连续的日期

Question

希望这不是另一个问题的欺骗，但我在其他任何地方都看不到它 - 这也是 another question I asked 的简化版本，希望能让我开始研究如何解决它。

我希望找出每个月至少有一次付款的连续付款范围。

我有以下示例数据

CREATE TABLE #data
(
Contact_reference NVARCHAR(55)
,Date_payment DATETIME
,Payment_value MONEY
)

INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2003-06-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2004-06-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2004-12-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-04-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-05-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-06-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-07-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-08-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-09-08',12.82)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-10-10',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-11-10',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2005-12-10',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2006-01-10',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2006-02-10',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2006-02-28',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2006-04-12',12.8205)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2006-05-10',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-06-11',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-07-10',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-08-09',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-09-10',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-10-09',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-11-09',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2007-12-10',19.2308)
INSERT INTO #data VALUES ('18EC3CD2-3065-4FF4-BE40-000004228590','2008-01-10',19.2308)

我希望能够为每个联系人计算出他们连续给予的范围（定义为每个日历月至少给予一次）、连续付款的次数、每次的总价值范围（如果可能的话，最好是当前范围和最近一个范围的结尾之间的差距）。

对于上面的测试数据，我的输出如下所示：

CREATE TABLE #results
(
contact_reference NVARCHAR(55)
,Range_start DATETIME
,Range_end DATETIME
,Payments INT
,Value MONEY
,months_until_next_payment INT --works out the gap between the range_end date for a group and the range_start date for the next group
)
INSERT INTO #results VALUES('18EC3CD2-3065-4FF4-BE40-000004228590','2003-06-08','2003-06-08',1,12.82,12)
INSERT INTO #results VALUES('18EC3CD2-3065-4FF4-BE40-000004228590','2004-06-08','2004-06-08',1,12.82,6)
INSERT INTO #results VALUES('18EC3CD2-3065-4FF4-BE40-000004228590','2004-12-08','2004-12-08',1,12.82,4)
INSERT INTO #results VALUES('18EC3CD2-3065-4FF4-BE40-000004228590','2005-04-08','2006-02-28',12,153.843,2)
INSERT INTO #results VALUES('18EC3CD2-3065-4FF4-BE40-000004228590','2006-04-12','2008-06-06',27,416.6673,NULL)

我已经使用岛屿或迭代来寻找答案，但坦率地说，我什至不知道从哪里开始将它们应用于我的问题，所以非常感谢任何帮助:)

Answer 1

编辑：我已在months_until_next_payment 列中添加。这在应用程序中比使用自联接更有效，但是因为 SQL Server 没有任何特别令人满意的方式来引用下一行和上一行。

;WITH base AS ( 
SELECT    Contact_reference  ,
          Payment_value,
          DATEPART(YEAR, Date_payment)*12 + DATEPART(MONTH, Date_payment) - 
               DENSE_RANK() OVER 
                   (PARTITION BY Contact_reference 
                    ORDER BY DATEPART(YEAR, Date_payment)*12 + DATEPART(MONTH, Date_payment)) AS G,
          Date_payment
 FROM     #data
 ),
 cte AS
 (
 SELECT 
          Contact_reference, 
          ROW_NUMBER() over (partition by Contact_reference 
                                 order by MIN(Date_payment)) RN,
          MIN(Date_payment) Range_start,
          MAX(Date_payment) Range_end, 
          COUNT(Payment_value) Payments, 
          SUM(Payment_value) Value
 FROM base
 GROUP BY Contact_reference, G
 )
 SELECT 
       c1.Contact_reference, 
       c1.Payments, 
       c1.Range_end, 
       c1.Range_start, 
       c1.Value, 
       DATEDIFF(month, c1.Range_end,c2.Range_start) months_until_next_payment
 FROM cte c1
 LEFT join cte c2 ON c1.Contact_reference=c2.Contact_reference and c2.RN = c1.RN+1

Answer 2

您可以使用光标来完成。像 c#/java 这样的语言是解决这个问题的更好选择。

DECLARE @date DATETIME
DECLARE @nextDate DATETIME
DECLARE @rangeStart DATETIME
DECLARE @rangeEnd DATETIME

DECLARE @value decimal(18,2)
DECLARE @valueSum decimal(18,2)
DECLARE @count int

DECLARE @PaymentCursor CURSOR

SET @PaymentCursor = CURSOR FOR
    SELECT Date_payment, Payment_value FROM #data
    ORDER BY Date_payment

OPEN @PaymentCursor
    FETCH NEXT FROM @PaymentCursor INTO @nextDate, @value   
    SET @date = @nextDate
    SET @rangeStart = @nextDate
    SET @valueSum = 0
    SET @count = 0

    WHILE (@@FETCH_STATUS = 0)
    BEGIN       
        FETCH NEXT FROM @PaymentCursor INTO @nextDate, @value

        SET @count = @count + 1
        SET @valueSum = @valueSum + @value      

        IF (DATEDIFF(mm, @date, @nextDate) > 1)
        BEGIN
            SELECT @rangeStart AS RangeStart, @date AS RangeEnd, @count AS Coount, @valueSum AS VALUE, DATEDIFF(mm, @date, @nextDate) AS months_until_next_payment
            SET @valueSum = 0               
            SET @count = 0
            SET @rangeStart = @nextDate
        END

        SET @date = @nextDate           
    END

    SELECT @rangeStart AS RangeStart, @date AS RangeEnd, @count AS Coount, @valueSum AS VALUE, null AS months_until_next_payment

CLOSE @PaymentCursor
DEALLOCATE @PaymentCursor