 2975.0 2758.3333333333335
PRESIDENT 5000.0 5000.0
SALESMAN 1600.0 1400.0

select t2.loc,t2.ename,t2.sal 
from
(select t1.loc,t1.ename,t1.sal,
row_number() over(distribute by t1.loc sort by cast(t1.sal as int) desc) as index
from
(select  dept.loc,ump.ename,ump.sal from 
dept join ump
on dept.deptno=ump.deptno)t1
)t2
where t2.index=1;

#CHICAGO    BLAKE    2850.0
#DALLAS    FORD    3000.0
#NEW    KING    5000.0

select t1.loc,count(*)as cnt
from 
(select dept.loc,ump.ename,
cast(substr(ump.hiredate,6,2) as int) as hire_month
from dept join ump 
on dept.deptno=ump.deptno)t1
where t1.hire_month<=6
group by t1.loc
order by cnt desc
limit 1;

CHICAGO    3