Hive 基础测试(二)

准备数据

• 学生表student

         学号sid，姓名sname，性别ssex，年龄sage，系 department
         95001,李勇,男,20,CS
         95002,刘晨,女,19,IS
         95003,王敏,女,22,MA
         95004,张立,男,19,IS
         95005,刘刚,男,18,MA
         95006,赵丽,女,20,CS

• 成绩表score

         学生编号sid，课程编号cid，成绩sscore 
         95001,1,81
         95001,2,85
         95001,3,88
         95001,4,70
         95002,1,90
         95002,2,80
         95002,3,90
         95002,4,80
         95003,1,70
         95003,2,78
         95003,3,65
         95003,4,65
         95004,1,70
         95004,2,90
         95004,3,85
         95004,4,90
         95005,1,70
         95005,2,90
         95005,3,70
         95005,4,90
         95006,1,70
         95006,2,90
         95006,3,70
         95006,4,90

• 课程表course

         课程编号cid，课程名cname
         1,数据库
         2,数学
         3,信息系统
         4,操作系统

需求1：创建三个外部表，并分别给外部表加载数据.

create external  table student(
 sid string,
 sname string,
 ssex string,
 sage int)
row format delimited fields terminated by ',';
load data local inpath '/root/test/student.txt' into table student;


create external  table score(
sid string,
cid string,
 sscore int)
row format delimited fields terminated by ',';
load data local inpath '/root/test/score.txt' into table score;


create  external table course(
cid string,
cname string)
row format delimited fields terminated by ',';
load data local inpath '/root/test/course.txt' into table course;

需求2：查询各课的学生人数。

select  b.cname, a.num
from 
(select cid ,count(*)  num from score group by cid) a, course b
where a.cid=b.cid;

需求3: 查询每个学生的总成绩，并对总成绩进行降序排序,要求显示字段:学生名字，学生学号，学生总成绩

select  st.sname ,st.sid  ,sum(sc.sscore)
from student st
    join score  sc
        on st.sid=sc.sid
group by st.sname, st.sid;

需求4：求总课程平均分最高的前三名学生

select sname,b.dr,b.avgScore
from(select a.sid,avgScore,dense_rank() over(order by avgScore desc) dr
from (select sid,avg(sscore) avgScore
from score group by sid) a) b,student 
where b.sid = student.sid and dr<4;