SQL - Case statement to remove duplicate columns - sql

I have a table as follows:
Type_id name Comments
-------------------
61 a aa
62 a Test2
62 b bb
63 c cc
63 b bb
63 c bb
64 c cc
Now I would like to select the result set as follows:
Type_id name Comments
-------------------
61 a aa
62 a Test2
b bb
63 c cc
b bb
c bb
64 c cc
The duplicate Type_id should display an empty string if there are multiple values. I tried using CASE statements but without much luck.
Here is the query that I have tried with:
select
case when Type_id = 61 then 'Cell1'
when Type_id = 62 then 'Cell2'
when Type_id = 63 then 'Cell3'
else ''
end as Type_id,
name,
Comments
FROM
TBL
where
CATEGORY_ID = 120
order by Type_id
Can anyone help me. Thanks in advance.

I used a combination of LAG and CASE to solve:
CREATE TABLE #temp (ID VARCHAR(2), [name] VARCHAR (1), comment VARCHAR(10))
INSERT INTO #temp (ID, [name], comment)
VALUES
(61 , 'a' , 'aa' ),
(62 , 'a' , 'Test2' ),
(62 , 'b' , 'bb' ),
(63 , 'c' , 'cc' ),
(63, 'b' , 'bb' ),
(63 , 'c' , 'bb' ),
(64 , 'c' , 'cc' );
SELECT CASE WHEN id = (LAG(id, 1, 0) OVER (ORDER BY Id))
THEN ''
ELSE id
END AS id,
[name],
comment
FROM #temp
DROP TABLE #temp

here is my version
--temp data
if object_id('tempdb..#x') is not null drop table #x
CREATE TABLE #x(type_id INT, name VARCHAR(1), comments VARCHAR(20))
INSERT INTO #x(type_id, name, comments) VALUES
( 61, 'a', 'aa'),
( 62, 'a', 'Test2'),
( 62, 'b', 'bb'),
( 63, 'c', 'cc'),
( 63, 'b', 'bb'),
(63, 'c', 'bb'),
(64, 'c', 'cc')
--query
SELECT CASE WHEN type_id=LAG(type_id,1,0) OVER(ORDER BY type_id) THEN NULL ELSE type_id END AS 'type_id',
name, comments
FROM #x
output
type_id name comments
61 a aa
62 a Test2
NULL b bb
63 c cc
NULL b bb
NULL c bb
64 c cc
If you don't have LAG as the requester states
if object_id('tempdb..#x') is not null drop table #x
CREATE TABLE #x(type_id INT, name VARCHAR(1), comments VARCHAR(20))
INSERT INTO #x(type_id, name, comments) VALUES
( 61, 'a', 'aa'),
( 62, 'a', 'Test2'),
( 62, 'b', 'bb'),
( 63, 'c', 'cc'),
( 63, 'b', 'bb'),
(63, 'c', 'bb'),
(64, 'c', 'cc')
if object_id('tempdb..#a') is not null drop table #a
SELECT x.*,
ROW_NUMBER() OVER(PARTITION BY x.type_id ORDER BY x.type_id) AS 'id_count'
INTO #a
FROM #x AS x
SELECT CASE WHEN a.id_count>1 THEN NULL ELSE a.type_id END AS 'type_id',
a.name, a.comments
FROM #a AS a

select
case when row_number() -- only return 1st value
over (partition by Type_id
order by name) = 1
then cast(Type_id as varchar(10))
else ''
end as Type_id,
name,
Comments
FROM
TBL
where
CATEGORY_ID = 120
order by Type_id, name -- same order by used in ROW_NUMBER

Related

Selecting rows from a table with specific values per id

I have the below table
Table 1
Id WFID data1 data2
1 12 'd' 'e'
1 13 '3' '4f'
1 15 'e' 'dd'
2 12 'f' 'ee'
3 17 'd' 'f'
2 17 'd' 'f'
4 12 'd' 'f'
5 20 'd' 'f'
From this table I just want to select the rows which has 12 and 17 only exclusively. Like from the table I just want to retrieve the distinct id's 2,3 and 4. 1 is excluded because it has 12 but also has 13 and 15. 5 is excluded because it has 20.
2 in included because it has just 12 and 17.
3 is included because it has just 17
4 is included because it has just 12
If you just want the list of distinct ids that satisfy the conditions, you can use aggregation and filter with a having clause:
select id
from mytable
group by id
having max(case when wfid not in (12, 17) then 1 else 0 end) = 0
This filters out groups that have any wfid other than 12 or 17.
If you want the entire corresponding rows, then window functions are more appropriate:
select
from (
select t.*,
max(case when wfid not in (12, 17) then 1 else 0 end) over(partition by id) flag
from mytable t
) t
where flag = 0
You really need to start thinking in terms of sets. And it helps everyone if you provide a script that can be used to experiment and demonstrate. Here is another approach using the EXCEPT operator. The idea is to first generate a set of IDs that we want based on the filter. You then generate a set of IDs that we do not want. Using EXCEPT we can then remove the 2nd set from the 1st.
declare #x table (Id tinyint, WFID tinyint, data1 char(1), data2 varchar(4));
insert #x (Id, WFID, data1, data2) values
(1, 12, 'd', 'e'),
(1, 13, '3', '4f'),
(1, 15, 'e', 'dd'),
(2, 12, 'f', 'ee'),
(3, 17, 'd', 'f'),
(2, 17, 'd', 'f'),
(4, 12, 'd', 'f'),
(2, 12, 'z', 'ef'),
(5, 20, 'd', 'f');
select * from #x
select id from #x where WFID not in (12, 17);
select id from #x where WFID in (12, 17)
except
select id from #x where WFID not in (12, 17);
Notice the added row to demonstrate what happens when there are "duplicates".

change data format from rows to columns

I have a SQL table in the below format. Every ID has 2 entries in the table for a particular date.
Input:
ID date rownum subid value1 value2
A 200911 1 X 10 20
A 200911 2 Y 15 25
B 201001 2 S 60 35
B 201001 1 R 40 50
I want to write a SQL query to change this to the below format, so that every ID/date combination has only 1 entry as shown below. The rownum is already included and the values should be represented so that rownnum 1 is displayed first and then the value with rownum second as shown below.
Output:
ID date row1subid row1value1 row1value2 row2subid row2value1 row2value2
A 200911 X 10 20 Y 15 25
B 201001 R 40 50 S 60 35
Let me know if something is not clear.
Thanks for all your help!
Here is what you need to do as a SQL Fiddle.
And for reference:
CREATE TABLE TestData
([ID] varchar(1),
[date] int,
[rownum] int,
[subid] varchar(1),
[value1] int,
[value2] int)
;
INSERT INTO TestData
([ID], [date], [rownum], [subid], [value1], [value2])
VALUES
('A', 200911, 1, 'X', 10, 20),
('A', 200911, 2, 'Y', 15, 25),
('B', 201001, 2, 'S', 60, 35),
('B', 201001, 1, 'R', 40, 50)
;
SELECT A.ID, A.date, A.rownum, A.subid, A.value1, A.value2, B.value1 AS r2value1, B.value2 AS r2value2
FROM TestData AS A
INNER JOIN TestData B ON A.id = B.id AND B.rownum = 2
WHERE A.rownum = 1

Merging groups of interval data - SQL Server

I have two sets of interval data I.E.
Start End Type1 Type2
0 2 L NULL
2 5 L NULL
5 7 L NULL
7 10 L NULL
2 3 NULL S
3 5 NULL S
5 8 NULL S
11 12 NULL S
What I'd like to do is merge these sets into one. This seems possible by utilising an islands and gaps solution but due to the non-continuous nature of the intervals I'm not sure how to go about applying it... The output I'm expecting would be:
Start End Type1 Type2
0 2 L NULL
2 3 L S
3 5 L S
5 7 L S
7 8 L S
8 10 L NULL
11 12 NULL S
Anyone out there done something like this before??? Thanks!
Create script below:
CREATE TABLE Table1
([Start] int, [End] int, [Type1] varchar(4), [Type2] varchar(4))
;
INSERT INTO Table1
([Start], [End], [Type1], [Type2])
VALUES
(0, 2, 'L', NULL),
(2, 3, NULL, 'S'),
(2, 5, 'L', NULL),
(3, 5, NULL, 'S'),
(5, 7, 'L', NULL),
(5, 8, NULL, 'S'),
(7, 10, 'L', NULL),
(11, 12, NULL, 'S')
;
I assume that Start is inclusive, End is exclusive and given intervals do not overlap.
CTE_Number is a table of numbers. Here it is generated on the fly. I have it as a permanent table in my database.
CTE_T1 and CTE_T2 expand each interval into the corresponding number of rows using a table of numbers. For example, interval [2,5) generates rows with Values
2
3
4
This is done twice: for Type1 and Type2.
Results for Type1 and Type2 are FULL JOINed together on Value.
Finally, a gaps-and-islands pass groups/collapses intervals back.
Run the query step-by-step, CTE-by-CTE and examine intermediate results to understand how it works.
Sample data
I added few rows to illustrate a case when there is a gap between values.
DECLARE #Table1 TABLE
([Start] int, [End] int, [Type1] varchar(4), [Type2] varchar(4))
;
INSERT INTO #Table1 ([Start], [End], [Type1], [Type2]) VALUES
( 0, 2, 'L', NULL),
( 2, 3, NULL, 'S'),
( 2, 5, 'L', NULL),
( 3, 5, NULL, 'S'),
( 5, 7, 'L', NULL),
( 5, 8, NULL, 'S'),
( 7, 10, 'L', NULL),
(11, 12, NULL, 'S'),
(15, 20, 'L', NULL),
(15, 20, NULL, 'S');
Query
WITH
e1(n) AS
(
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
) -- 10
,e2(n) AS (SELECT 1 FROM e1 CROSS JOIN e1 AS b) -- 10*10
,e3(n) AS (SELECT 1 FROM e1 CROSS JOIN e2) -- 10*100
,CTE_Numbers
AS
(
SELECT ROW_NUMBER() OVER (ORDER BY n) AS Number
FROM e3
)
,CTE_T1
AS
(
SELECT
T1.[Start] + CA.Number - 1 AS Value
,T1.Type1
FROM
#Table1 AS T1
CROSS APPLY
(
SELECT TOP(T1.[End] - T1.[Start]) CTE_Numbers.Number
FROM CTE_Numbers
ORDER BY CTE_Numbers.Number
) AS CA
WHERE
T1.Type1 IS NOT NULL
)
,CTE_T2
AS
(
SELECT
T2.[Start] + CA.Number - 1 AS Value
,T2.Type2
FROM
#Table1 AS T2
CROSS APPLY
(
SELECT TOP(T2.[End] - T2.[Start]) CTE_Numbers.Number
FROM CTE_Numbers
ORDER BY CTE_Numbers.Number
) AS CA
WHERE
T2.Type2 IS NOT NULL
)
,CTE_Values
AS
(
SELECT
ISNULL(CTE_T1.Value, CTE_T2.Value) AS Value
,CTE_T1.Type1
,CTE_T2.Type2
,ROW_NUMBER() OVER (ORDER BY ISNULL(CTE_T1.Value, CTE_T2.Value)) AS rn
FROM
CTE_T1
FULL JOIN CTE_T2 ON CTE_T2.Value = CTE_T1.Value
)
,CTE_Groups
AS
(
SELECT
Value
,Type1
,Type2
,rn
,ROW_NUMBER() OVER
(PARTITION BY rn - Value, Type1, Type2 ORDER BY Value) AS rn2
FROM CTE_Values
)
SELECT
MIN(Value) AS [Start]
,MAX(Value) + 1 AS [End]
,Type1
,Type2
FROM CTE_Groups
GROUP BY rn-rn2, Type1, Type2
ORDER BY [Start];
Result
+-------+-----+-------+-------+
| Start | End | Type1 | Type2 |
+-------+-----+-------+-------+
| 0 | 2 | L | NULL |
| 2 | 8 | L | S |
| 8 | 10 | L | NULL |
| 11 | 12 | NULL | S |
| 15 | 20 | L | S |
+-------+-----+-------+-------+
A step-by-step way is:
-- Finding all break points
;WITH breaks AS (
SELECT Start
FROM yourTable
UNION
SELECT [End]
FROM yourTable
) -- Finding Possible Ends
, ends AS (
SELECT Start
, (SELECT Min([End]) FROM yourTable WHERE yourTable.Start = breaks.Start) End1
, (SELECT Max([End]) FROM yourTable WHERE yourTable.Start < breaks.Start) End2
FROM breaks
) -- Finding periods
, periods AS (
SELECT Start,
CASE
WHEN End1 > End2 And End2 > Start THEN End2
WHEN End1 IS NULL THEN End2
ELSE End1
END [End]
FROM Ends
WHERE NOT(End1 IS NULL AND Start = End2)
) -- Generating results
SELECT p.Start, p.[End], Max(Type1) Type1, Max(Type2) Type2
FROM periods p, yourTable t
WHERE p.start >= t.Start AND p.[End] <= t.[End]
GROUP BY p.Start, p.[End];
In above query some situations may not fit at analyzing all of them, you can improve it as you want ;).
First getting all the numbers of start and end via a Union.
Then joining those numbers on both the 'L' and 'S' records.
Uses a table variable for the test.
DECLARE #Table1 TABLE (Start int, [End] int, Type1 varchar(4), Type2 varchar(4));
INSERT INTO #Table1 (Start, [End], Type1, Type2)
VALUES (0, 2, 'L', NULL),(2, 3, NULL, 'S'),(2, 5, 'L', NULL),(3, 5, NULL, 'S'),
(5, 7, 'L', NULL),(5, 8, NULL, 'S'),(7, 10, 'L', NULL),(11, 12, NULL, 'S');
select
n.Num as Start,
(case when s.[End] is null or l.[End] <= s.[End] then l.[End] else s.[End] end) as [End],
l.Type1,
s.Type2
from
(select Start as Num from #Table1 union select [End] from #Table1) n
left join #Table1 l on (n.Num >= l.Start and n.Num < l.[End] and l.Type1 = 'L')
left join #Table1 s on (n.Num >= s.Start and n.Num < s.[End] and s.Type2 = 'S')
where (l.Start is not null or s.Start is not null)
order by Start, [End];
Output:
Start End Type1 Type2
0 2 L NULL
2 3 L S
3 5 L S
5 7 L S
7 8 L S
8 10 L NULL
11 12 NULL S

Unpivot multiple columns not showing desire result

Original
RecordKey Name Section1_Product Section1_Code Section2_Product Section2_Code ......
1 a ff 22
2 b gg 22
3 c hh 33
RecordKey Name Section Product Code ......
1 a 1 ff 22
1 a 2
2 b 1 gg 22
2 b 2
3 c 1 hh 22
3 c 2
I am trying to unpivot the columns into rows. Some sections will have null value.
SELECT RecordKey
,Name
,'Num_of_Sections' = ROW_NUMBER() OVER (PARTITION BY RecordKey ORDER BY ID)
,Product
,Code
FROM (
SELECT RecordKey, Name, Section1_Product, Section1_Code, Section2_Product, Section2_Code FROM Table
) M
UNPITVOT (
Product FOR ID IN (Section1_Product, Section2_Product)
) p
UNPIVOT (
Code FOR CO IN (Section1_Code, Section2_Code)
) c
If I execute with only one column (Product, comment out Code) then I will have 2 values in ID column (1,2). If I run the query with 2 columns then I get 4 values in ID column(1, 2, 3, 4).
may as per my assumption and your data provided we can achieve this using Cross apply and Row_number
declare #Record TABLE
([RecordKey] int,
[Name] varchar(1),
[Section1_Product] varchar(2),
[Section1_Code] int,
[Section2_Product] varchar(2),
[Section2_Code] int)
;
INSERT INTO #Record
([RecordKey], [Name], [Section1_Product], [Section1_Code],[Section2_Product],[Section2_Code])
VALUES
(1, 'a', 'ff', 22,NULL,NULL),
(2, 'b', 'gg', 22,NULL,NULL),
(3, 'c', 'hh', 33,NULL,NULL)
;
With cte as (
Select T.RecordKey,
T.Name,
T.val,
T.val1 from (
select RecordKey,Name,val,val1 from #Record
CROSS APPLY (VALUES
('Section1_Product',Section1_Product),
('Section2_Product',Section2_Product))cs(col,val)
CROSS APPLY (VALUES
('Section1_Code',Section1_Code),
('Section2_Code',Section2_Code))css(col1,val1)
WHERE val is NOT NULL)T
)
Select c.RecordKey,
c.Name,
c.RN,
CASE WHEN RN = 2 THEN NULL ELSE c.val END Product,
c.val1 Code
from (
Select RecordKey,
Name,
ROW_NUMBER()OVER(PARTITION BY val ORDER BY (SELECT NULL))RN,
val,
val1 from cte )C

Consolidating subsets in a table

I have a table in SqlServer 2008 with data of the form
UserID StartWeek EndWeek Type
1 1 3 A
1 4 5 A
1 6 10 A
1 11 13 B
1 14 16 A
2 1 5 A
2 6 9 A
2 10 16 B
I'd like to consolidate/condense the adjacent types so that the resulting table looks like this.
UserID StartWeek EndWeek Type
1 1 10 A
1 11 13 B
1 14 16 A
2 1 9 A
2 10 16 B
Does anyone have any suggestions as to the best way to accomplish this? I've been looking at using Row_number and Partition, but I can't get it to behave exactly as I'd like.
There's probably a neater way to do it, but this produces the correct result
DECLARE #t TABLE
(UserId TINYINT
,StartWeek TINYINT
,EndWeek TINYINT
,TYPE CHAR(1)
)
INSERT #t
SELECT 1,1,3,'A'
UNION SELECT 1,4,5,'A'
UNION SELECT 1,6,10,'A'
UNION SELECT 1,11,13,'B'
UNION SELECT 1,14,16,'A'
UNION SELECT 2,1,5,'A'
UNION SELECT 2,6,9,'A'
UNION SELECT 2,10,16,'B'
;WITH srcCTE
AS
(
SELECT *
,ROW_NUMBER() OVER (PARTITION BY t1.UserID, t1.Type
ORDER BY t1.EndWeek
) AS rn
FROM #t AS t1
)
,recCTE
AS
(
SELECT *
,0 AS grp
FROM srcCTE
WHERE rn = 1
UNION ALL
SELECT s.UserId
,s.StartWeek
,s.EndWeek
,s.TYPE
,s.rn
,CASE WHEN s.StartWeek - 1 = r.EndWeek
THEN r.grp
ELSE r.grp+ 1
END AS GRP
FROM srcCTE AS s
JOIN recCTE AS r
ON r.UserId = s.UserId
AND r.TYPE = s.TYPE
AND r.rn = s.rn - 1
)
SELECT UserId
,MIN(StartWeek) AS StartWeek
,MAX(EndWeek) AS EndWeek
,TYPE
FROM recCTE AS s1
GROUP BY UserId
,TYPE
,grp
Also using a CTE, but in a slightly different way
DECLARE #Consolidate TABLE (
UserID INTEGER, StartWeek INTEGER,
EndWeek INTEGER, Type CHAR(1))
INSERT INTO #Consolidate VALUES (1, 1, 3, 'A')
INSERT INTO #Consolidate VALUES (1, 4, 5, 'A')
INSERT INTO #Consolidate VALUES (1, 6, 10, 'A')
INSERT INTO #Consolidate VALUES (1, 14, 16, 'A')
INSERT INTO #Consolidate VALUES (1, 11, 13, 'B')
INSERT INTO #Consolidate VALUES (2, 1, 5, 'A')
INSERT INTO #Consolidate VALUES (2, 6, 9, 'A')
INSERT INTO #Consolidate VALUES (2, 10, 16, 'B')
;WITH ConsolidateCTE AS
(
SELECT UserID, StartWeek, EndWeek, Type
FROM #Consolidate
UNION ALL
SELECT cte.UserID, cte.StartWeek, c.EndWeek, c.Type
FROM ConsolidateCTE cte
INNER JOIN #Consolidate c ON
c.UserID = cte.UserID
AND c.StartWeek = cte.EndWeek + 1
AND c.Type = cte.Type
)
SELECT UserID, [StartWeek] = MIN(Startweek), EndWeek, Type
FROM (
SELECT UserID, Startweek, [EndWeek] = MAX(EndWeek), Type
FROM ConsolidateCTE
GROUP BY UserID, StartWeek, Type
) c
GROUP BY UserID, EndWeek, Type
ORDER BY 1, 2, 3