どのようにSQL Server内のグループ同様の行に

Question

は、私はこのような表が持っている

CREATE TABLE MyTable ([Date] date, 
         ConfigID int, 
         ItemID int, 
         ClientName char(1), 
         Metric1 decimal(3,1), 
         Metric2 decimal(3,1)); 
INSERT INTO MyTable 
VALUES ('2017-01-01',1,1,'A',2.0,2.0), 
     ('2017-01-01',3,1,'A',2.0,2.0), 
     ('2017-01-01',4,2,'B',5.0,5.0), 
     ('2017-01-02',4,3,'A',6.0,6.0), 
     ('2017-01-01',2,1,'A',2.0,2.0);  

WITH Dupes   
AS (   
    SELECT *   
     ,ROW_NUMBER() OVER ( 
      PARTITION BY 
       [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2] 
      ORDER BY [Date] DESC 
    ) AS RowNum 
    FROM myTable) 

SELECT * 
FROM Dupes 

しかし、それはこのような何かを返す：

Date  ConfigID ItemID ClientName Metric1 Metric2 RowNum 
====  ======== ====== ========== ======= ======= ====== 
2017-01-01 1   1   A    2.0  2.0  1 
2017-01-01 3   1   A    2.0  2.0  2 
2017-01-01 4   2   B    5.0  5.0  1 
2017-01-02 4   3   A    6.0  6.0  1 
2017-01-01 2   1   A    2.0  2.0  3 
.... 
(20 million rows here) 

0を

PARTITION BY句に基づいて同様の項目をグループ化したいと思います。言い換えれば、私は（私は本当にRowNumを必要としない）、このようなものを見てみたいと思います：

Date  ConfigID ItemID ClientName Metric1 Metric2 RowNum 
====  ======== ====== ========== ======= ======= ====== 
2017-01-01 1   1   A    2.0  2.0  1 
2017-01-01 3   1   A    2.0  2.0  2 
2017-01-01 2   1   A    2.0  2.0  3 
2017-01-01 4   2   B    5.0  5.0  1 
2017-01-02 4   3   A    6.0  6.0  1 
.... 
(20 million rows here) 

何SQLクエリは、グループにテーブル内の類似した/重複行を私を助けるでしょうか？進んでいただきありがとうございます。

Answer 1

ROW_NUMBERの代わりにDENSE_RANKを使用すると役立ちますか？

;   
WITH Dupes   
AS (   
    SELECT *   
     ,DENSE_RANK () 
     OVER ( 
      ORDER BY 
       [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2]   
      DESC 
    ) AS GroupID 
    FROM myTable) 

SELECT * 
FROM Dupes 

がここに解決策が提案されている：

;   
WITH D1   
AS (   
    SELECT *   
     ,DENSE_RANK () 
     OVER ( 
      ORDER BY 
       [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2]   
      DESC 
    ) AS GroupID 
    FROM myTable) 
, Dupes AS (
    SELECT * 
     , COUNT(*) OVER (PARTITION BY GroupID) AS GroupItemsCount 
    FROM D1 
) 
SELECT * 
FROM Dupes 
WHERE GroupItemsCount <> 1 

をより良い方法がコメントでルカの提案に基づいて

;   
WITH Dupes   
AS (   
    SELECT *   
     ,COUNT(*) 
     OVER ( 
      partition BY 
       [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2]   
    ) AS GroupItemsCount 
    FROM myTable) 

SELECT * 
FROM Dupes 
WHERE GroupItemsCount > 1 

Answer 2

ちょうど私はあなただけorder byが必要だと思う選択

;   
WITH Dupes   
AS (   
    SELECT *   
     ,ROW_NUMBER() OVER ( 
      PARTITION BY 
       [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2] 
      ORDER BY [Date] DESC 
    ) AS RowNum 
    FROM myTable) 

SELECT * 
FROM Dupes 
order by [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2], 
RowNum 

Answer 3

内で順序を与えます。 CTEは必要ありません。

. . . 
SELECT * 
FROM Dupes 
ORDER BY [Date], [ItemID], [ClientName], [Metric1], [Metric2]; 

Answer 4

可能性があり、COUNT(*) PARTITION BY(...)を使用して動作するようです：

CREATE TABLE MyTable ([Date] date, 
         ConfigID int, 
         ItemID int, 
         ClientName char(1), 
         Metric1 decimal(3,1), 
         Metric2 decimal(3,1)); 
INSERT INTO MyTable 
VALUES ('2017-01-01',1,1,'A',2.0,2.0), 
     ('2017-01-01',3,1,'A',2.0,2.0), 
     ('2017-01-01',4,2,'B',5.0,5.0), 
     ('2017-01-02',4,3,'A',6.0,6.0), 
     ('2017-01-01',2,1,'A',2.0,2.0);  

WITH Dupes   
AS (   
    SELECT *   
     ,COUNT(*) OVER ( 
      PARTITION BY 
       [Date] 
       ,[ItemID] 
       ,[ClientName] 
       ,[Metric1] 
       ,[Metric2] 
      ORDER BY [Date] DESC 
    ) AS DupeCount 
    FROM myTable) 

SELECT * 
FROM Dupes 
WHERE DupeCount > 1