牛客网SQL进阶135 ：每个6/7级用户活跃情况

news2024/11/15 8:25:58

每个67级用户活跃情况_牛客题霸_牛客网

0 问题描述

基于用户信息表user_info、、试卷作答记录表exam_record、题目练习记录表practice_record，统计 每个6/7级用户总活跃月份数、2021年活跃天数、2021年试卷作答活跃天数、2021年答题活跃天数，结果按照总活跃月份数、2021年活跃天数降序排序。

1 数据准备

drop table if exists examination_info,user_info,exam_record,practice_record;
CREATE TABLE examination_info (
    id int PRIMARY KEY AUTO_INCREMENT COMMENT '自增ID',
    exam_id int UNIQUE NOT NULL COMMENT '试卷ID',
    tag varchar(32) COMMENT '类别标签',
    difficulty varchar(8) COMMENT '难度',
    duration int NOT NULL COMMENT '时长',
    release_time datetime COMMENT '发布时间'
)CHARACTER SET utf8 COLLATE utf8_general_ci;
 
CREATE TABLE user_info (
    id int PRIMARY KEY AUTO_INCREMENT COMMENT '自增ID',
    uid int UNIQUE NOT NULL COMMENT '用户ID',
    `nick_name` varchar(64) COMMENT '昵称',
    achievement int COMMENT '成就值',
    level int COMMENT '用户等级',
    job varchar(32) COMMENT '职业方向',
    register_time datetime COMMENT '注册时间'
)CHARACTER SET utf8 COLLATE utf8_general_ci;
 
CREATE TABLE practice_record (
    id int PRIMARY KEY AUTO_INCREMENT COMMENT '自增ID',
    uid int NOT NULL COMMENT '用户ID',
    question_id int NOT NULL COMMENT '题目ID',
    submit_time datetime COMMENT '提交时间',
    score tinyint COMMENT '得分'
)CHARACTER SET utf8 COLLATE utf8_general_ci;
 
CREATE TABLE exam_record (
    id int PRIMARY KEY AUTO_INCREMENT COMMENT '自增ID',
    uid int NOT NULL COMMENT '用户ID',
    exam_id int NOT NULL COMMENT '试卷ID',
    start_time datetime NOT NULL COMMENT '开始时间',
    submit_time datetime COMMENT '提交时间',
    score tinyint COMMENT '得分'
)CHARACTER SET utf8 COLLATE utf8_general_ci;
 
INSERT INTO user_info(uid,`nick_name`,achievement,level,job,register_time) VALUES
  (1001, '牛客1号', 3100, 7, '算法', '2020-01-01 10:00:00'),
  (1002, '牛客2号', 2300, 7, '算法', '2020-01-01 10:00:00'),
  (1003, '牛客3号', 2500, 7, '算法', '2020-01-01 10:00:00'),
  (1004, '牛客4号', 1200, 5, '算法', '2020-01-01 10:00:00'),
  (1005, '牛客5号', 1600, 6, 'C++', '2020-01-01 10:00:00'),
  (1006, '牛客6号', 2000, 6, 'C++', '2020-01-01 10:00:00');
 
INSERT INTO examination_info(exam_id,tag,difficulty,duration,release_time) VALUES
  (9001, 'SQL', 'hard', 60, '2021-09-01 06:00:00'),
  (9002, 'C++', 'hard', 60, '2021-09-01 06:00:00'),
  (9003, '算法', 'medium', 80, '2021-09-01 10:00:00');
 
INSERT INTO practice_record(uid,question_id,submit_time,score) VALUES
(1001, 8001, '2021-08-02 11:41:01', 60),
(1002, 8001, '2021-09-02 19:30:01', 50),
(1002, 8001, '2021-09-02 19:20:01', 70),
(1002, 8002, '2021-09-02 19:38:01', 70),
(1004, 8001, '2021-08-02 19:38:01', 70),
(1004, 8002, '2021-08-02 19:48:01', 90),
(1001, 8002, '2021-08-02 19:38:01', 70),
(1004, 8002, '2021-08-02 19:48:01', 90),
(1004, 8002, '2021-08-02 19:58:01', 94),
(1004, 8003, '2021-08-02 19:38:01', 70),
(1004, 8003, '2021-08-02 19:48:01', 90),
(1004, 8003, '2021-08-01 19:38:01', 80);
 
INSERT INTO exam_record(uid,exam_id,start_time,submit_time,score) VALUES
(1001, 9001, '2021-09-01 09:01:01', '2021-09-01 09:31:00', 81),
(1002, 9002, '2021-09-01 12:01:01', '2021-09-01 12:31:01', 81),
(1003, 9001, '2021-09-01 19:01:01', '2021-09-01 19:40:01', 86),
(1003, 9002, '2021-09-01 12:01:01', '2021-09-01 12:31:51', 89),
(1004, 9001, '2021-09-01 19:01:01', '2021-09-01 19:30:01', 85),
(1005, 9002, '2021-09-01 12:01:01', '2021-09-01 12:31:02', 85),
(1006, 9003, '2021-09-07 10:01:01', '2021-09-07 10:21:01', 84),
(1006, 9001, '2021-09-07 10:01:01', '2021-09-07 10:21:01', 80);

2 数据分析


select
    ui.uid  as uid,
	--每个6/7级用户总活跃月份数
    count(distinct act_month) as act_month_total,
	--2021年活跃天数 (总活跃天数 = 试卷作答活跃天数 + 答题活跃天数) 
    count(distinct case when year(act_time) = 2021 then act_day end) as act_days_2021,
	--2021年 试卷作答活跃天数
    count(distinct case when year(act_time) = 2021 and tag = 'exam' then act_day end) as act_days_2021_exam,
	--2021年 答题活跃天数，
    count(distinct case when year(act_time) = 2021 and tag = 'question' then act_day end) as act_days_2021_question		
from user_info ui 
 left join 
   ( select 
         uid,
         start_time as act_time,
         date_format(start_time, '%Y%m') as act_month,
         date_format(start_time, '%Y%m%d') as act_day,
         'exam' as tag
     from exam_record
     union all
     select 
          uid,
          submit_time as act_time,
          date_format(submit_time, '%Y%m') as act_month,
          date_format(submit_time, '%Y%m%d') as act_day,
          'question' as tag
     from practice_record
   )ep 
on ui.uid = ep.uid
where ui.level >= 6
group by ui.uid 
 order by act_month_total desc, act_days_2021 desc;

思路分析：

step1: 试卷以开始答题时间作为活跃时间，只要用户答题了就代表活跃，不管有没有完成。先筛选出用户ID，开始答题时间作为活跃时间，开始答题的月份作为活跃月份，开始答题的日期作为活跃天，标记tag为'exam'
step2：题目以提交时间作为活跃时间，先筛选出用户ID，提交时间作为活跃时间，提交的月份作为活跃月份，提交的日期作为活跃天，标记tag为'question'
step3：将上述两个筛选结果合并作为新表ep
step4：活跃信息在新表ep 中，用户等级信息在user_info中，因此在表user_info的右边去连接新表，以uid为准。left join...on...
step5：从连接后的表中筛选出等级大于等于6的用户，然后统计每个用户的活跃信息：