Creating clusters of related columns - tsql

Question

I have a table named Stores with columns:
StoreCode NVARCHAR(10),
OldStoreCode NVARCHAR(10)
Here is a sample of my data:
| StoreCode | OldStoreCode |
|-----------|--------------|
| A | B |
| B | A |
| D | E |
| E | F |
| M | K |
| J | K |
| K | L |
|-----------|--------------|
I want to create clusters of related Stores. Related store means there is a one way relation between StoreCodes and OldStoreCodes.
Expected result table:
| StoreCode | ClusterId |
|-----------|-----------|
| A | 1 |
| B | 1 |
| D | 2 |
| E | 2 |
| F | 2 |
| M | 3 |
| K | 3 |
| J | 3 |
| L | 3 |
|-----------|-----------|
There is no maximum number hops. There may be a StoreCode A which has a OldStoreCode B, which has a OldStoreCode C, which has a OldStoreCode D etc.
How can I cluster stores like this?

Answer 1

Try it like this:
EDIT: With changes by OP taken from comment
DECLARE #tbl TABLE(ID INT IDENTITY, StoreCode VARCHAR(100),OldStoreCode VARCHAR(100));
INSERT INTO #tbl VALUES
('A','B'),('B','A'),('D','E'),('E','F'),('M','K'),('J','K'),('K','L');
WITH Related AS
(
SELECT DISTINCT t1.ID,Val
FROM #tbl AS t1
INNER JOIN #tbl AS t2 ON t1.StoreCode=t2.StoreCode
OR t1.OldStoreCode=t2.OldStoreCode
OR t1.OldStoreCode=t2.StoreCode
OR t1.StoreCode=t2.OldStoreCode
CROSS APPLY(SELECT DISTINCT Val
FROM
(VALUES(t1.StoreCode),(t2.StoreCode),(t1.OldStoreCode),(t2.OldStoreCode)) AS A(Val)
) AS valsInCols
)
,ClusterKeys AS
(
SELECT r1.ID
,(
SELECT r2.Val AS [*]
FROM Related AS r2
WHERE r2.ID=r1.ID
ORDER BY r2.Val
FOR XML PATH('')
) AS ClusterKey
FROM Related AS r1
GROUP BY r1.ID
)
,ClusterIds AS
(
SELECT ClusterKey
,MIN(ID) AS ID
FROM ClusterKeys
GROUP BY ClusterKey
)
SELECT r.ID
,r.Val
FROM ClusterIds c
INNER JOIN Related r ON c.ID = r.ID
The result
ID Val
1 A
1 B
3 D
3 E
3 F
5 J
5 K
5 L
5 M

Answer 2

This should do it:
SAMPLE DATA:
IF OBJECT_ID('tempdb..#Temp1') IS NOT NULL
BEGIN
DROP TABLE #Temp1;
END;
CREATE TABLE #Temp1(StoreCode NVARCHAR(10)
, OldStoreCode NVARCHAR(10));
INSERT INTO #Temp1(StoreCode
, OldStoreCode)
VALUES
('A'
, 'B'),
('B'
, 'A'),
('D'
, 'E'),
('E'
, 'F'),
('M'
, 'K'),
('J'
, 'K'),
('K'
, 'L');
QUERY:
;WITH A -- get all distinct new and old storecodes
AS (
SELECT StoreCode
FROM #Temp1
UNION
SELECT OldStoreCode
FROM #Temp1),
B -- give a unique number id to each store code
AS (SELECT rn = RANK() OVER(ORDER BY StoreCode)
, StoreCode
FROM A),
C -- combine the store codes and the unique number id's in one table
AS (SELECT b2.rn AS StoreCodeID
, t.StoreCode
, b1.rn AS OldStoreCodeId
, t.OldStoreCode
FROM #Temp1 AS t
LEFT OUTER JOIN B AS b1 ON t.OldStoreCode = b1.StoreCode
LEFT OUTER JOIN B AS b2 ON t.StoreCode = b2.StoreCode),
D -- assign a row number for each entry in the data set
AS (SELECT rn = RANK() OVER(ORDER BY StoreCode)
, *
FROM C),
E -- derive first and last store in the path
AS (SELECT FirstStore = d2.StoreCode
, LastStore = d1.OldStoreCode
, GroupID = d1.OldStoreCodeId
FROM D AS d1
RIGHT OUTER JOIN D AS d2 ON d1.StoreCodeID = d2.OldStoreCodeId
AND d1.rn - 1 = d2.rn
WHERE d1.OldStoreCode IS NOT NULL) ,
F -- get the stores wich led to the last store with one hop
AS (SELECT C.StoreCode
, E.GroupID
FROM E
INNER JOIN C ON E.LastStore = C.OldStoreCode)
-- combine to get the full grouping
SELECT A.StoreCode, ClusterID = DENSE_RANK() OVER (ORDER BY A.GroupID) FROM (
SELECT C.StoreCode,F.GroupID FROM C INNER JOIN F ON C.OldStoreCode = F.StoreCode
UNION
SELECT * FROM F
UNION
SELECT E.LastStore,E.GroupID FROM E) AS A ORDER BY StoreCode, ClusterID
RESULTS: