将 GROUP BY 与 FIRST_VALUE 和 LAST_VALUE 结合使用

Question

我正在处理一些当前以 1 分钟为间隔存储的数据，如下所示：

CREATE TABLE #MinuteData
    (
      [Id] INT ,
      [MinuteBar] DATETIME ,
      [Open] NUMERIC(12, 6) ,
      [High] NUMERIC(12, 6) ,
      [Low] NUMERIC(12, 6) ,
      [Close] NUMERIC(12, 6)
    );

INSERT  INTO #MinuteData
        ( [Id], [MinuteBar], [Open], [High], [Low], [Close] )
VALUES  ( 1, '2015-01-01 17:00:00', 1.557870, 1.557880, 1.557870, 1.557880 ),
        ( 2, '2015-01-01 17:01:00', 1.557900, 1.557900, 1.557880, 1.557880 ),
        ( 3, '2015-01-01 17:02:00', 1.557960, 1.558070, 1.557960, 1.558040 ),
        ( 4, '2015-01-01 17:03:00', 1.558080, 1.558100, 1.558040, 1.558050 ),
        ( 5, '2015-01-01 17:04:00', 1.558050, 1.558100, 1.558020, 1.558030 ),
        ( 6, '2015-01-01 17:05:00', 1.558580, 1.558710, 1.557870, 1.557950 ),
        ( 7, '2015-01-01 17:06:00', 1.557910, 1.558120, 1.557910, 1.557990 ),
        ( 8, '2015-01-01 17:07:00', 1.557940, 1.558250, 1.557940, 1.558170 ),
        ( 9, '2015-01-01 17:08:00', 1.558140, 1.558200, 1.558080, 1.558120 ),
        ( 10, '2015-01-01 17:09:00', 1.558110, 1.558140, 1.557970, 1.557970 );

SELECT  *
FROM    #MinuteData;

DROP TABLE #MinuteData;

这些值跟踪货币汇率，因此对于每个分钟间隔（柱），分钟开始时有 Open 价格，分钟结束时有 Close 价格。 High 和 Low 值代表每一分钟内的最高和最低速率。

期望输出

我希望以 5 分钟的间隔重新格式化此数据以生成以下输出：

MinuteBar                Open       Close       Low         High
2015-01-01 17:00:00.000  1.557870   1.558030    1.557870    1.558100
2015-01-01 17:05:00.000  1.558580   1.557970    1.557870    1.558710

这从 5 的第一分钟获取 Open 值，从 5 的最后一分钟获取 Close 值。High 和 Low 值代表 5 分钟内最高 high 和最低 low 率。

当前解决方案

我有一个解决方案可以做到这一点（如下），但感觉不够优雅，因为它依赖于 id 值和自连接。另外，我打算运行它在更大的数据集上，所以我希望尽可能以更有效的方式进行：

-- Create a column to allow grouping in 5 minute Intervals
SELECT  Id, MinuteBar, [Open], High, Low, [Close], 
DATEDIFF(MINUTE, '2015-01-01T00:00:00', MinuteBar)/5 AS Interval
INTO    #5MinuteData
FROM    #MinuteData
ORDER BY minutebar

-- Group by inteval and aggregate prior to self join
SELECT  Interval ,
        MIN(MinuteBar) AS MinuteBar ,
        MIN(Id) AS OpenId ,
        MAX(Id) AS CloseId ,
        MIN(Low) AS Low ,
        MAX(High) AS High
INTO    #DataMinMax
FROM    #5MinuteData
GROUP BY Interval;

-- Self join to get the Open and Close values
SELECT  t1.Interval ,
        t1.MinuteBar ,
        tOpen.[Open] ,
        tClose.[Close] ,
        t1.Low ,
        t1.High
FROM    #DataMinMax t1
        INNER JOIN #5MinuteData tOpen ON tOpen.Id = OpenId
        INNER JOIN #5MinuteData tClose ON tClose.Id = CloseId;

DROP TABLE #DataMinMax
DROP TABLE #5MinuteData

返工尝试

我一直在考虑使用 FIRST_VALUE and LAST_VALUE 而不是上述查询，因为这似乎是我所追求的，但我不能完全让它与我的分组一起工作'我在做可能有比我正在尝试做的更好的解决方案，所以我愿意接受建议。目前我正在尝试这样做：

SELECT  MIN(MinuteBar) MinuteBar5 ,
        FIRST_VALUE([Open]) OVER (ORDER BY MinuteBar) AS Opening,
        MAX(High) AS High ,
        MIN(Low) AS Low ,
        LAST_VALUE([Close]) OVER (ORDER BY MinuteBar) AS Closing ,
        DATEDIFF(MINUTE, '2015-01-01 00:00:00', MinuteBar) / 5 AS Interval
FROM    #MinuteData
GROUP BY DATEDIFF(MINUTE, '2015-01-01 00:00:00', MinuteBar) / 5

这给了我下面的错误，如果我删除这些行，它与作为查询运行的 FIRST_VALUE 和 LAST_VALUE 有关：

Column '#MinuteData.MinuteBar' is invalid in the select list because it is not contained in either an aggregate function or the GROUP BY clause.

Answer 1

这是一种不用临时表的方法：

;WITH CTEInterval AS 
(  -- This replaces your first temporary table (#5MinuteData)
    SELECT  [Id], 
            [MinuteBar], 
            [Open], 
            [High], 
            [Low], 
            [Close],
            DATEPART(MINUTE, MinuteBar)/5 AS Interval
    FROM #MinuteData
), CTEOpenClose as 
( -- this is instead of your second temporary table (#DataMinMax)
    SELECT  [Id], 
            [MinuteBar], 
            FIRST_VALUE([Open]) OVER (PARTITION BY Interval ORDER BY MinuteBar) As [Open],
            [High],
            [Low], 
            FIRST_VALUE([Close]) OVER (PARTITION BY Interval ORDER BY MinuteBar DESC) As [Close],
            Interval
    FROM CTEInterval
)

-- This is the final select
SELECT  MIN([MinuteBar]) as [MinuteBar], 
        AVG([Open]) as [Open], -- All values of [Open] in the same interval are the same...
        AVG([Close]) as [Close],  -- All values of [Close] in the same interval are the same...
        MIN([Low]) as [Low], 
        MAX([High]) as [High]
FROM CTEOpenClose
GROUP BY Interval

结果：

MinuteBar                Open       Close       Low         High
2015-01-01 17:00:00.000  1.557870   1.558030    1.557870    1.558100
2015-01-01 17:05:00.000  1.558580   1.557970    1.557870    1.558710

Answer 2

SELECT 
    MIN(MinuteBar) AS MinuteBar5,
    Opening,
    MAX(High) AS High,
    MIN(Low) AS Low,
    Closing,
    Interval
FROM 
(
    SELECT FIRST_VALUE([Open]) OVER (PARTITION BY DATEDIFF(MINUTE, '2015-01-01 00:00:00', MinuteBar) / 5 ORDER BY MinuteBar) AS Opening,
           FIRST_VALUE([Close]) OVER (PARTITION BY DATEDIFF(MINUTE, '2015-01-01 00:00:00', MinuteBar) / 5 ORDER BY MinuteBar DESC) AS Closing,
           DATEDIFF(MINUTE, '2015-01-01 00:00:00', MinuteBar) / 5 AS Interval,
           *
    FROM #MinuteData
) AS T
GROUP BY Interval, Opening, Closing

接近您当前的解决方案。你有两个地方做错了

FIRST_VALUE 和 LAST_VALUE 是 解析函数 ，它们作用于 window 或分区，而不是团体。您可以单独运行嵌套查询并查看其结果。

LAST_VALUE是current的最后一个值window，在你的查询中没有指定，默认的window是从第一行开始的行当前分区到 当前行 。您可以按降序使用 FIRST_VALUE 或指定 window

LAST_VALUE([Close]) OVER (PARTITION BY DATEDIFF(MINUTE, '2015-01-01 00:00:00', MinuteBar) / 5 
            ORDER BY MinuteBar 
            ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS Closing,

Answer 3

Demo here

;with cte
as
(--this can be your permanent table with intervals ,rather than generating on fly
select cast('2015-01-01 17:00:00.000' as datetime) as interval,dateadd(mi,5,'2015-01-01 17:00:00.000') as nxtinterval
union all
select dateadd(mi,5,interval),dateadd(mi,5,nxtinterval) from cte
where interval<='2015-01-01 17:45:00.000'

)
,finalcte
as
(select minutebar,
low,high,
dense_rank() over (order by  interval,nxtinterval) as grpd,
last_value([close]) over ( partition by interval,nxtinterval order by interval,nxtinterval) as [close],
first_value([open]) over (partition by interval,nxtinterval order by interval,nxtinterval) as [open]
 from cte c
join
#minutedata m
on m.minutebar between interval and nxtinterval
)
select 
min(minutebar) as minutebar,
min(low) as 'low',
max(high) as 'High',
max([open]) as 'open',
max([close]) as 'close'
 from finalcte
 group by grpd

将 GROUP BY 与 FIRST_VALUE 和 LAST_VALUE 结合使用

Using GROUP BY with FIRST_VALUE and LAST_VALUE

sql-server

group-by

aggregate-functions

sql-server-2014

analytic-functions