Grouping similar items recursively - sql-server

Question

I have been reading the following Microsoft article on recursive queries using CTE and just can't seem to wrap my head around how to use it for group common items.
I have a table the contains the following columns:
ID
FirstName
LastName
DateOfBirth
BirthCountry
GroupID
What I need to do is start with the first person in the table and iterate through the table and find all the people that have the same (LastName and BirthCountry) or have the same (DateOfBirth and BirthCountry).
Now the tricky part is that I have to assign them the same GroupID and then for each person in that GroupID, I need to see if anyone else has the same information and then put the in the same GroupID.
I think I could do this with multiple cursors but it is getting tricky.
Here is sample data and output.
ID FirstName LastName DateOfBirth BirthCountry GroupID
----------- ---------- ---------- ----------- ------------ -----------
1 Jonh Doe 1983-01-01 Grand 100
2 Jack Stone 1976-06-08 Grand 100
3 Jane Doe 1982-02-08 Grand 100
4 Adam Wayne 1983-01-01 Grand 100
5 Kay Wayne 1976-06-08 Grand 100
6 Matt Knox 1983-01-01 Hay 101
John Doe and Jane Doe are in the same Group (100) because they have the same (LastName and BirthCountry).
Adam Wayne is in Group (100) because he has the same (BirthDate and BirthCountry) as John Doe.
Kay Wayne is in Group (100) because she has the same (LastName and BirthCountry) as Adam Wayne who is already in Group (100).
Matt Knox is in a new group (101) because he does not match anyone in previous groups.
Jack Stone is in a group (100) because he has the same (BirthDate and BirthCountry) as Kay Wayne who is already in Group (100).
Data scripts:
CREATE TABLE #Tbl(
ID INT,
FirstName VARCHAR(50),
LastName VARCHAR(50),
DateOfBirth DATE,
BirthCountry VARCHAR(50),
GroupID INT NULL
);
INSERT INTO #Tbl VALUES
(1, 'Jonh', 'Doe', '1983-01-01', 'Grand', NULL),
(2, 'Jack', 'Stone', '1976-06-08', 'Grand', NULL),
(3, 'Jane', 'Doe', '1982-02-08', 'Grand', NULL),
(4, 'Adam', 'Wayne', '1983-01-01', 'Grand', NULL),
(5, 'Kay', 'Wayne', '1976-06-08', 'Grand', NULL),
(6, 'Matt', 'Knox', '1983-01-01', 'Hay', NULL);

Answer 1

Here's what I came up with. I have rarely written recursive queries so it was some good practice for me. By the way Kay and Adam do not share a birth country in your sample data.
with data as (
select
LastName, DateOfBirth, BirthCountry,
row_number() over (order by LastName, DateOfBirth, BirthCountry) as grpNum
from T group by LastName, DateOfBirth, BirthCountry
), r as (
select
d.LastName, d.DateOfBirth, d.BirthCountry, d.grpNum,
cast('|' + cast(d.grpNum as varchar(8)) + '|' as varchar(1024)) as equ
from data as d
union all
select
d.LastName, d.DateOfBirth, d.BirthCountry, r.grpNum,
cast(r.equ + cast(d.grpNum as varchar(8)) + '|' as varchar(1024))
from r inner join data as d
on d.grpNum > r.grpNum
and charindex('|' + cast(d.grpNum as varchar(8)) + '|', r.equ) = 0
and (d.LastName = r.LastName or d.DateOfBirth = r.DateOfBirth)
and d.BirthCountry = r.BirthCountry
), g as (
select LastName, DateOfBirth, BirthCountry, min(grpNum) as grpNum
from r group by LastName, DateOfBirth, BirthCountry
)
select t.*, dense_rank() over (order by g.grpNum) + 100 as GroupID
from T as t
inner join g
on g.LastName = t.LastName
and g.DateOfBirth = t.DateOfBirth
and g.BirthCountry = t.BirthCountry
For the recursion to terminate it's necessary to keep track of the equivalences (via string concatenation) so that at each level it only needs to consider newly discovered equivalences (or connections, transitivities, etc.) Notice that I've avoided using the word group to avoid bleeding into the GROUP BY concept.
http://rextester.com/edit/TVRVZ10193
EDIT: I used an almost arbitrary numbering for the equivalences but if you wanted them to appear in a sequence based on the lowest ID with each block that's easy to do. Instead of using row_number() say min(ID) as grpNum presuming, of course, that IDs are unique.

Answer 2

I assume groupid is the output you want which start from 100.
Even if groupid come from another table,then it is no problem.
Firstly,sorry for my "No cursor comments".Cursor or RBAR operation is require for this task.In fact after a very long time i met such requirement which took so long and I use RBAR operation.
if tommorrow i am able to do using SET BASE METHOD,then I will come and edit it.
Most importantly using RBAR operation make the script more understanding and I think it wil work for other sample data too.
Also give feedback about the performance and how it work with other sample data.
Alsi in my script you note that id are not in serial,and it do not matter,i did this in order to test.
I use print for debuging purpose,you can remove it.
SET NOCOUNT ON
DECLARE #Tbl TABLE(
ID INT,
FirstName VARCHAR(50),
LastName VARCHAR(50),
DateOfBirth DATE,
BirthCountry VARCHAR(50),
GroupID INT NULL
);
INSERT INTO #Tbl VALUES
(1, 'Jonh', 'Doe', '1983-01-01', 'Grand', NULL) ,
(2, 'Jack', 'Stone', '1976-06-08', 'Grand', NULL),
(3, 'Jane', 'Doe', '1982-02-08', 'Grand', NULL),
(4, 'Adam', 'Wayne', '1983-01-01', 'Grand', NULL),
(5, 'Kay', 'Wayne', '1976-06-08', 'Grand', NULL),
(6, 'Matt', 'Knox', '1983-01-01', 'Hay', NULL),
(7, 'Jerry', 'Stone', '1976-06-08', 'Hay', NULL)
DECLARE #StartGroupid INT = 100
DECLARE #id INT
DECLARE #Groupid INT
DECLARE #Maxid INT
DECLARE #i INT = 1
DECLARE #MinGroupID int=#StartGroupid
DECLARE #MaxGroupID int=#StartGroupid
DECLARE #LastGroupID int
SELECT #maxid = max(id)
FROM #tbl
WHILE (#i <= #maxid)
BEGIN
SELECT #id = id
,#Groupid = Groupid
FROM #Tbl a
WHERE id = #i
if(#Groupid is not null and #Groupid<#MinGroupID)
set #MinGroupID=#Groupid
if(#Groupid is not null and #Groupid>#MaxGroupID)
set #MaxGroupID=#Groupid
if(#Groupid is not null)
set #LastGroupID=#Groupid
UPDATE A
SET groupid =case
when #id=1 and b.groupid is null then #StartGroupid
when #id>1 and b.groupid is null then #MaxGroupID+1--(Select max(groupid)+1 from #tbl where id<#id)
when #id>1 and b.groupid is not null then #MinGroupID --(Select min(groupid) from #tbl where id<#id)
end
FROM #Tbl A
INNER JOIN #tbl B ON b.id = #ID
WHERE (
(
a.BirthCountry = b.BirthCountry
and a.DateOfBirth = b.dateofbirth
)
or (a.LastName = b.LastName and a.BirthCountry = b.BirthCountry)
or (a.LastName = b.LastName and a.dateofbirth = b.dateofbirth)
)
--if(#id=7) --#id=2,#id=3 and so on (for debug
--break
SET #i = #i + 1
SET #ID = #I
END
SELECT *
FROM #Tbl
Alternate Method but still it return 56,000 rows without rownum=1.See if it work with other sample data or see if you can further optimize it.
;with CTE as
(
select a.ID,a.FirstName,a.LastName,a.DateOfBirth,a.BirthCountry
,#StartGroupid GroupID
,1 rn
FROM #Tbl A where a.id=1
UNION ALL
Select a.ID,a.FirstName,a.LastName,a.DateOfBirth,a.BirthCountry
,case when ((a.BirthCountry = b.BirthCountry and a.DateOfBirth = b.dateofbirth)
or (a.LastName = b.LastName and a.BirthCountry = b.BirthCountry)
or (a.LastName = b.LastName and a.dateofbirth = b.dateofbirth)
) then b.groupid else b.groupid+1 end
, b.rn+1
FROM #tbl A
inner join CTE B on a.id>1
where b.rn<#Maxid
)
,CTE1 as
(select * ,row_number()over(partition by id order by groupid )rownum
from CTE )
select * from cte1
where rownum=1

Answer 3

Maybe you can run it in this way
SELECT *
FROM table_name
GROUP BY
FirstName,
LastName,
GroupID
HAVING COUNT(GroupID) >= 2
ORDER BY GroupID