使用分组依据，等级，行号重复删除

问题描述 投票：0回答：1

我有两个桌子。一个是CustomerOrders，另一个是OrderCustomerRef-查找表。

两个表都具有一对多关系-一个客户可能与多个订单相关联。

CustomerOrders表具有重复的客户（相同的LName，FName，电子邮件）。但是它们具有不同的Cust_ID。

我需要将所有重复的联系人合并到基本客户表中（一对一）。 （此表未在此处显示）。

步骤1：

需要找出应将哪个Cust_ID合并到相应的重复客户（相同的LName，FName，电子邮件）中。具有最新Order_Date的联系人应赢得其对应的重复副本（客户）。 VIP客户有一个例外-不管Order_Date如何，他们都应该一直是获胜者。

步骤2：更新了OrderCustomerRef表：将所有丢失的重复Cust_ID替换为获胜的Cust_ID。

步骤3：从基本“客户”表中删除所有丢失的联系人（在当前范围内为否。我自己做）。 

IF OBJECT_ID('tempdb..#table') IS NOT NULL
DROP TABLE #table;

IF OBJECT_ID('tempdb..#CustomerOrders') IS NOT NULL
DROP TABLE #CustomerOrders;

IF OBJECT_ID('tempdb..#OrderCustomerRef') IS NOT NULL
DROP TABLE #OrderCustomerRef;

CREATE TABLE #CustomerOrders 
(
[PK_ID] INT NOT NULL PRIMARY KEY IDENTITY(1,1),
Cust_ID INT NOT NULL, 
LName VARCHAR(100) NULL, 
FName VARCHAR(100) NULL, 
[Customer_E-mail] VARCHAR(100) NULL,
Order_Date DATETIME NULL,
Customer_Source VARCHAR(100) NULL,
CustomerType VARCHAR(100) NULL
)

INSERT INTO #CustomerOrders (Cust_ID, LName, FName, [Customer_E-mail], Order_Date, Customer_Source, CustomerType)
VALUES 
(1, 'John', 'Smith', '[email protected]', '2018-11-10 01:40:55.150', 'XYZ Company', 'Regular'),
(2, 'John', 'Smith', '[email protected]', '2018-10-10 05:05:55.150', 'Internet', 'VIP'),
(3, 'Adam', 'Burns', '[email protected]', '2017-05-05 00:00:00.000', 'XYZ Company','Regular'),
(3, 'Adam', 'Burns', '[email protected]', '2017-05-05 00:00:00.000', 'XYZ Company','VIP'),
(4, 'Adam', 'Burns', '[email protected]', '2017-05-05 00:00:00.000', 'Internet','Regular'),
(5, 'Adam', 'Burns', '[email protected]', '2017-05-05 00:00:00.000', 'Internet','VIP'),
(6, 'James', 'Snatcher', '[email protected]', '2019-07-07 00:00:00.000', 'XYZ Company', 'Regular'),
(7, 'James', 'Snatcher', '[email protected]', '2019-07-07 00:00:00.000', 'Internet','Regular'),
(9, 'Thomas', 'Johnson', '[email protected]', '2016-05-01 00:00:00.000', 'Internet','Regular'),
(9, 'Thomas', 'Johnson', '[email protected]', '2015-04-01 00:00:00.000', 'Internet','Regular'),
(10, 'Thomas', 'Johnson', '[email protected]', '2014-03-01 00:00:00.000', 'Internet','Regular'),
(11, 'Thomas', 'Johnson', '[email protected]', '2013-02-01 00:00:00.000', 'XYZ Company','Regular'),
(12, 'Peter', 'McDonald', '[email protected]', '2013-02-01 00:00:00.000', 'XYZ Company','Regular'),
(13, 'Jose', 'Mainster', '[email protected]', '2013-02-01 00:00:00.000', 'Internet','Regular'),
(14, 'Kevin', 'Digginton', '[email protected]', '2013-02-01 00:00:00.000', 'Internet','Regular'),
(14, 'Kevin', 'Digginton', '[email protected]', '2015-09-03 00:00:00.000', 'Internet','Regular')

CREATE TABLE #OrderCustomerRef
(
    Raw_PK INT NOT NULL PRIMARY KEY IDENTITY(1,1),
    OrderID INT NOT NULL, 
    Cust_ID INT NULL, 
    OrderType VARCHAR(100) NULL
)

    INSERT INTO #OrderCustomerRef (OrderID, Cust_ID, OrderType)
    VALUES 
    (1,1,'Online'),
    (2,2,'Online'),
    (3,3,'Online'),
    (4,3,'Online'),
    (5,4,'In Store'),
    (6,5,'Online'),
    (7,6,'Online'),
    (8,7,'In Store'),
    (9,9,'Online'),
    (10,9,'Online'),
    (11,10,'In Store'),
    (12,11,'Online'),
    (13,12,'Online'),
    (14,13,'Online'),
    (15,14,'Online'),
    (16,14,'In Store')

    -- SELECT * FROM #OrderCustomerRef

    SELECT *,
    RANK() OVER (PARTITION BY FName, LName, [Customer_E-mail], Customer_Source ORDER BY Order_Date DESC) AS Rank_1,
    RANK() OVER (PARTITION BY FName, LName, [Customer_E-mail], Customer_Source ORDER BY Order_Date, CustomerType DESC ) AS Rank_CustType,
    RANK() OVER (PARTITION BY Cust_ID, FName, LName, [Customer_E-mail], Customer_Source ORDER BY Order_Date, CustomerType DESC ) AS Rank_CustID,
    RANK() OVER (PARTITION BY FName, LName, [Customer_E-mail] ORDER BY Order_Date DESC) AS Rank_2,
    RANK() OVER (PARTITION BY FName, LName, [Customer_E-mail] ORDER BY Cust_ID) AS Rank_3
    FROM #CustomerOrders

期望的输出应该看似：

*例外：-丢失的客户ID 1、3（应该赢了，但是由于副本重复，所以是VIP，所以正在输）-赢得客户ID 2、5（因为是VIP，有例外）

例如：## OrderCustomerRef中所有出现的Cust_ID为1的John Smith的Cust_ID都应替换为Cust_ID为2的John Smith，Adam Burns的Cust_ID的所有出现且Cust_ID的为3应该替换为Cust_ID为5的Adam Burns

一般规则：-丢失客户ID 7、10、11、4-获奖客户ID 6，9，12，13，14

例如：## OrderCustomerRef中所有出现的Cust_ID为7，应替换为6，所有出现的Cust_ID为10，均应替换为9 *

最终，我应该在## OrderCustomerRef表中仅具有客户ID 6、9、12、13、14、2、5，

使用Rank_CustType_1，column_1，column_2，我可以确定步骤1。但是我仍然对第2步有问题-像这样更新OrderCustomerRef表：所有丢失的Cust_ID应替换为对应的重复的获胜Cust_ID。

我已经尝试过了。但这仍然不能代替丢失的Cust_ID。 

SELECT *,
    RANK() OVER (PARTITION BY FName, LName, [Customer_E-mail] ORDER BY Order_Date, CustomerType DESC) AS Rank_CustType_1,
    RANK() OVER (PARTITION BY FName, LName, [Customer_E-mail] ORDER BY Cust_ID) AS Rank_3
INTO #table
FROM #CustomerOrders

; with cte as (
    select Cust_ID, FName, LName, [Customer_E-mail], max(t.Rank_CustType_1) as Rank_CustType_1
    ,(select distinct Cust_ID from #table a where a.Cust_ID = t.Cust_ID and Rank_3 = 1) column_1
    ,(select distinct Cust_ID from #table a where a.Cust_ID = t.Cust_ID and Rank_3 <> 1) column_2

from #table t
group by Cust_ID, FName, LName, [Customer_E-mail]
    )

    update b
    set Cust_ID = case  
    when b.Cust_ID = cte.Cust_ID and
     b.Cust_ID = ISNULL(cte.column_1,'') and Rank_CustType_1 != 1 then b.Cust_ID 
    when b.Cust_ID = cte.Cust_ID and
     b.Cust_ID = ISNULL(cte.column_2,'') and Rank_CustType_1 != 1 then cte.column_2     
    when b.Cust_ID = cte.Cust_ID and Rank_CustType_1 = 1 and cte.column_1 is null and cte.column_2 is not null then cte.column_2
    when b.Cust_ID = cte.Cust_ID and Rank_CustType_1 = 1 and cte.column_1 is not null and cte.column_2 is null then cte.column_1 
    end  
    from #OrderCustomerRef b
    inner join cte on b.Cust_ID = cte.Cust_ID;

    select * from #OrderCustomerRef;
sql-server group-by duplicates ranking row-number
1个回答
1
投票

根据您提供的信息，我使用了以下CTE来显示可以得到所需结果的结果：

WITH DaCTE -- To rank the existing rows
AS  (
        SELECT pk_ID
            , cust_ID
            , fname
            , lname
            , [customer_e-mail]
            , Order_Date
            , Customer_Source
            , customertype
            , ROW_NUMBER() OVER (PARTITION BY fname, lname, [customer_e-mail] ORDER BY customertype DESC, order_date DESC, cust_id) as RankYo -- Orders by the criteria provided but while you suggested 3 should lose to 5, they have the same criteria so either one could win based on ordering
        FROM #customerorders
    )
, NewSource -- To show winning Customer ID next to Original ID
AS  (
        SELECT co.pk_ID
            , DaCTE.cust_ID as NewCustomerID
            , co.cust_ID as OriginalCustomerID
            , co.fname
            , co.lname
            , co.[customer_e-mail]
            , co.Order_Date
            , co.Customer_Source
            , co.customertype
        FROM DaCTE
        INNER JOIN #CustomerOrders as co
            ON co.fname = DaCTE.FName
            AND co.lname = DaCTE.LName
            AND co.[customer_e-mail] = DaCTE.[Customer_E-mail]
        WHERE DaCTE.RankYo = 1 -- filter to show only the winning IDs based on resulting rank from previous CTE
    )
SELECT *
/*UPDATE ocr --commented out so you can see the results before running update
SET ocr.Cust_ID = ns.NewCustomerID*/
FROM #OrderCustomerRef as ocr
INNER JOIN NewSource as ns
    ON ns.OriginalCustomerID = ocr.Cust_ID
最新问题
© www.soinside.com 2019 - 2024. All rights reserved.