将表格分组为 15 分钟间隔

Question

T-SQL、SQL Server 2008 及更高版本

给定一个样本表

 StatusSetDateTime   | UserID | Status    | StatusEndDateTime   | StatusDuration(in seconds)
============================================================================
 2012-01-01 12:00:00 | myID   | Available | 2012-01-01 13:00:00 | 3600

我需要将其分解为使用 15 分钟间隔的视图，例如：

IntervalStart       | UserID | Status | Duration

===========================================

2012-01-01 12:00:00 | myID | Available | 900 

2012-01-01 12:15:00 | myID | Available | 900

2012-01-01 12:30:00 | myID | Available | 900 

2012-01-01 12:45:00 | myID | Available | 900 

2012-01-01 13:00:00 | myID | Available | 0

etc....

现在我已经能够四处搜索并找到一些会崩溃的查询 我为 MySql Here 找到了类似的东西：

还有一些用于 T-SQL 的东西Here

但在第二个示例中，他们将结果相加，而我需要将总持续时间除以间隔时间（900 秒）除以用户除以状态。

我能够调整第二个链接中的示例以将所有内容拆分为间隔，但返回总持续时间，我无法完全弄清楚如何拆分间隔持续时间（并且仍然总计为原始总持续时间)。

提前感谢您提供任何见解！

编辑：第一次尝试

 ;with cte as 
    (select MIN(StatusDateTime) as MinDate
          , MAX(StatusDateTime) as MaxDate
          , convert(varchar(14),StatusDateTime, 120) as StartDate
          , DATEPART(minute, StatusDateTime) /15 as GroupID
          , UserID
          , StatusKey
          , avg(StateDuration) as AvgAmount
     from AgentActivityLog
     group by convert(varchar(14),StatusDateTime, 120)
         , DATEPART(minute, StatusDateTime) /15
         , Userid,StatusKey)

  select dateadd(minute, 15*GroupID, CONVERT(datetime,StartDate+'00'))
         as [Start Date]
       , UserID, StatusKey, AvgAmount as [Average Amount]
  from cte

编辑：第二次尝试

;With cte As
   (Select DateAdd(minute
                   , 15 * (DateDiff(minute, '20000101', StatusDateTime) / 15)
                   , '20000101') As StatusDateTime
         , userid, statuskey, StateDuration
    From AgentActivityLog)

 Select StatusDateTime, userid,statuskey,Avg(StateDuration)
 From cte
 Group By StatusDateTime,userid,statuskey;

Answer 1

;with cte_max as 
(
   select dateadd(mi, -15, max(StatusEndDateTime)) as EndTime, min(StatusSetDateTime) as StartTime
   from AgentActivityLog
), times as
(
    select StartTime as Time from cte_max
    union all
    select dateadd(mi, 15, c.Time)
    from times as c
        cross join cte_max as cm
    where c.Time <= cm.EndTime
)
select
    t.Time, A.UserID, A.Status,
    case
        when t.Time = A.StatusEndDateTime then 0
        else A.StatusDuration / (count(*) over (partition by A.StatusSetDateTime, A.UserID, A.Status) - 1)
    end as Duration
from AgentActivityLog as A
    left outer join times as t on t.Time >= A.StatusSetDateTime and t.Time <= A.StatusEndDateTime

sql fiddle demo

Answer 2

我从不习惯使用日期数学将事物分成多个分区。似乎有各种各样的陷阱。

我更喜欢做的是创建一个表（预定义的、表值函数、表变量），其中每个日期分区范围都有一行。表值函数方法特别有用，因为您可以根据需要为任意范围和分区大小构建它。然后，您可以加入此表以拆分内容。

paritionid starttime     endtime
---------- ------------- -------------
1          8/1/2012 5:00 8/1/2012 5:15
2          8/1/2012 5:15 8/1/2012 5:30
...

我无法评价这种方法的性能，但我发现查询更加直观。

Answer 3

如果您有一个每 15 分钟时间戳的帮助表，则相对简单，您可以通过 BETWEEN 将其加入到您的基表中。您可以即时构建帮助表或将其永久保存在数据库中。你公司的下一个人也很容易弄清楚：

// declare a table and a timestamp variable
declare @timetbl table(t datetime)
declare @t datetime

// set the first timestamp
set @t = '2012-01-01 00:00:00'

// set the last timestamp, can easily be extended to cover many years
while @t <= '2013-01-01'
begin
    // populate the table with a new row, every 15 minutes
    insert into @timetbl values (@t)
    set @t = dateadd(mi, 15, @t)
end


// now the Select query:
select 
   tt.t, aal.UserID, aal.Status,
   case when aal.StatusEndDateTime <= tt.t then 0 else 900 end as Duration
   // using a shortcut for Duration, based on your comment that Start/End are always on the quarter-hour, and thus always 900 seconds or zero

from 
   @timetbl tt 
      INNER JOIN AgentActivityLog aal 
         on tt.t between aal.StatusSetDateTime and aal.StatusEndDateTime

order by
  aal.UserID, tt.t

Answer 4

您可以使用 recursive Common Table Expression，在 StatusEndDateTime 大于 IntervalStart 时继续添加持续时间，例如

;with cte as (
    select StatusSetDateTime as IntervalStart
        ,UserID
        ,Status
        ,StatusDuration/(datediff(mi, StatusSetDateTime, StatusEndDateTime)/15) as Duration
        , StatusEndDateTime
    From AgentActivityLog
    Union all
    Select DATEADD(ss, Duration, IntervalStart) as IntervalStart
        , UserID
        , Status
        , case when DATEADD(ss, Duration, IntervalStart) = StatusEndDateTime then 0 else Duration end as Duration
        , StatusEndDateTime
    From cte
    Where IntervalStart < StatusEndDateTime
)

select IntervalStart, UserID, Status, Duration from cte

Answer 5

这是一个无需辅助表即可为您完成工作的查询。 （我不反对辅助表，它们很有用，我使用它们。有时也可以不使用它们。）此查询允许活动在任何时间开始和结束，即使不是以 :00 结尾的整分钟， :15,:30,:45。如果会有毫秒部分，那么您将不得不做一些实验，因为按照您的模型，我只达到了第二个分辨率。

如果您有一个已知的硬最大持续时间，则删除 @MaxDuration 并将其替换为该值（以分钟为单位）。 N <= @MaxDuration 对查询执行良好至关重要。

DECLARE @MaxDuration int;
SET @MaxDuration = (SELECT Max(StatusDuration) / 60 FROM #AgentActivityLog);

WITH
L0 AS(SELECT 1 c UNION ALL SELECT 1),
L1 AS(SELECT 1 c FROM L0, L0 B),
L2 AS(SELECT 1 c FROM L1, L1 B),
L3 AS(SELECT 1 c FROM L2, L2 B),
L4 AS(SELECT 1 c FROM L3, L3 B),
L5 AS(SELECT 1 c FROM L4, L4 B),
Nums AS(SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 0)) n FROM L5)
SELECT
   S.IntervalStart,
   Duration = DateDiff(second, S.IntervalStart, E.IntervalEnd)
FROM
   #AgentActivityLog L
   CROSS APPLY (
      SELECT N, Offset = (N.N - 1) * 900
      FROM Nums N
      WHERE N <= @MaxDuration
   ) N
   CROSS APPLY (
      SELECT Edge =
         DateAdd(second, N.Offset, DateAdd(minute,
            DateDiff(minute, '20000101', L.StatusSetDateTime)
            / 15 * 15, '20000101')
         )
   ) G
   CROSS APPLY (
      SELECT IntervalStart = Max(T.BeginTime)
      FROM (
         SELECT L.StatusSetDateTime
         UNION ALL SELECT G.Edge
      ) T (BeginTime)
   ) S
   CROSS APPLY (
      SELECT IntervalEnd = Min(T.EndTime)
      FROM (
         SELECT L.StatusEndDateTime
         UNION ALL SELECT G.Edge + '00:15:00'
      ) T (EndTime)
   ) E
WHERE
   N.Offset <= L.StatusDuration
ORDER BY
   L.StatusSetDateTime,
   S.IntervalStart;

如果你想试试，这里是安装脚本：

CREATE TABLE #AgentActivityLog (
    StatusSetDateTime datetime,
    StatusEndDateTime datetime,
    StatusDuration AS (DateDiff(second, 0, StatusEndDateTime - StatusSetDateTime))
);

INSERT #AgentActivityLog -- weird end times
SELECT '20120101 12:00:00', '20120101 13:00:00'
UNION ALL SELECT '20120101 13:00:00', '20120101 13:27:56'
UNION ALL SELECT '20120101 13:27:56', '20120101 13:28:52'
UNION ALL SELECT '20120101 13:28:52', '20120120 11:00:00'

INSERT #AgentActivityLog -- 15-minute quantized end times
SELECT '20120101 12:00:00', '20120101 13:00:00'
UNION ALL SELECT '20120101 13:00:00', '20120101 13:30:00'
UNION ALL SELECT '20120101 13:30:00', '20120101 14:00:00'
UNION ALL SELECT '20120101 14:00:00', '20120120 11:00:00'

另外，这里有一个版本，它只要求整分钟以 :00、:15、:30 或 :45 结尾的时间。

DECLARE @MaxDuration int;
SET @MaxDuration = (SELECT Max(StatusDuration) / 60 FROM #AgentActivityLog);

WITH
L0 AS(SELECT 1 c UNION ALL SELECT 1),
L1 AS(SELECT 1 c FROM L0, L0 B),
L2 AS(SELECT 1 c FROM L1, L1 B),
L3 AS(SELECT 1 c FROM L2, L2 B),
L4 AS(SELECT 1 c FROM L3, L3 B),
L5 AS(SELECT 1 c FROM L4, L4 B),
Nums AS(SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 0)) n FROM L5)
SELECT
   S.IntervalStart,
   Duration = CASE WHEN Offset = StatusDuration THEN 0 ELSE 900 END
FROM
   #AgentActivityLog L
   CROSS APPLY (
      SELECT N, Offset = (N.N - 1) * 900
      FROM Nums N
      WHERE N <= @MaxDuration
   ) N
   CROSS APPLY (
      SELECT IntervalStart = DateAdd(second, N.Offset, L.StatusSetDateTime)
   ) S
WHERE
   N.Offset <= L.StatusDuration   
ORDER BY
   L.StatusSetDateTime,
   S.IntervalStart;

看起来最后的 0 Duration 行确实不正确，因为那样你就不能只按 IntervalStart 排序，因为有重复的 IntervalStart 值。使总数加 0 的行有什么好处？