SQL Server 2005 中的数据聚合

Question

我需要查询 SQl server 2005 (SQL server management studio express)。 我将数据存储为 1 分钟时间范围（每行 1 分钟），每个表的列是 ID、符号、日期时间、开盘价、最高价、最低价、收盘价、成交量。 我需要转换（压缩）到每个可能的多个时间帧，所以假设 10 分钟、13 分钟、15 分钟等等。 如果有人可以提供帮助，请提供完整的详细信息。 谢谢 阿尔贝托

Answer 1

Alberto，您似乎需要在 SQL 语句中使用“Group By”子句（如 Leppie 所述）。所以，你最好去寻找它。

首先，您应该使用开始和结束日期/时间过滤要聚合的行，然后按上述子句对它们进行分组。

这是我通过 Google 搜索“sql group by”关键字时的第一个 link。

Answer 2

;WITH cte AS
(SELECT *,
        (32 * CAST([DATETIME] AS INT)) + DATEPART(HOUR,[DATETIME]) + (DATEPART(MINUTE,[DATETIME])/15)/4.0 AS Seg
     FROM     prices
     )
,cte1 AS
(
SELECT *,
        ROW_NUMBER() OVER (PARTITION BY Symbol,Seg ORDER BY [DATETIME])      AS RN_ASC ,
        ROW_NUMBER() OVER (PARTITION BY Symbol,Seg ORDER BY [DATETIME] DESC) AS RN_DESC
FROM cte
)     
SELECT 
      Symbol,
      Seg,
      MAX(CASE WHEN RN_ASC=1 THEN [DATETIME] END) AS OpenDateTime,
      MAX(CASE WHEN RN_ASC=1 THEN [OPEN] END) AS [OPEN],
      MAX(High) High,
      MIN(Low)  Low,
      SUM(Volume) Volume,
      MAX(CASE WHEN RN_DESC=1 THEN [CLOSE] END) AS [CLOSE],
      MAX(CASE WHEN RN_DESC=1 THEN [DATETIME] END) AS CloseDateTime
FROM cte1
GROUP BY Symbol,Seg
ORDER BY OpenDateTime

或者另一种可能值得测试的方法，看看它是否更快。

DECLARE @D1 DATETIME
DECLARE @D2 DATETIME
DECLARE @Interval FLOAT

SET @D1  = '2010-10-18 09:00:00.000'
SET @D2  = '2010-10-19 18:00:00.000'
SET @Interval = 15

;WITH 
L0 AS (SELECT 1 AS c UNION ALL SELECT 1),
L1 AS (SELECT 1 AS c FROM L0 A CROSS JOIN L0 B),
L2 AS (SELECT 1 AS c FROM L1 A CROSS JOIN L1 B),
L3 AS (SELECT 1 AS c FROM L2 A CROSS JOIN L2 B),
L4 AS (SELECT 1 AS c FROM L3 A CROSS JOIN L3 B),
Nums AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 0)) AS i FROM L4),
Ranges AS(
SELECT 
      DATEADD(MINUTE,@Interval*(i-1),@D1) AS StartRange,
      DATEADD(MINUTE,@Interval*i,@D1) AS NextRange
FROM Nums where i <= 1+CEILING(DATEDIFF(MINUTE,@D1,@D2)/@Interval))
,cte AS (
SELECT 
     * 
     ,ROW_NUMBER() OVER (PARTITION BY Symbol,r.StartRange ORDER BY [DateTime])      AS RN_ASC 
     ,ROW_NUMBER() OVER (PARTITION BY Symbol,r.StartRange ORDER BY [DateTime] DESC) AS RN_DESC
FROM Ranges r
JOIN prices p ON p.[DateTime] >= r.StartRange and p.[DateTime] < r.NextRange )
SELECT 
      Symbol,
      MAX(CASE WHEN RN_ASC=1 THEN [DateTime] END) AS OpenDateTime,
      MAX(CASE WHEN RN_ASC=1 THEN [Open] END) AS [Open],
      MAX(High) High,
      MIN(Low)  Low,
      SUM(Volume) Volume,
      MAX(CASE WHEN RN_DESC=1 THEN [Close] END) AS [Close],
      MAX(CASE WHEN RN_DESC=1 THEN [DateTime] END) AS CloseDateTime
FROM cte
GROUP BY Symbol,StartRange
ORDER BY OpenDateTime

Answer 3

不是简单的“分组依据” - 需要为组中的第一行和相应的最后一行获取打开和关闭值。或者至少对于外汇数据来说是这样的:)

Answer 4

使用存储过程先提取 MIN(datetime) 会更漂亮，但这里有一个草图：

WITH quarters(q) AS (
    SELECT DISTINCT
        15*CAST(DATEDIFF("n",'2000/01/01',dataora) / 15 as Int) AS primo
    FROM 
        Prezzi
)
SELECT
    simbolo, DATEADD("n",q,'2000/01/01') AS tick, 
        MIN(minimo) AS minimo, MAX(massimo) AS massimo,
        (SELECT 
            TOP 1 apertura FROM Prezzi P 
         WHERE 
            P.simbolo = simbolo AND 
            P.dataora >= DATEADD("n",q,'2000/01/01')
         ORDER BY
            P.dataora ASC
         ) as primaapertura,
        (SELECT 
            TOP 1 chiusura FROM Prezzi P 
         WHERE 
            P.simbolo = simbolo AND 
            P.dataora < DATEADD("s",14*60+59,DATEADD("n",q,'2000/01/01'))
         ORDER BY
            P.dataora DESC
         ) as ultimachiusara,
        SUM(volume) / COUNT(*) AS volumemedio
FROM
    quarters INNER JOIN Prezzi
    ON dataora BETWEEN DATEADD("n",q,'2000/01/01')
        AND DATEADD("s",14*60+59,DATEADD("n",q,'2000/01/01'))
GROUP BY
    simbolo, DATEADD("n",q,'2000/01/01')
ORDER BY 
    1, 2

WITH 子句在您的数据集中获取 15 分钟间隔的列表，向下取整（假设 2000 年之前没有任何内容）。 然后使用这些间隔按 14:59 间隔分组。 对于数量，您必须决定是要平均还是总数量。

语法可能有点过时，但你应该明白。

编辑：调整 MIN（打开），MIN（关闭）以获取 FIRST 和 LAST。实际上这不会有太大变化，因为打开和关闭的概念取决于了解报价来源的交易所与收集数据的计算机时钟之间的时差。

此外，除非 OP 有权获得所有交易所的实时信息，否则所有报价都会延迟 20 分钟。

EDIT(2)：非常正确，FIRST 和 LAST 是我在 IBM 时代的遗留物 >;-)

解决方案现在使用 TOP 和 ASC/DESC 在间隔期间选择第一个和最后一个引号。

Answer 5

    Declare @tbl1MinENI Table 
    (ID int identity,
     Simbolo char(3),
     DataOra datetime,
     Apertura numeric(15,4),
     Massimo  numeric(15,4),
     Minimo numeric(15,4),
     Chiusura numeric(15,4),
     Volume int)

    Insert Into  @tbl1MinENI (  Simbolo, DataOra, Apertura, Massimo, Minimo, Chiusura, Volume)
    Values
    ('ENI', '2010/10/18 09:00:00', 16.1100, 16.1800, 16.1100, 16.1400, 244015),
    ('ENI', '2010/10/18 09:01:00', 16.1400, 16.1400, 16.1300, 16.1400, 15692 ),
    ('ENI', '2010/10/18 09:02:00', 16.1400, 16.1500, 16.1400, 16.1500, 147035),
    ('ENI', '2010/10/18 09:03:00', 16.1500, 16.1600, 16.1500, 16.1600, 5181  ),
    ('ENI', '2010/10/18 09:04:00', 16.1600, 16.2000, 16.1600, 16.1900, 5134  ),
    ('ENI', '2010/10/18 09:05:00', 16.1900, 16.1900, 16.1800, 16.1800, 15040 ),
    ('ENI', '2010/10/18 09:06:00', 16.1900, 16.1900, 16.1600, 16.1600, 68867 ),
    ('ENI', '2010/10/18 09:07:00', 16.1600, 16.1600, 16.1600, 16.1600, 7606  ),
    ('ENI', '2010/10/18 09:08:00', 16.1500, 16.1500, 16.1500, 16.1500, 725   ),
    ('ENI', '2010/10/18 09:09:00', 16.1600, 16.1600, 16.1600, 16.1600, 81    ),
    ('ENI', '2010/10/18 09:10:00', 16.1700, 16.1800, 16.1700, 16.1700, 68594 ),
    ('ENI', '2010/10/18 09:11:00', 16.1800, 16.1800, 16.1800, 16.1800, 6619  )

    Declare @nRowsPerGroup int = 3

;With Prepare as
(
Select datediff(minute, '2010/10/18 09:00:00', DataOra)/@nRowsPerGroup as Grp,
       Row_Number() over (partition by datediff(minute, '2010/10/18 09:00:00', DataOra)/@nRowsPerGroup order by dataora) as rn,
       *
  From tbl1MinENI     
), b as
(
Select a.Grp, 
         Min(a.DataOra)          as GroupDataOra, 
         Min(ID) AperturaID,
         max(a.Massimo)          as Massimo, 
         Min(a.Minimo)           as Minimo, 
         max(id) ChiusuraID,
         sum(a.Volume)           as Volume
    From Prepare a
   Group by Grp
)
Select b.grp,
       b.GroupDataOra,
       ta.Apertura,
       b.Massimo,
       b.Minimo,
       tc.Chiusura,
       b.Volume
 From b
 Inner Join tbl1MinENI ta on ta.ID=b.AperturaID
 Inner Join tbl1MinENI tc on tc.ID=b.ChiusuraID
 ;