使用现有查询的概念

Question

编辑：

我正在使用Sql Server 2005，并且我试图获得当年（例如6月1日 - 5月30日）和过去3年中不同用户的年度（YOY）数量。我能够通过运行四次选择语句来做我需要的事情，但我现在似乎无法找到更好的方法。我可以在一个查询中获得每年的独特计数，但我需要累计不同的计数。下面是我到目前为止的模型：

SELECT [Year], COUNT(DISTINCT UserID)
FROM
(
  SELECT u.uID AS UserID, 
      CASE 
        WHEN dd.ddEnd BETWEEN @yearOneStart AND @yearOneEnd THEN 'Year1'
        WHEN dd.ddEnd BETWEEN @yearTwoStart AND @yearTwoEnd THEN 'Year2'
        WHEN dd.ddEnd BETWEEN @yearThreeStart AND @yearThreeEnd THEN 'Year3'
        WHEN dd.ddEnd BETWEEN @yearFourStart AND @yearFourEnd THEN 'Year4'
        ELSE 'Other'
      END AS [Year]
  FROM Users AS u   
  INNER JOIN UserDataIDMatch AS udim
    ON u.uID = udim.udim_FK_uID
  INNER JOIN DataDump AS dd
    ON udim.udimUserSystemID = dd.ddSystemID
) AS Data
WHERE LOWER([Year])  'other'
GROUP BY
  [Year]

我得到类似的东西：

Year1    1
Year2    1
Year3    1
Year4    1

但我真的需要：

Year1    1
Year2    2
Year3    3
Year4    4

下面是一个粗略的架构和一组值（为简单起见而更新）。我试图创建一个SQL小提琴，但是当我尝试构建架构时，我遇到了磁盘空间错误。

CREATE TABLE Users
(
  uID int identity primary key, 
  uFirstName varchar(75), 
  uLastName varchar(75)
);

INSERT INTO Users (uFirstName, uLastName)
VALUES
('User1', 'User1'),
('User2', 'User2')
('User3', 'User3')
('User4', 'User4');

CREATE TABLE UserDataIDMatch
(
  udimID int indentity primary key,
  udim.udim_FK_uID int foreign key references Users(uID),
  udimUserSystemID varchar(75)
);

INSERT INTO UserDataIDMatch (udim_FK_uID, udimUserSystemID)
VALUES
(1, 'SystemID1'),
(2, 'SystemID2'),
(3, 'SystemID3'),
(4, 'SystemID4');

CREATE TABLE DataDump
(
  ddID int identity primary key,
  ddSystemID varchar(75),
  ddEnd datetime
);

INSERT INTO DataDump (ddSystemID, ddEnd)
VALUES
('SystemID1', '10-01-2013'),
('SystemID2', '10-01-2014'),
('SystemID3', '10-01-2015'),
('SystemID4', '10-01-2016');

Answer 1

使用现有查询的概念

我做了类似的事情，找出了多年来购买东西的不同客户的数量，我修改它以使用你的年份概念，你添加的变量将是开始日和年度开始月份，开始年度和结束年度。

从技术上讲，有一种方法可以避免使用循环，但这是非常清楚的，你不能超过9999年，所以不要放置聪明的代码来避免循环有意义

加快查询的提示

同样，当匹配日期时，请确保您正在比较日期，而不是比较列的功能评估，因为这意味着在每个记录集上运行该函数，如果它们存在于日期（它们应该），则会使索引无效。使用日期添加为了启动您的目标日期，从一年中减去1900，从月份减去一个，从目标日期减去一个。

然后自我加入表格，其中日期创建有效范围（即年份到年份）并使用子查询基于该范围创建总和。由于您希望从第一年到最后一次限制累积结果从第一年开始。

最后你会错过第一年，因为根据我们的定义它不符合范围，要解决这个问题，只需在你创建的临时表上做一个联合，以添加缺少的年份和不同值的数量在它。

DECLARE @yearStartMonth INT = 6, @yearStartDay INT = 1
DECLARE @yearStart INT = 2008, @yearEnd INT  = 2012

DECLARE @firstYearStart DATE = 
        DATEADD(day,@yearStartDay-1, 
           DATEADD(month, @yearStartMonth-1,
             DATEADD(year, @yearStart- 1900,0)))

DECLARE @lastYearEnd DATE = 
        DATEADD(day, @yearStartDay-2,
            DATEADD(month, @yearStartMonth-1,
               DATEADD(year, @yearEnd -1900,0)))    

DECLARE @firstdayofcurrentyear DATE = @firstYearStart 
DECLARE @lastdayofcurrentyear DATE = DATEADD(day,-1,DATEADD(year,1,@firstdayofcurrentyear))
DECLARE @yearnumber INT = YEAR(@firstdayofcurrentyear)

DECLARE @tempTableYearBounds TABLE
(
    startDate DATE NOT NULL,
    endDate DATE NOT NULL,
    YearNumber INT NOT NULL
)

WHILE @firstdayofcurrentyear < @lastYearEnd
BEGIN
INSERT INTO @tempTableYearBounds 
VALUES(@firstdayofcurrentyear,@lastdayofcurrentyear,@yearNumber)
SET @firstdayofcurrentyear = DATEADD(year,1,@firstdayofcurrentyear)
SET @lastdayofcurrentyear = DATEADD(year,1,@lastdayofcurrentyear)
SET @yearNumber = @yearNumber + 1
END



DECLARE @tempTableCustomerCount TABLE
(
    [Year] INT NOT NULL,
    [CustomerCount] INT NOT NULL
)


INSERT INTO @tempTableCustomerCount
SELECT 
YearNumber as [Year],
COUNT(DISTINCT CustomerNumber) as CutomerCount
FROM Ticket
     JOIN @tempTableYearBounds ON
          TicketDate >= startDate AND TicketDate <=endDate
GROUP BY YearNumber


SELECT * FROM(
SELECT t2.Year as [Year], 
(SELECT 
    SUM(CustomerCount) 
    FROM @tempTableCustomerCount 
    WHERE Year>=t1.Year 
         AND Year <=t2.Year) AS CustomerCount
FROM @tempTableCustomerCount t1 JOIN @tempTableCustomerCount t2
    ON t1.Year < t2.Year
WHERE t1.Year = @yearStart
UNION
SELECT [Year], [CustomerCount] 
FROM @tempTableCustomerCount
WHERE [YEAR] = @yearStart
) tt
ORDER BY tt.Year

效率不高，但最后你正在处理的临时表是如此之小，我认为它并不重要，并且与你使用的方法相比增加了更多的多功能性。

更新：我更新了查询以反映您想要的数据集结果，我基本上测试的是看它是否更快，它更快10秒但是我处理的数据集与相对较小。（从12秒到2秒）。

使用您的数据

我更改了你给临时表的表，所以它没有影响我的环境，我删除了外键，因为临时表不支持它们，逻辑与包含的示例相同，但只是针对数据集进行了更改。

DECLARE @startYear INT = 2013, @endYear INT = 2016
DECLARE @yearStartMonth INT = 10 , @yearStartDay INT = 1
DECLARE @startDate DATETIME = DATEADD(day,@yearStartDay-1,
                                 DATEADD(month, @yearStartMonth-1,
                                     DATEADD(year,@startYear-1900,0)))
DECLARE @endDate DATETIME = DATEADD(day,@yearStartDay-1,
                                DATEADD(month,@yearStartMonth-1,
                                    DATEADD(year,@endYear-1899,0)))

DECLARE @tempDateRangeTable TABLE
(
    [Year] INT NOT NULL,
    StartDate DATETIME NOT NULL, 
    EndDate DATETIME NOT NULL
)

DECLARE @currentDate DATETIME = @startDate
WHILE @currentDate < @endDate
BEGIN
DECLARE @nextDate DATETIME  = DATEADD(YEAR, 1, @currentDate)
INSERT INTO @tempDateRangeTable(Year,StartDate,EndDate)
VALUES(YEAR(@currentDate),@currentDate,@nextDate)
SET @currentDate = @nextDate
END

CREATE TABLE Users
(
  uID int identity primary key, 
  uFirstName varchar(75), 
  uLastName varchar(75)
);

INSERT INTO Users (uFirstName, uLastName)
VALUES
('User1', 'User1'),
('User2', 'User2'),
('User3', 'User3'),
('User4', 'User4');

CREATE TABLE UserDataIDMatch
(
  udimID int indentity primary key,
  udim.udim_FK_uID int foreign key references Users(uID),
  udimUserSystemID varchar(75)
);

INSERT INTO UserDataIDMatch (udim_FK_uID, udimUserSystemID)
VALUES
(1, 'SystemID1'),
(2, 'SystemID2'),
(3, 'SystemID3'),
(4, 'SystemID4');

CREATE TABLE DataDump
(
  ddID int identity primary key,
  ddSystemID varchar(75),
  ddEnd datetime
);   


INSERT INTO DataDump (ddSystemID, ddEnd)
VALUES
('SystemID1', '10-01-2013'),
('SystemID2', '10-01-2014'),
('SystemID3', '10-01-2015'),
('SystemID4', '10-01-2016');


DECLARE @tempIndividCount TABLE
(
    [Year] INT NOT NULL,
    UserCount INT NOT NULL
)


-- no longer need to filter out other because you are using an
--inclusion statement rather than an exclusion one, this will 
--also make your query faster (when using real tables not temp ones)
INSERT INTO @tempIndividCount(Year,UserCount)
SELECT tdr.Year, COUNT(DISTINCT UId) FROM
    Users u JOIN UserDataIDMatch um
       ON um.udim_FK_uID  = u.uID
    JOIN DataDump dd ON
       um.udimUserSystemID = dd.ddSystemID
    JOIN @tempDateRangeTable tdr ON
        dd.ddEnd >= tdr.StartDate AND dd.ddEnd < tdr.EndDate
GROUP BY tdr.Year

-- will show you your result
SELECT * FROM @tempIndividCount

--add any ranges that did not have an entry but were in your range
--can easily remove this by taking this part out.
INSERT INTO @tempIndividCount
SELECT t1.Year,0 FROM
    @tempDateRangeTable t1 LEFT OUTER JOIN @tempIndividCount t2
        ON  t1.Year = t2.Year
    WHERE t2.Year IS NULL


SELECT YearNumber,UserCount FROM (
SELECT 'Year'+CAST(((t2.Year-t1.Year)+1) AS CHAR) [YearNumber] ,t2.Year,(
    SELECT SUM(UserCount) 
    FROM @tempIndividCount 
    WHERE Year >= t1.Year AND Year <=t2.Year 
    ) AS UserCount 
FROM @tempIndividCount t1 
    JOIN @tempIndividCount t2
        ON t1.Year < t2.Year
WHERE t1.Year = @startYear
UNION ALL 
--add the missing first year, union it to include the value
SELECT 'Year1',Year, UserCount FROM @tempIndividCount
WHERE Year = @startYear) tt
ORDER BY tt.Year

优于使用基于案例的方法

更健壮

不需要明确确定每年的结束日期和开始日期，就像在逻辑年份只需知道开始日期和结束日期一样。可以通过一些简单的修改轻松改变你想要的东西（即你想要所有的2年范围或3年）。

如果数据库正确编入索引会更快

由于您基于相同的数据类型进行搜索，因此可以使用应在数据库中的日期列上创建的索引。

缺点

更复杂

查询要复杂得多，即使它更健壮，实际查询中还有很多额外的逻辑。

在某些情况下，不会很好地提高执行时间

如果数据集非常小，或者比较的日期数量不重要，那么就无法节省足够的时间来进行评估。

Answer 2

除非我遗漏了某些内容，否则您只想知道日期小于或等于当前会计年度的记录数。

DECLARE @YearOneStart DATETIME, @YearOneEnd DATETIME,
        @YearTwoStart DATETIME, @YearTwoEnd DATETIME,
        @YearThreeStart DATETIME, @YearThreeEnd DATETIME,
        @YearFourStart DATETIME, @YearFourEnd DATETIME

SELECT @YearOneStart = '06/01/2013', @YearOneEnd = '05/31/2014',
        @YearTwoStart = '06/01/2014', @YearTwoEnd = '05/31/2015',
        @YearThreeStart = '06/01/2015', @YearThreeEnd = '05/31/2016',
        @YearFourStart = '06/01/2016', @YearFourEnd = '05/31/2017'

;WITH cte AS 
(
      SELECT u.uID AS UserID, 
      CASE 
        WHEN dd.ddEnd BETWEEN @yearOneStart AND @yearOneEnd THEN 'Year1'
        WHEN dd.ddEnd BETWEEN @yearTwoStart AND @yearTwoEnd THEN 'Year2'
        WHEN dd.ddEnd BETWEEN @yearThreeStart AND @yearThreeEnd THEN 'Year3'
        WHEN dd.ddEnd BETWEEN @yearFourStart AND @yearFourEnd THEN 'Year4'
        ELSE 'Other'
      END AS [Year]
      FROM Users AS u   
      INNER JOIN UserDataIDMatch AS udim
        ON u.uID = udim.udim_FK_uID
      INNER JOIN DataDump AS dd
        ON udim.udimUserSystemID = dd.ddSystemID
)

SELECT 
    DISTINCT [Year],
    (SELECT COUNT(*) FROM cte cteInner WHERE cteInner.[Year] <= cteMain.[Year] )
FROM cte cteMain

Answer 3

在SQL Server内匹配WHEN内的CASE时，它会停止评估，不会继续评估下一个WHEN子句。因此，你无法积累那种方式。

如果我理解正确，这将显示您的结果。

;WITH cte AS 
(F
    SELECT dd.ddEnd [dateEnd], u.uID AS UserID
    FROM Users AS u     
    INNER JOIN UserDataIDMatch AS udim
        ON u.uID = udim.udim_FK_uID
    INNER JOIN DataDump AS dd
        ON udim.udimUserSystemID = dd.ddSystemID
    WHERE ddEnd BETWEEN @FiscalYearStart AND @FiscalYearEnd3
) 
SELECT datepart(year, @FiscalYearStart) AS [Year], COUNT(DISTINCT UserID) AS CntUserID
FROM cte
WHERE dateEnd BETWEEN  @FiscalYearStart AND @FiscalYearEnd1
GROUP BY @FiscalYearStart
UNION 
SELECT datepart(year, @FiscalYearEnd1) AS [Year], COUNT(DISTINCT UserID) AS CntUserID
FROM cte
WHERE dateEnd BETWEEN  @FiscalYearStart AND @FiscalYearEnd2
GROUP BY @FiscalYearEnd1
UNION 
SELECT datepart(year, @FiscalYearEnd3) AS [Year], COUNT(DISTINCT UserID) AS CntUserID
FROM cte
WHERE dateEnd BETWEEN  @FiscalYearStart AND @FiscalYearEnd3
GROUP BY @FiscalYearEnd2

年同比（YOY）与众不同

3 个答案:

使用现有查询的概念

加快查询的提示

使用您的数据

优于使用基于案例的方法

更健壮

如果数据库正确编入索引会更快

缺点

更复杂

在某些情况下，不会很好地提高执行时间