每日HiveSQL_查询每个用户多个指标_11

D(自律版)

已于 2023-12-03 16:54:13 修改

阅读量181

点赞数 4

分类专栏： HiveSQL习题集锦文章标签： hive 数据仓库大数据

于 2023-12-03 16:52:35 首次发布

本文链接：https://blog.csdn.net/m0_64893323/article/details/134766658

版权

HiveSQL习题集锦专栏收录该内容

15 篇文章 3 订阅

订阅专栏

1.从用户登录明细表（user_login_detail）和订单信息表（order_info）中查询每个用户的注册日期（首次登录日期）、总登录次数以及其在2021年的登录次数、订单数和订单总额

需求结果

2.所用到的表和数据

--订单信息表
create table order_info
(
    `order_id`     string COMMENT '订单id',
    `user_id`      string COMMENT '用户id',
    `create_date`  string COMMENT '下单日期',
    `total_amount` decimal(16, 2) COMMENT '订单总金额'
) COMMENT '订单表'
    ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

--数据装载
insert overwrite table order_info
values ('1', '101', '2021-09-27', 29000.00),
       ('2', '101', '2021-09-28', 70500.00),
       ('3', '101', '2021-09-29', 43300.00),
       ('4', '101', '2021-09-30', 860.00),
       ('5', '102', '2021-10-01', 46180.00),
       ('6', '102', '2021-10-01', 50000.00),
       ('7', '102', '2021-10-01', 75500.00),
       ('8', '102', '2021-10-02', 6170.00),
       ('9', '103', '2021-10-02', 18580.00),
       ('10', '103', '2021-10-02', 28000.00),
       ('11', '103', '2021-10-02', 23400.00),
       ('12', '103', '2021-10-03', 5910.00),
       ('13', '104', '2021-10-03', 13000.00),
       ('14', '104', '2021-10-03', 69500.00),
       ('15', '104', '2021-10-03', 2000.00),
       ('16', '104', '2021-10-03', 5380.00),
       ('17', '105', '2021-10-04', 6210.00),
       ('18', '105', '2021-10-04', 68000.00),
       ('19', '105', '2021-10-04', 43100.00),
       ('20', '105', '2021-10-04', 2790.00),
       ('21', '106', '2021-10-04', 9390.00),
       ('22', '106', '2021-10-05', 58000.00),
       ('23', '106', '2021-10-05', 46600.00),
       ('24', '106', '2021-10-05', 5160.00),
       ('25', '107', '2021-10-05', 55350.00),
       ('26', '107', '2021-10-05', 14500.00),
       ('27', '107', '2021-10-06', 47400.00),
       ('28', '107', '2021-10-06', 6900.00),
       ('29', '108', '2021-10-06', 56570.00),
       ('30', '108', '2021-10-06', 44500.00),
       ('31', '108', '2021-10-07', 50800.00),
       ('32', '108', '2021-10-07', 3900.00),
       ('33', '109', '2021-10-07', 41480.00),
       ('34', '109', '2021-10-07', 88000.00),
       ('35', '109', '2020-10-08', 15000.00),
       ('36', '109', '2020-10-08', 9020.00),
       ('37', '1010', '2020-10-08', 9260.00),
       ('38', '1010', '2020-10-08', 12000.00),
       ('39', '1010', '2020-10-08', 23900.00),
       ('40', '1010', '2020-10-08', 6790.00);
--登录明细表
CREATE TABLE user_login_detail
(
    `user_id`    string comment '用户id',
    `ip_address` string comment 'ip地址',
    `login_ts`   string comment '登录时间',
    `logout_ts`  string comment '登出时间'
) COMMENT '用户登录明细表'
    ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

--数据装载
INSERT overwrite table user_login_detail
VALUES ('101', '180.149.130.161', '2021-09-21 08:00:00', '2021-09-27 08:30:00'),
       ('101', '180.149.130.161', '2021-09-27 08:00:00', '2021-09-27 08:30:00'),
       ('101', '180.149.130.161', '2021-09-28 09:00:00', '2021-09-28 09:10:00'),
       ('101', '180.149.130.161', '2021-09-29 13:30:00', '2021-09-29 13:50:00'),
       ('101', '180.149.130.161', '2021-09-30 20:00:00', '2021-09-30 20:10:00'),
       ('102', '120.245.11.2', '2021-09-22 09:00:00', '2021-09-27 09:30:00'),
       ('102', '120.245.11.2', '2021-10-01 08:00:00', '2021-10-01 08:30:00'),
       ('102', '180.149.130.174', '2021-10-01 07:50:00', '2021-10-01 08:20:00'),
       ('102', '120.245.11.2', '2021-10-02 08:00:00', '2021-10-02 08:30:00'),
       ('103', '27.184.97.3', '2021-09-23 10:00:00', '2021-09-27 10:30:00'),
       ('103', '27.184.97.3', '2021-10-03 07:50:00', '2021-10-03 09:20:00'),
       ('104', '27.184.97.34', '2021-09-24 11:00:00', '2021-09-27 11:30:00'),
       ('104', '27.184.97.34', '2021-10-03 07:50:00', '2021-10-03 08:20:00'),
       ('104', '27.184.97.34', '2021-10-03 08:50:00', '2021-10-03 10:20:00'),
       ('104', '120.245.11.89', '2021-10-03 08:40:00', '2021-10-03 10:30:00'),
       ('105', '119.180.192.212', '2021-10-04 09:10:00', '2021-10-04 09:30:00'),
       ('106', '119.180.192.66', '2021-10-04 08:40:00', '2021-10-04 10:30:00'),
       ('106', '119.180.192.66', '2021-10-05 21:50:00', '2021-10-05 22:40:00'),
       ('107', '219.134.104.7', '2021-09-25 12:00:00', '2021-09-27 12:30:00'),
       ('107', '219.134.104.7', '2021-10-05 22:00:00', '2021-10-05 23:00:00'),
       ('107', '219.134.104.7', '2021-10-06 09:10:00', '2021-10-06 10:20:00'),
       ('107', '27.184.97.46', '2021-10-06 09:00:00', '2021-10-06 10:00:00'),
       ('108', '101.227.131.22', '2021-10-06 09:00:00', '2021-10-06 10:00:00'),
       ('108', '101.227.131.22', '2021-10-06 22:00:00', '2021-10-06 23:00:00'),
       ('109', '101.227.131.29', '2021-09-26 13:00:00', '2021-09-27 13:30:00'),
       ('109', '101.227.131.29', '2021-10-06 08:50:00', '2021-10-06 10:20:00'),
       ('109', '101.227.131.29', '2021-10-08 09:00:00', '2021-10-08 09:10:00'),
       ('1010', '119.180.192.10', '2021-09-27 14:00:00', '2021-09-27 14:30:00'),
       ('1010', '119.180.192.10', '2021-10-09 08:50:00', '2021-10-09 10:20:00');

3.答案

解析：基本功考察，涉及多表join、分组聚合

3.1从用户登录表中得到每个用户的首次登录的时间以及总的登录的次数

select user_id,
       count(login_ts)              total_login_count,
       min(substr(login_ts, 0, 10)) register_date
from user_login_detail
group by user_id;

运行结果

3.2从用户登录表中得到每个用户2021年的登录次数

select user_id,
       count(login_ts) login_count_2021
from user_login_detail
where year(login_ts) = '2021'
group by user_id;

运行结果

3.3从订单表中得到每个用户2021年的销量及销售额

select user_id,
       count(order_id)   order_count_2021,
       sum(total_amount) order_amount_2021
from order_info
where year(create_date) = '2021'
group by user_id;

运行结果

3.4上述三表关联得到结果

with tlc_rd as (
    select user_id,
           count(login_ts)              total_login_count,
           min(substr(login_ts, 0, 10)) register_date
    from user_login_detail
    group by user_id
),
     lc_2021 as (
         select user_id,
                count(login_ts) login_count_2021
         from user_login_detail
         where year(login_ts) = '2021'
         group by user_id
     ),
     order_2021_ca as (
         select user_id,
                count(order_id)   order_count_2021,
                sum(total_amount) order_amount_2021
         from order_info
         where year(create_date) = '2021'
         group by user_id
     )
select order_2021_ca.user_id,
       register_date,
       total_login_count,
       login_count_2021,
       order_count_2021,
       order_amount_2021
from order_2021_ca
         left join tlc_rd on order_2021_ca.user_id = tlc_rd.user_id
         left join lc_2021 on order_2021_ca.user_id = lc_2021.user_id;

运行结果