统计分钟级别的视频在线用户数

1、原始数据如下：

uid  vid  starttime  endtime
select 'aa' as uid,'v00l' as vid,'2023-10-25 12:00' as starttime,'2023-10-2512:15' as endtime 
union

select 'bb' as uid,'v002' as vid,'2023-10-25 12:05' as starttime,'2023-10-25 12:19' as endtime

结果如下：

 

2、需求分析

• 将用户看视频的时间拆解到分钟
• 现在能算出用户看视频的时长(分钟)，并且知道用户看视频的开始时间，如果拆解到分钟级别观看记录呢？
• 肯定涉及到列转行，但是如何拆分成 时长单位(分钟) 个 分钟级别观看记录行？ 

3、完整代码如下

3.1、实现一：repeat+explode+row_number()over(partitions by )

--step6、统计每分钟看视频的用户数，并按照时间排序
select 
    each_online_minute,from_unixtime(each_online_minute,'yyyy-MM-dd hh:mm') as minute_lab bel,count(distinct uid) online_uid_cnt 
from
(--step5、形成每个用户看视频的分钟级别的观看记录
   select
        uid,vid,starttime,starttimestamp, endtime, endtimestamp,min_cnt
        ,row_number()over(part: ition by uid,vid,starttime order by endtimestamp) rk
        ,starttimestamp+60*row_number()over(partition by uid,vid,starttime order by endtimest tamp) as each_online_minute 
   
   from
   (--step4、explode列炸裂
       select uid,vid, starttime,starttimestamp ,endtime,endtimestamp, min_cnt,new_repeat 
       from
       (--step3、用repeat产生持续时长(分钟) 个数组
           select uid,vid,starttime,starttimestamp,endtime,endtimestamp,min_cnt,repeat('a,',mir n_cnt-1) as repeat_str 
           from
           (--step2、转化为时间戳，且计算看视频持续时长(分钟)
              select 
                 uid
                 ,vid
                 ,starttime
                 ,unix_timestamp(starttime,'yyyy-MM-dd hh:mm' ) as starttimestamp
                 ,endtime
                 ,unix_timestamp(endtime, 'yyyy-MM-dd hh:mm' ) as endtimestamp
                 ,(unix_timestamp(endtime,'yyyy-MM-dd hh:mm')-unix_timestamp(starttime,'yyyy-Mr M-dd hh:mm'))/60 as min_cnt 
              from
              (--step1、获取原始数据
                  select 'aa' as uid,'v0ol' as vid,'2023-10-25 12:00' as starttime,'2023-10-2512:15' as endtime 
                  union
                  select 'bb' as uid,'v0o2' as vid,'2023-10-25 12:05' as starttime,'2023-10-25 12::19' as endtime
              )tb_base
           )tb_tmp
       )tb_final
       lateral view explode(split(repeat_str,',')) tb_tmp as new_repeat
   )tb_outer
) tb
group by each_online_minute
order by each_online_minute asc

3.2、实现二:  repeat+posexplode

--step6、统计每分钟看视频的用户数，并按照时间排序
select 
    each_online_minute,from_unixtime(each_online_minute,'yyyy-MM-dd hh:mm') as minute_lab bel,count(distinct uid) online_uid_cnt 
from
(--step5、形成每个用户看视频的分钟级别的观看记录
   select
        uid,vid,starttime,starttimestamp, endtime, endtimestamp,min_cnt
        ,starttimestamp+60*repeat_pos as each_online_minute 
   
   from
   (--step4、explode列炸裂
       select uid,vid, starttime,starttimestamp ,endtime,endtimestamp, min_cnt,new_repeat,repeat_pos 
       from
       (--step3、用repeat产生持续时长(分钟) 个数组
           select uid,vid,starttime,starttimestamp,endtime,endtimestamp,min_cnt,repeat('a,',mir n_cnt-1) as repeat_str 
           from
           (--step2、转化为时间戳，且计算看视频持续时长(分钟)
              select 
                 uid
                 ,vid
                 ,starttime
                 ,unix_timestamp(starttime,'yyyy-MM-dd hh:mm' ) as starttimestamp
                 ,endtime
                 ,unix_timestamp(endtime, 'yyyy-MM-dd hh:mm' ) as endtimestamp
                 ,(unix_timestamp(endtime,'yyyy-MM-dd hh:mm')-unix_timestamp(starttime,'yyyy-Mr M-dd hh:mm'))/60 as min_cnt 
              from
              (--step1、获取原始数据
                  select 'aa' as uid,'v0ol' as vid,'2023-10-25 12:00' as starttime,'2023-10-2512:15' as endtime 
                  union
                  select 'bb' as uid,'v0o2' as vid,'2023-10-25 12:05' as starttime,'2023-10-25 12::19' as endtime
              )tb_base
           )tb_tmp
       )tb_final
       lateral view posexplode(split(repeat_str,',')) tb_tmp as repeat_pos,new_repeat
   )tb_outer
) tb
group by each_online_minute
order by each_online_minute asc

4、相关hive函数介绍

4.1、reverse返回字符串反序

       用法：reverse('foobar')参数类型string，返回值string，例如：

        select reverse('foobar')
      --返回：raboof

4.2、space返回指定n个空格字符串

用法：space(10)参数类型int，返回值string   例如：

select space(10)
--返回：'         '

4.3、repeat返回字符串重复n次后的字符串

用法：repeat('a',10)   例如：

select repeat('a',10)
--返回：'aaaaaaaaaa'

 4.3、split将字符串按指定分隔符，拆分为数组 用法：

select split('a,b,c,d',',')
--返回：["a","b","c","d"]