SQL持续时间计算

Question

我有一个在给定时间的历史巴士位置表，每秒记录一次。模式如下所示：

BusID  int   not null, 
BreadcrumbID int   not null identity (1, 1), 
BusStopID int   null, 
Timestamp datetime not null 

我想根据历史性旅程生成公交车站时间表。如果其车辆编号BusStopID与停车位相对应，则车辆处于“停车位”，如果BusStopID为空，则不处于“停车位”。

我需要生成公交车在每站的平均时间。所以基本上，我需要做到以下几点：

• 识别倍总线处于停止状态 - 一个简单的where条款的伎俩
• 确定的平均时间的公交车处于停止状态。出于我的目的，我将一个离散的“停止时间”定义为正负10分钟的窗口;如果一辆公共汽车从10:04 - 10:08停靠一天，另一天在10:06 - 10:08，第三天在10:14 - 10:18停靠，那么这些停靠是相同的，但如果停止在10:45 - 10:48，这将是一个不同的停止事件。
• 筛选出来的“噪音” - 即在一个头绪来完成第二和第三颗子弹停止我完全倍，只发生过几次，但从来没有再

。请帮忙！

Answer 1

在很多场合我做了类似的事情。实质上，基于复杂排序内的分离进行分组。我使用的方法的基础知识如下：

1. 构建一个所有感兴趣的时间范围表。
2. 找到每组感兴趣的时间范围的开始时间。
3. 找出每组感兴趣的时间范围的结束时间。
4. 将开始和结束时间加入到时间范围和组列表中。

或者，更详细：（每一个步骤可能是一个大的CTE的一部分，但我已经打破它分解成易于阅读的临时表...）

第1步：找到感兴趣的所有时间范围的列表（我使用了与@Brad链接的方法类似的方法）。 注意：正如@Manfred Sorg所指出的那样，这假定公交车的数据中没有“缺失的秒数”。如果时间戳中有中断，则此代码将将单个范围解释为两个（或更多）不同的范围。

;with stopSeconds as (
    select BusID, BusStopID, TimeStamp, 
     [date] = cast(datediff(dd,0,TimeStamp) as datetime), 
     [grp] = dateadd(ss, -row_number() over(partition by BusID order by TimeStamp), TimeStamp) 
    from #test 
    where BusStopID is not null 
) 
select BusID, BusStopID, date, 
     [sTime] = dateadd(ss,datediff(ss,date,min(TimeStamp)), 0), 
     [eTime] = dateadd(ss,datediff(ss,date,max(TimeStamp)), 0), 
     [secondsOfStop] = datediff(ss, min(TimeStamp), max(Timestamp)), 
     [sOrd] = row_number() over(partition by BusID, BusStopID order by datediff(ss,date,min(TimeStamp))), 
     [eOrd] = row_number() over(partition by BusID, BusStopID order by datediff(ss,date,max(TimeStamp))) 
into #ranges 
from stopSeconds 
group by BusID, BusStopID, date, grp 

第2步：找到的最早时间为每个停止

select this.BusID, this.BusStopID, this.sTime minSTime, 
     [stopOrder] = row_number() over(partition by this.BusID, this.BusStopID order by this.sTime) 
into #starts 
from #ranges this 
    left join #ranges prev on this.BusID = prev.BusID 
         and this.BusStopID = prev.BusStopID 
         and this.sOrd = prev.sOrd+1 
         and this.sTime between dateadd(mi,-10,prev.sTime) and dateadd(mi,10,prev.sTime) 
where prev.BusID is null 

第3步：查找每个最晚时间停止

select this.BusID, this.BusStopID, this.eTime maxETime, 
     [stopOrder] = row_number() over(partition by this.BusID, this.BusStopID order by this.eTime) 
into #ends 
from #ranges this 
    left join #ranges next on this.BusID = next.BusID 
         and this.BusStopID = next.BusStopID 
         and this.eOrd = next.eOrd-1 
         and this.eTime between dateadd(mi,-10,next.eTime) and dateadd(mi,10,next.eTime) 
where next.BusID is null 

第4步：一起加入一切

select r.BusID, r.BusStopID, 
     [avgLengthOfStop] = avg(datediff(ss,r.sTime,r.eTime)), 
     [earliestStop] = min(r.sTime), 
     [latestDepart] = max(r.eTime) 
from #starts s 
    join #ends e on s.BusID=e.BusID 
       and s.BusStopID=e.BusStopID 
       and s.stopOrder=e.stopOrder 
    join #ranges r on r.BusID=s.BusID 
       and r.BusStopID=s.BusStopID 
       and r.sTime between s.minSTime and e.maxETime 
       and r.eTime between s.minSTime and e.maxETime 
group by r.BusID, r.BusStopID, s.stopOrder 
having count(distinct r.date) > 1 --filters out the "noise" 

最后，是完整的，收拾：

drop table #ends 
drop table #starts 
drop table #ranges 

Answer 2

新鲜的答案...

尝试了这一点：

DECLARE @stopWindowMinutes INT 
SET @stopWindowMinutes = 10 

-- 
; 
WITH test_data 
      AS (SELECT 1 [BusStopId] 
         ,'2010-01-01 10:00:04' [Timestamp] 
       UNION SELECT 1,'2010-01-01 10:00:05' 
       UNION SELECT 1,'2010-01-01 10:00:06' 
       UNION SELECT 1,'2010-01-01 10:00:07' 
       UNION SELECT 1,'2010-01-01 10:00:08' 
       UNION SELECT 1,'2010-01-02 10:00:06' 
       UNION SELECT 1,'2010-01-02 10:00:07' 
       UNION SELECT 1,'2010-01-02 10:00:08' 
       UNION SELECT 2,'2010-01-01 10:00:06' 
       UNION SELECT 2,'2010-01-01 10:00:07' 
       UNION SELECT 2,'2010-01-01 10:00:08' 
       UNION SELECT 2,'2010-01-01 10:00:09' 
       UNION SELECT 2,'2010-01-01 10:00:10' 
       UNION SELECT 2,'2010-01-01 10:00:09' 
       UNION SELECT 2,'2010-01-01 10:00:10' 
       UNION SELECT 2,'2010-01-01 10:00:11' 
       UNION SELECT 1,'2010-01-02 10:33:43' 
       UNION SELECT 1,'2010-01-02 10:33:44' 
       UNION SELECT 1,'2010-01-02 10:33:45' 
       UNION SELECT 1,'2010-01-02 10:33:46' 
      ) 
    SELECT DISTINCT 
      [BusStopId] 
      ,[AvgStop] 
    FROM (SELECT [a].[BusStopId] 
         ,(SELECT MIN([b].[Timestamp]) 
          FROM  [test_data] b 
          WHERE  [a].[BusStopId] = [b].[BusStopId] 
            AND CONVERT(VARCHAR(10), [a].[Timestamp], 120) = CONVERT(VARCHAR(10), [b].[Timestamp], 120) 
            AND [b].[Timestamp] BETWEEN DATEADD(SECOND, -@stopWindowMinutes * 60, 
                     [a].[Timestamp]) 
                 AND  DATEADD(SECOND, @stopWindowMinutes * 60, [a].[Timestamp]) -- w/i X minutes 

         ) [MinStop] 
         ,(SELECT MAX([b].[Timestamp]) 
          FROM  [test_data] b 
          WHERE  [a].[BusStopId] = [b].[BusStopId] 
            AND CONVERT(VARCHAR(10), [a].[Timestamp], 120) = CONVERT(VARCHAR(10), [b].[Timestamp], 120) 
            AND [b].[Timestamp] BETWEEN DATEADD(SECOND, -@stopWindowMinutes * 60, 
                     [a].[Timestamp]) 
                 AND  DATEADD(SECOND, @stopWindowMinutes * 60, [a].[Timestamp]) -- w/i X minutes 

         ) [MaxStop] 
         ,(SELECT DATEADD(second, 
              AVG(DATEDIFF(second, CONVERT(VARCHAR(10), [b].[Timestamp], 120), 
                 [b].[Timestamp])), 
              CONVERT(VARCHAR(10), MIN([b].[Timestamp]), 120)) 
          FROM  [test_data] b 
          WHERE  [a].[BusStopId] = [b].[BusStopId] 
            AND CONVERT(VARCHAR(10), [a].[Timestamp], 120) = CONVERT(VARCHAR(10), [b].[Timestamp], 120) 
            AND [b].[Timestamp] BETWEEN DATEADD(SECOND, -@stopWindowMinutes * 60, 
                     [a].[Timestamp]) 
                 AND  DATEADD(SECOND, @stopWindowMinutes * 60, [a].[Timestamp]) -- w/i X minutes 

         ) [AvgStop] 
       FROM  [test_data] a 
       WHERE  CONVERT(VARCHAR(10), [Timestamp], 120) = CONVERT(VARCHAR(10), [Timestamp], 120) 
       GROUP BY [a].[BusStopId] 
         ,[a].[Timestamp] 
      ) subset1 

Answer 3

This post我刚刚看到可以帮助你。 （Sql Server Central）

Answer 4

由于通常情况下，这些类型的问题都比较容易解决，并通过破坏它们切成一口大小的块维护：

-- Split into Date and minutes-since-midnight 
WITH observed(dates,arrival,busstop,bus) AS (
    SELECT 
     CONVERT(CHAR(8), TimeStamp, 112), 
     DATEPART(HOUR,TimeStamp) * 60 + DATEPART(MINUTE,TimeStamp), 
     busstopid, 
     busid 
    FROM 
     History 
), 
-- Identify times at stop subsequent to arrival at that stop 
atstop(dates,stoptime,busstop,bus) AS (
    SELECT 
     a.dates, 
     a.arrival, 
     a.busstop, 
     a.bus 
    FROM 
     observed a 
    WHERE 
     EXISTS (
      SELECT 
       * 
      FROM 
       observed b 
      WHERE 
       a.dates = b.dates AND 
       a.busstop = b.busstop AND 
       a.bus = b.bus AND 
       a.arrival - b.arrival BETWEEN 1 AND 10 
     ) 
), 
-- Isolate actual arrivals at stops, excluding waiting at stops 
dailyhalts(dates,arrival,busstop,bus) AS (
    SELECT 
     a.dates,a.arrival,a.busstop,a.bus 
    FROM 
     observed a 
    WHERE 
     arrival NOT IN (
      SELECT 
       stoptime 
      FROM 
       atstop b 
      WHERE 
       a.dates = b.dates AND 
       a.busstop = b.busstop AND 
       a.bus = b.bus 
    ) 
), 
-- Merge arrivals across all dates 
timetable(busstop,bus,arrival) AS (
    SELECT 
     a.busstop, a.bus, a.arrival 
    FROM 
     dailyhalts a 
    WHERE 
     NOT EXISTS (
      SELECT 
       * 
      FROM 
       dailyhalts h 
      WHERE 
       a.busstop = h.busstop AND 
       a.bus = h.bus AND 
       a.arrival - h.arrival BETWEEN 1 AND 10 
     ) 
    GROUP BY 
     a.busstop, a.bus, a.arrival 
) 
-- Print timetable for a given day 
SELECT 
    a.busstop, a.bus, a.arrival, DATEADD(minute,AVG(b.arrival),'2010/01/01') 
FROM 
    timetable a INNER JOIN 
    observed b ON 
     a.busstop = b.busstop AND 
     a.bus = b.bus AND 
     b.arrival BETWEEN a.arrival AND a.arrival + 10 
GROUP BY 
    a.busstop, a.bus, a.arrival 

输入：

ID BusID BusStopID TimeStamp 
1 1 1 2010-01-01 10:00:00.000 
2 1 1 2010-01-01 10:01:00.000 
3 1 1 2010-01-01 10:02:00.000 
4 1 2 2010-01-01 11:00:00.000 
5 1 3 2010-01-01 12:00:00.000 
6 1 3 2010-01-01 12:01:00.000 
7 1 3 2010-01-01 12:02:00.000 
8 1 3 2010-01-01 12:03:00.000 
9 1 1 2010-01-02 11:00:00.000 
10 1 1 2010-01-02 11:03:00.000 
11 1 1 2010-01-02 11:07:00.000 
12 1 2 2010-01-02 12:00:00.000 
13 1 3 2010-01-02 13:00:00.000 
14 1 3 2010-01-02 13:01:00.000 
15 1 1 2010-01-03 10:03:00.000 
16 1 1 2010-01-03 10:05:00.000 

输出：

busstop bus arrival (No column name) 
1 1 600 2010-01-01 10:02:00.000 
1 1 660 2010-01-01 11:03:00.000 
2 1 660 2010-01-01 11:00:00.000 
2 1 720 2010-01-01 12:00:00.000 
3 1 720 2010-01-01 12:01:00.000 
3 1 780 2010-01-01 13:00:00.000