【hive】关于用户留存率的计算

    SET mapreduce.job.queuename=xxx;
    SET mapreduce.job.name=xxx;
    set mapreduce.job.reduces=19;
            select ‘日期‘, ‘注册用户数‘, ‘次日留存率‘, ‘2日留存率‘, ‘3日留存率‘,  dim_date
                ,total_cnt
                ,concat_ws(‘% | ‘, cast(round(dif_1cnt*100/total_cnt, 2) as string), cast(dif_1cnt as string))
                ,concat_ws(‘% | ‘, cast(round(dif_2cnt*100/total_cnt, 2) as string), cast(dif_2cnt as string))
                ,concat_ws(‘% | ‘, cast(round(dif_3cnt*100/total_cnt, 2) as string), cast(dif_3cnt as string))
                ,concat_ws(‘% | ‘, cast(round(dif_4cnt*100/total_cnt, 2) as string), cast(dif_4cnt as string))
            from
            (
                select p1.state dim_date
                    ,p1.device_os
                    ,count(distinct p1.user_id) total_cnt
                    ,count(distinct if(datediff(p3.state,p1.state) = 1, p1.user_id, null)) dif_1cnt
                    ,count(distinct if(datediff(p3.state,p1.state) = 2, p1.user_id, null)) dif_2cnt
                    ,count(distinct if(datediff(p3.state,p1.state) = 3, p1.user_id, null)) dif_3cnt
                    ,count(distinct if(datediff(p3.state,p1.state) = 4, p1.user_id, null)) dif_4cnt
                from
                    (
                        select
                            from_unixtime(unix_timestamp(cast(partition_date as string), ‘yyyyMMdd‘), ‘yyyy-MM-dd‘) state,
                            user_id
                        from user_active_day
                        where partition_date between date1 and date2
                        and user_is_new = 1
                        group by 1,2
                    )p1 --日新增用户名单(register_date,user_id)
                    left outer join
                    (
                        select
                            from_unixtime(unix_timestamp(cast(partition_date as string), ‘yyyyMMdd‘), ‘yyyy-MM-dd‘) state,
                            user_id
                        from active_users
                        where partition_date between date1 and date2
                        group by 1,2
                    )p3 --期间活跃用户(active_date,user_id)
                    on (p3.user_id = p1.user_id)
                group by 1,2
            ) p4;