hive50道经典练习题

    技术2023-09-01  108

    CREATE TABLE STUDENT( S_ID STRING, S_NAME STRING, S_BIRTH STRING, S_SEX STRING ) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

    CREATE TABLE COURSE(  C_ID STRING,  C_NAME STRING,  T_ID STRING ) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

    CREATE TABLE TEACHER( T_ID STRING, T_NAME STRING ) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

    CREATE TABLE SCORE ( S_ID STRING, C_ID STRING, S_SCORE INT ) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

    vi /opt/hivetest/student.csv

    01 赵雷 1990-01-01 男 02 钱电 1990-12-21 男 03 孙风 1990-05-20 男 04 李云 1990-08-06 男 05 周梅 1991-12-01 女 06 吴兰 1992-03-01 女 07 郑竹 1989-07-01 女 08 王菊 1990-01-20 女 vi /opt/hivetest/course.csv 01    语文    02 02    数学    01 03    英语    03 vi /opt/hivetest/teacher.csv 01    张三 02    李四 03    王五 vi /opt/hivetest/score.csv 01    01    80 01    02    90 01    03    99 02    01    70 02    02    60 02    03    80 03    01    80 03    02    80 03    03    80 04    01    50 04    02    30 04    03    20 05    01    76 05    02    87 06    01    31 06    03    34 07    02    89 07    03    98

    1. 查询"01"课程比"02"课程成绩高的学生的信息及课程分数: 方式1 select * from  (select  st.S_ID, st.S_NAME, co.C_ID, co.C_NAME, sc.S_SCORE from score as sc left join student as st on st.S_ID=sc.S_ID left join course as co on co.C_ID=sc.C_ID where co.C_ID='01' ) sc01 inner join  ( select  st.S_ID, st.S_NAME, co.C_ID, co.C_NAME, sc.S_SCORE from score as sc left join student as st on st.S_ID=sc.S_ID left join course as co on co.C_ID=sc.C_ID where co.C_ID='02' )sc02 on sc02.S_ID=sc01.S_ID where sc01.S_SCORE>sc02.S_SCORE

    ##方式2  with a as 效率更高 WITH A AS(  SELECT * FROM SCORE WHERE C_ID ='01' ), B AS(  SELECT * FROM SCORE WHERE C_ID ='02' ), C AS (  SELECT S.*,A.S_SCORE AS FIRST_SCORE, B.S_SCORE AS SECOND_SCORE FROM STUDENT S,A,B WHERE S.S_ID = A.S_ID AND S.S_ID = B.S_ID )  SELECT * FROM C WHERE  C.FIRST_SCORE>C.SECOND_SCORE

    ##方式3  with a as(select * from SCORE where C_ID='01'),  b as(select * from SCORE where C_ID='02'),  c as (select * from student as s left join a on s.S_ID=a.S_ID left join b on s.S_ID=b.S_ID where a.S_SCORE>b.S_SCORE)  select * from c; ##方式4 SELECT s.* FROM student s, (SELECT sid, score FROM sc WHERE cid = '01') t1, (SELECT sid, score FROM sc WHERE cid = '02') t2 WHERE s.sid = t1.sid AND t1.sid = t2.sid AND t1.score > t2.score;

    2. 查询"01"课程比"02"课程成绩低的学生的信息及课程分数:

     with a as(select * from SCORE where C_ID='01'),  b as(select * from SCORE where C_ID='02'),  c as (select * from student as s left join a on s.S_ID=a.S_ID left join b on s.S_ID=b.S_ID where a.S_SCORE<b.S_SCORE)  select * from c;

     3. 查询平均成绩大于等于60分的同学的学生编号和学生姓名和平均成绩:  with b as(select  b.S_ID, b.S_NAME, ROUND(avg(a.S_SCORE),2) as score  from score as a  left join student as b on a.S_ID=b.S_ID  group by  b.S_ID, b.S_NAME)  select * from b where score>60;

     4. 查询平均成绩小于60分的同学的学生编号和学生姓名和平均成绩:– (包括有成绩的和无成绩的)

     with b as(select  b.S_ID, b.S_NAME, ROUND(avg(if(a.S_SCORE is null,0,a.S_SCORE)),2) as score  from student as b left join score as a  on a.S_ID=b.S_ID  group by  b.S_ID, b.S_NAME)  select * from b where score<60;

     SELECT B.S_ID,B.S_NAME,ROUND(IF(AVG(A.S_SCORE) IS NULL,0,AVG(A.S_SCORE)),2) AS AVG_SCORE   FROM SCORE A RIGHT JOIN STUDENT B ON A.S_ID = B.S_ID GROUP BY B.S_ID,B.S_NAME HAVING IF(AVG(A.S_SCORE) IS NULL,0,AVG(A.S_SCORE))<60 

    5. 查询所有同学的学生编号、学生姓名、选课总数、所有课程的总成绩:

    select  b.S_ID, b.S_NAME,count(a.C_ID), ROUND(sum(if(a.S_SCORE is null,0,a.S_SCORE)),2) as score  from student as b left join score as a  on a.S_ID=b.S_ID   group by b.S_ID, b.S_NAME;

     SELECT S.S_ID,S.S_NAME,SIZE(COLLECT_SET(C.C_ID)) CHANGE_COURSE_SUM,IF(SUM(C.S_SCORE) IS NULL,0, SUM(C.S_SCORE)) SUM_SCORE   FROM STUDENT S LEFT JOIN SCORE C ON S.S_ID = C.S_ID GROUP BY S.S_ID,S.S_NAME

    6. 查询"李"姓老师的数量:

    select count(*) from TEACHER where T_NAME like '李%' ;

    7. 查询学过"张三"老师授课的同学的信息:

    with a as(select * from TEACHER where T_NAME='张三'), b as(select s.* from student as s left join score as sc on s.S_ID=sc.S_ID left join course as c on sc.C_ID=c.c_ID right join a on c.T_ID=a.T_ID ) select b.s_id,b.S_NAME,count(*) from b group by b.s_id,b.S_NAME;

    8. 查询没学过"张三"老师授课的同学的信息:

    with a as(select * from TEACHER where T_NAME ='张三'), b as(select s.*,a.T_NAME from student as s left join score as sc on s.S_ID=sc.S_ID left join course as c on sc.C_ID=c.c_ID right join a on c.T_ID=a.T_ID ) select st.* from (select b.s_id,b.S_NAME,count(*) from b  group by b.s_id,b.S_NAME) as d right join student as st on d.s_id=st.s_id where d.S_ID is null;

    WITH T AS(   SELECT C.C_ID FROM COURSE C LEFT JOIN TEACHER T ON C.T_ID = T.T_ID WHERE T.T_NAME = '张三' ), T1 AS (  SELECT DISTINCT S.S_ID FROM T LEFT JOIN SCORE S ON T.C_ID = S.C_ID   ) SELECT S.* FROM T1 RIGHT JOIN STUDENT S ON  S.S_ID = T1.S_ID WHERE T1.S_ID IS NULL

    9. 查询学过编号为"01"并且也学过编号为"02"的课程的同学的信息:

    with a as(select * from score where c_id='01'), b as (select * from score where c_id ='02'), c as (select st.* from student as st right join a on st.s_id=a.s_id right join b on st.s_id=b.s_id) select * from c;

    10. 查询学过编号为"01"但是没有学过编号为"02"的课程的同学的信息:

    with a as(select * from score where c_id='01'), b as (select * from score where c_id ='02'), c as (select * from student as st left join a on st.s_id=a.s_id left join b on st.s_id=b.s_id where b.s_id is null and a.s_id is not null) select * from c;

    WITH A AS(  SELECT STU.* FROM SCORE A LEFT JOIN STUDENT STU ON A.S_ID = STU.S_ID WHERE A.C_ID ='01' ), B AS(   SELECT STU.* FROM SCORE A LEFT JOIN STUDENT STU ON A.S_ID = STU.S_ID WHERE A.C_ID ='02' ) SELECT A.* FROM A LEFT JOIN B ON A.S_ID = B.S_ID WHERE B.S_ID IS NULL

    11. 查询没有学全所有课程的同学的信息:  with a as(select count(*) count from course),  b as(select st.s_id,count(*) count from student as st left join score sc on st.s_id=sc.s_id group by st.s_id),  c as(select * from  b left join a on 1=1 where b.count<a.count)  select st.* from student st inner join c on c.s_id=st.s_id;

    12. 查询至少有一门课与学号为"01"的同学所学相同的同学的信息:

    with a as(select * from score where s_id='01'), b as(select sc.s_id from score as sc  left join a on sc.c_id=a.c_id where sc.s_id!='01' group by sc.s_id) select * from student as st right join b on st.s_id=b.s_id;

    13. 查询和"01"号的同学学习的课程完全相同的其他同学的信息:

    with a as(select s_id,concat_ws(',',COLLECT_SET(c_id)) as cids from score  group by s_id), b as(select * from a where s_id='01' ), c as(select st.* from b left join a on a.cids=b.cids left join student st on a.s_id=st.s_id where st.s_id!='01') select * from c;

    14. 查询没学过"张三"老师讲授的任一门课程的学生姓名:

    with a as(select co.* from teacher te left join course co on te.t_id=co.t_id where te.t_name ='张三'), b as(select sc.s_id from score sc right join a on sc.c_id=a.c_id group by s_id) select st.* from student st left join b on st.s_id=b.s_id where b.s_id is null;

    15. 查询两门及其以上不及格课程的同学的学号,姓名及其平均成绩:

    with t1 as(select s_id,round( avg(S_SCORE),2 ) avgs from score group by s_id), t2 as(select s_id,S_SCORE,if(S_SCORE>=60,0,1) rank from score), t3 as(select s_id,sum(rank) rank from t2 group by s_id), t4 as(select * from t3 where rank>=2) select st.*,t1.avgs from t4 left join t1 on t4.s_id=t1.s_id left join student st on t1.s_id=st.s_id;

    with t1 as(select s_id,round(avg(s_score),2) from score where s_score<60 group by s_id having count(s_id)>1) select * from t1 left join student on t1.s_id=student.s_id;

    16. 检索"01"课程分数小于60,按分数降序排列的学生信息:

    select st.* from score left join student st on score.s_id=st.s_id where c_id='01' and s_score<60 order by s_score desc;

    17. 按平均成绩从高到低显示所有学生的所有课程的成绩以及平均成绩:

    with t1 as(select s_id,c_id,s_score,round(avg(s_score) over (partition by s_id),2) avgScore from score) select st.s_name,t1.c_id,t1.s_score,t1.avgScore from t1 left join student st on t1.s_id=st.s_id order by t1.avgScore desc ;

    WITH B AS (   SELECT C.C_NAME ,S.* FROM COURSE C RIGHT JOIN SCORE S ON S.C_ID = C.C_ID      ) SELECT S.S_NAME, MAX(CASE WHEN B.C_NAME='英语' THEN B.S_SCORE ELSE 0 END) AS `英语`, MAX(CASE WHEN B.C_NAME='数学' THEN B.S_SCORE ELSE 0 END) AS `数学`, MAX(CASE WHEN B.C_NAME='语文' THEN B.S_SCORE ELSE 0 END) AS `语文`, #sum(if) ROUND(IF(AVG(B.S_SCORE) IS NULL,0,AVG(B.S_SCORE)),2) AVG_SCORE FROM B RIGHT JOIN STUDENT S ON S.S_ID = B.S_ID GROUP BY S.S_NAME ORDER BY AVG_SCORE DESC

    18. 查询各科成绩最高分、最低分和平均分:以如下形式显示:课程ID,课程name,最高分,最低分,平均分,及格率,中等率,优良率,优秀率:

    select   co.c_id,co.c_name, max(sc.s_score) max, min(sc.s_score) min, round(avg(sc.s_score),2) avg, round(sum(case when sc.s_score>=60 then 1 else 0 end)/count(*),2) from score sc left join course co on sc.c_id=co.c_id group by co.c_id,co.c_name;

    19. 按各科成绩进行排序,并显示排名:

    select co.c_id,co.c_name,sc.s_score, rank() over(partition by co.c_id order by sc.s_score desc) rank from score sc left join course co on sc.c_id=co.c_id order by  co.c_id,co.c_name;

    20. 查询学生的总成绩并进行排名:

    with t1 as(select sc.s_id,sum(sc.s_score) scoreSum from score sc group by sc.s_id) select t1.s_id,t1.scoreSum,rank() over(order by t1.scoreSum desc) from t1;

    21. 查询不同老师所教不同课程平均分从高到低显示:

    with t1 as(select co.t_id,round(avg(sc.s_score),2) as scoreAvg from score sc left join course co on sc.c_id=co.c_id group by co.t_id) select * from t1 order by scoreAvg desc;

    22. 查询所有课程的成绩第2名到第3名的学生信息及该课程成绩: 

    with t1 as(select s_id,c_id,S_SCORE,ROW_NUMBER() over(partition by c_id order by S_SCORE desc) as rank from score order by c_id,S_SCORE) select * from t1 where (rank>=2 and rank <=3);

    23. 统计各科成绩各分数段人数:课程编号,课程名称,[100-85],[85-70],[70-60],[0-60]及所占百分比 #between and 左右都是闭区间,慎用 select c_id, sum(if(S_SCORE between 0 and 60,1,0)) as re11, sum(if(S_SCORE between 60 and 70,1,0)) as re12, sum(if(S_SCORE between 70 and 85,1,0)) , sum(if(S_SCORE between 85 and 100,1,0)), round(sum(if(S_SCORE between 0 and 60,1,0))/count(c_id),2), round(sum(if(S_SCORE between 60 and 70,1,0))/count(c_id),2), round(sum(if(S_SCORE between 70 and 85,1,0))/count(c_id),2) , round(sum(if(S_SCORE between 85 and 100,1,0))/count(c_id),2)  from score group by  c_id;

    24. 查询学生平均成绩及其名次:

    with t1 as(select s_id,round(avg(S_SCORE),2) as scoreAvg from score group by s_id), t2 as(select *,rank() over(order by  scoreAvg desc) rank from t1) select * from t2 order by rank;

    25. 查询各科成绩前三名的记录

    with t1 as(select s_id,c_id,S_SCORE,ROW_NUMBER() over(partition by c_id order by S_SCORE desc) as rank from score order by c_id,S_SCORE) select * from t1 where (rank <=3);

    26. 查询每门课程被选修的学生数:

    select c_id,count(*) from score group by c_id;

    27. 查询出只有两门课程的全部学生的学号和姓名:

    with t1 as(select s_id,count(*) count from score group by s_id) select st.* from student st right join t1 on st.s_id=t1.s_id where t1.count=2;

    28. 查询男生、女生人数: select  sum(if(S_SEX='男',1,0)), sum(if(S_SEX='女',1,0)), count(*)  from student ;

     select S_SEX,count(*) from student group by S_SEX;

     29. 查询名字中含有"风"字的学生信息:  select * from student where locate('风',s_name)>0;

    30. 查询同名同性学生名单,并统计同名人数: #方法一 with t1 as(select t1.* from student t1 left join student t2 on t1.s_name=t2.s_name where t1.s_id != t2.s_id), t2 as(select * from t1 group by s_id), t3 as(select count(*) from t2) select * from t3; #方二 WITH A AS (   SELECT *,COUNT(S_NAME) OVER (PARTITION BY S_NAME,S_SEX ) COUNT_S_NAME FROM STUDENT ) SELECT * FROM A WHERE COUNT_S_NAME>1

    31. 查询1990年出生的学生名单:

    select * from student where date_format(s_birth,'yyyy')='1990'; select * from student where YEAR(s_birth)='1990';

    32. 查询每门课程的平均成绩,结果按平均成绩降序排列,平均成绩相同时,按课程编号升序排列:

    SELECT C_ID,ROUND(AVG(S_SCORE),2) AS AVG_SCORE FROM SCORE GROUP BY C_ID ORDER BY AVG_SCORE DESC ,C_ID ASC 

    33. 查询平均成绩大于等于85的所有学生的学号、姓名和平均成绩:

    with t1 as(SELECT S_ID,AVG(S_SCORE) AS AVG_SCORE FROM SCORE GROUP BY S_ID having AVG_SCORE >= 85) select S_ID,round(AVG_SCORE,2) from t1;

    # mysql 可以 hive 不可以 SELECT S_ID,round(AVG(S_SCORE),2) AS AVG_SCORE FROM SCORE GROUP BY S_ID having AVG_SCORE >= 85

    34. 查询课程名称为"数学",且分数低于60的学生姓名和分数:

    select st.s_name,sc.s_score from SCORE sc left join student st on sc.s_id=st.s_id where c_id='02' and sc.s_score<60;

    35. 查询所有学生的课程及分数情况:

    select st.s_name,co.c_name,sc.s_score from student st left join SCORE sc on sc.s_id=st.s_id left join course co on sc.c_id=co.c_id;

    36. 查询任何一门课程成绩在70分以上的学生姓名、课程名称和分数:

    select st.s_name,co.c_name,sc.s_score from student st left join SCORE sc on sc.s_id=st.s_id left join course co on sc.c_id=co.c_id where sc.s_score>=70;

    37. 查询课程不及格的学生: with t1 as( select st.s_name,co.c_name,sc.s_score from student st left join SCORE sc on sc.s_id=st.s_id left join course co on sc.c_id=co.c_id where sc.s_score<60) select s_name from t1 group by s_name;

    38. 查询课程编号为01且课程成绩在80分以上的学生的学号和姓名:

    select st.s_name,sc.s_score from SCORE sc left join student st on sc.s_id=st.s_id where c_id='01' and sc.s_score>=80;

    39. 求每门课程的学生人数:

    select c_id,count(*) from SCORE group by c_id;

    40. 查询选修"张三"老师所授课程的学生中,成绩最高的学生信息及其成绩:

    select s_id,s_score from score where c_id='02' order by s_score desc limit 1;

    41.  每天更新十条

    Processed: 0.015, SQL: 9