Hive综合应用案例——用户学历查询

第一关 查询一个用户从出生到现在的总天数

---------- 禁止修改 ----------
drop database if exists mydb cascade;
---------- 禁止修改 ----------


---------- begin ----------
---创建mydb数据库
CREATE DATABASE mydb;

---使用mydb数据库
USE mydb;

---创建表usertab
CREATE TABLE usertab (
    id INT, 
    sex STRING,
    time STRING,
    education STRING,
    occupation STRING,
    income STRING,
    area STRING,
    desired_area STRING,
    city_countryside STRING 
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ',';


---导入数据：/root/data.txt
LOAD DATA LOCAL INPATH '/root/data.txt' INTO TABLE usertab;


---查询每一个用户从出生到现在的总天数
SELECT 
    id,
    DATEDIFF('2019-06-10', TO_DATE(REPLACE(time, '/', '-'))) AS days_since_birth
FROM usertab;


---------- end ----------

第二关 同一个地区相同的教育程度的最高收入

---------- 禁止修改 ----------
drop database if exists mydb cascade;
---------- 禁止修改 ----------


---------- begin ----------
---创建mydb数据库
CREATE DATABASE mydb;

---使用mydb数据库
USE mydb;

---创建表usertab1
CREATE TABLE usertab1 (
    id INT, 
    sex STRING,
    time STRING,
    education STRING,
    occupation STRING,
    income INT,
    area STRING,
    desired_area STRING,
    city_countryside STRING 
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ',';

---导入数据：/root/data1.txt
LOAD DATA LOCAL INPATH '/root/data1.txt' INTO TABLE usertab1;

--同一个地区相同的教育程度的最高收入
SELECT 
    area, 
    education, 
    MAX(income) AS max_income
FROM usertab1
GROUP BY area, education
ORDER BY area, 
         CASE education 
             WHEN '专科' THEN 1
             WHEN '本科' THEN 2
             WHEN '硕士' THEN 3
             ELSE 4
         END;

---------- end ----------

第三关 统计各级学历所占总人数百分比

---------- 禁止修改 ----------
drop database if exists mydb cascade;
set hive.mapred.mode=nonstrict;
---------- 禁止修改 ----------
 
 
---------- begin ----------
----创建mydb数据库
CREATE DATABASE mydb;
 
---使用mydb数据库
USE mydb;
 
---创建表user
CREATE TABLE usertab2 (
    id INT, 
    sex STRING,
    time STRING,
    education STRING,
    occupation STRING,
    income STRING,
    area STRING,
    desired_area STRING,
    city_countryside STRING 
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ',';
 
---导入数据：/root/data.txt
LOAD DATA LOCAL INPATH '/root/data.txt' INTO TABLE usertab2;
 
--查询
SELECT 
    CONCAT(ROUND(COUNT(*) * 100.0 / SUM(COUNT(*)) OVER(), 2), '%') AS percentage,
    education
FROM usertab2
GROUP BY education
ORDER BY education;
---------- end ----------