| Store_ID | item |
+ ----------+----------+
| 6 | Soda |
| 8 | Chips |
| 9 | Candy |
| 9 | Soda |
I basically have the above table. I want to make Store_id the rows and item the columns and have a flag as the values of the table. This is basically a user-interactions matrix/utility matrix.
How can I convert this Table to another Table of the aforementioned form?
Output:
store_id soda chips candy
-------------------------
6 1 0 0
8 0 1 0
9 1 0 1
One approach is to use a dynamic pivot table. Find an example below:
--- QUERY ---
-- Build list of unique item names
-- CAUTION: Consider using a domain table instead to retrieve the unique item list for performance reasons in case the store table is huge.
DECLARE #Columns AS VARCHAR(MAX)
SELECT
#Columns = COALESCE(#Columns + ', ','') + QUOTENAME(item)
FROM
(SELECT DISTINCT item FROM store) AS B
ORDER BY
B.item
-- Build SQL query
DECLARE #SQL AS VARCHAR(MAX)
SET #SQL = 'SELECT store_id, ' + #Columns + '
FROM
(
SELECT store_id, item
FROM store
) as PivotData
PIVOT
(
COUNT(item)
FOR item IN (' + #Columns + ')
) AS PivotResult
ORDER BY store_id';
-- Execute query
EXEC(#SQL)
--- RESULT ---
store_id Candy Chips Soda
----------- ----------- ----------- -----------
6 0 0 1
8 0 1 0
9 1 0 1
(3 rows affected)
Tested on Microsoft SQL Server 2019 (RTM-GDR) (KB4517790) - 15.0.2070.41 (X64)
wit that table design I only come with this solution
with stores as (
select Store_ID = 6, item = 'soda'
union all
select 8, 'candy'
union all
select 9, 'candy'
union all
select 9, 'soda'
union all
select 9, 'candy'
union all
select 9, 'soda'
union all
select 1, 'chips')
select store_id, soda = SUM(CASE WHEN item = 'soda' then 1 else 0 end),
candy = SUM(CASE WHEN item = 'candy' then 1 else 0 end),
chips = SUM(CASE WHEN item = 'chips' then 1 else 0 end)
from stores
group by store_id, item
Related
I am trying to get some pivot some year data to give me a cumulative total as the years increase and then get the top 5.
I have tried using a SUM on the total, for the years in the year column, but it doesn't appear to be increasing. The issue I think is due to some null values potentially?
The data in the table currently appears like
Name | ApplesEaten | Year
Bob | 2 | 2012
Bob | 5 | 2016
Elvis| 1 | 2017
Elvis| 2 | 2012
Sam | 8 | 2008
Elvis| 6 | 2004
Sam | 24 | 2019
Sarah| 14 | 2015
Bob | 6 | 2005
Rachel| 12 | 2010
Rachel| 10 | 2008
Bob | 82 | 2006
But im aiming to get it like
Name| 2004 | 2005 | 2006 .....
Bob | 0 | 6 | 88
The next issue, is getting the top 5 in total after the pivot has been done!
Is this what you want?
select top (5) name,
sum(case when year <= 2005 then ApplesEaten else 0 end) as apples_2005,
sum(case when year <= 2006 then ApplesEaten else 0 end) as apples_2006,
. . .
sum(case when year <= 2019 then ApplesEaten else 0 end) as apples_2019
from t
group by name
order by sum(ApplesEaten) desc
you can use case when
select top 5 name, max(case when year=2004 then ApplesEaten end ) [2004],
max(case when year=2005 then ApplesEaten end ) [2005],
max(case when year=2006 then ApplesEaten end ) [2006],
.......................
from table_name group by name
order by sum(ApplesEaten ) desc
Sample data
IF OBJECT_ID('tempdb..#Temp') IS NOT NULL
DROP TABLE #Temp
;WITH CTE(Name , ApplesEaten , [Year])
AS
(
SELECT 'Bob' , 2 , 2012 UNION ALL
SELECT 'Bob' , 5 , 2016 UNION ALL
SELECT 'Elvis', 1 , 2017 UNION ALL
SELECT 'Elvis', 2 , 2012 UNION ALL
SELECT 'Sam' , 8 , 2008 UNION ALL
SELECT 'Elvis', 6 , 2004 UNION ALL
SELECT 'Sam' , 24 , 2019 UNION ALL
SELECT 'Sarah', 14 , 2015 UNION ALL
SELECT 'Bob' , 6 , 2005 UNION ALL
SELECT 'Rachel', 12 , 2010 UNION ALL
SELECT 'Rachel', 10 , 2008 UNION ALL
SELECT 'Bob' , 82 , 2006
)
SELECT Name ,
ApplesEaten ,
[Year]
INTO #Temp
FROM CTE
Sql script using Dynamic Sql
DECLARE #Columns nvarchar(max),
#IsnullColumns nvarchar(max),
#Sql nvarchar(max)
SELECT #Columns = STUFF((SELECT DISTINCT ', '+QUOTENAME([Year]) FROM #Temp FOR XML PATH ('')),1,1,'')
SELECT #IsnullColumns = STUFF((SELECT DISTINCT ', '+'ISNULL(MAX('+QUOTENAME([Year])+'),''0'') AS apples_' +CAST(([Year]) AS VARCHAR(20))
FROM #Temp FOR XML PATH ('')),1,1,'')
SET #Sql ='SELECT TOp 5 Name,'+#IsnullColumns+'
FROM
(
SELECT *,SUM(ApplesEaten) OVER(PARTITION BY Name ORDER BY [Year]) AS SumApplesEaten FROM #Temp
) AS PVT
PIVOT
(
MAX(SumApplesEaten) FOR [Year] IN ('+#Columns+')
) AS PVT
GROUP BY Name
ORDER BY Name'
PRINT #Sql
EXEC (#Sql)
I am trying to transpose rows to columns but I didn't find any good answers.
Here is an example of what I want:
Input tables:
TABLE A
ID | NAME
1 | BOB
2 | JIM
3 | ROB
TABLE B
ID | CLUB
1 | 2
1 | 3
1 | 4
2 | 2
2 | 1
3 | 5
OUTPUT will be:
ID | CLUB1 | CLUB2 | CLUB3
1 | 2 | 3 | 4
2 | 2 | 1 |
3 | 5 | |
You need to enumerate the values to pivot them:
select id,
max(case when seqnum = 1 then club end) as club_1,
max(case when seqnum = 2 then club end) as club_2,
max(case when seqnum = 3 then club end) as club_3
from (select b.*,
row_number() over (partition by id order by club) as seqnum
from b
) b
group by id;
use conditional aggregation
select id,
max(case when id=1 then club end) club1,
max(case when id=2 then club end) club2,
max(case when id=3 then club end) club3
from tablename
group by id
use case when
select a.id,max(case when name='BOB' then CLUB end) ,
max(case when name='JIM' then CLUB end),
max(case when name='ROB' then CLUB end)
tablea a join tableb b on a.id=b.id group by a.id
Sample Data
IF OBJECT_ID('tempdb..#TempTab')IS NOT NULL
DROP TABLE #TempTab
;WITH CTE (ID,CLUB)
AS
(
SELECT 1 , 2 UNION ALL
SELECT 1 , 3 UNION ALL
SELECT 1 , 4 UNION ALL
SELECT 2 , 2 UNION ALL
SELECT 2 , 1 UNION ALL
SELECT 3 , 5
)
SELECT ID,
CLUB,
'CLUB'+CAST(ROW_NUMBER()OVER(PARTITION BY ID ORDER BY ID) AS VARCHAR) AS CLUBData
INTO #TempTab
FROM CTE
Dynamic sql
DECLARE #Column nvarchar(1000),#Column2 nvarchar(max),
#Sql nvarchar(max)
SELECT #Column =STUFF((SELECT DISTINCT ', '+QUOTENAME(CLUBData)
FROM #TempTab FOR XML PATH ('')),1,1,'')
SET #Sql = 'SELECT Id,'+#Column +'
FROM
(
SELECT * FROM #TempTab
) AS SRc
PIVOT
(
MAX(CLUB) FOR CLUBData IN ('+#Column+')
) AS pvt
'
PRINT #Sql
EXEC (#Sql)
Result
Id CLUB1 CLUB2 CLUB3
-------------------------
1 3 4 2
2 1 2 NULL
3 5 NULL NULL
My table looks for example like this:
Name date result
A 2012-01-01 1
A 2012-02-01 2
B 2013-01-01 1
...
For a full example: http://sqlfiddle.com/#!3/0226b/1
At the moment I have a working query that counts the rows by person and year: http://sqlfiddle.com/#!3/0226b/3
This is perfect, but what I want is some extra information for 2014. i need to count how many rows I have for every result.
something like this:
NAME 1 2 3 2014 2013 2012 TOTAL
Person B 4 0 2 6 2 2 10
Person A 2 1 1 4 3 4 11
Person C 1 1 1 3 1 0 4
Even better would be that I give the result-columns a good name (1 = lost, 2= draw, 3=won):
NAME lost draw won 2014 2013 2012 TOTAL
Person B 4 0 2 6 2 2 10
Person A 2 1 1 4 3 4 11
Person C 1 1 1 3 1 0 4
I tried to add some extra code, like:
select #colsResult
= STUFF((SELECT ',' + QUOTENAME(result)
from list
group by result
order by result
FOR XML PATH(''), TYPE
).value('.', 'NVARCHAR(MAX)')
,1,1,'')
I have as result:
,[1]
,[2]
,[3]
But if I run the whole code I get an error, invallid column name...
Since you have two columns that you now want to PIVOT, you'll first have to unpivot those columns and then convert those values into the new columns.
Starting in SQL Server 2005, you could use CROSS APPLY to unpivot the columns. The basic syntax will be similar to:
select
name,
new_col,
total
from
(
select name,
dt = year(date),
result,
total = count(*) over(partition by name)
from list
) d
cross apply
(
select 'dt', dt union all
select 'result', result
) c (old_col_name, new_col)
See SQL Fiddle with Demo. This query gets you a list of names, with the "new columns" and then the Total entries for each name.
| NAME | NEW_COL | TOTAL |
|----------|---------|-------|
| Person A | 2012 | 11 |
| Person A | 1 | 11 |
| Person A | 2012 | 11 |
| Person A | 2 | 11 |
You'll see that the dates and the results are now both stored in "new_col". These values will now be used as the new column names. If you have a limited number of columns, then you would simply hard-code the query:
select name, lost = [1],
draw=[2], won = [3],
[2014], [2013], [2012], Total
from
(
select
name,
new_col,
total
from
(
select name,
dt = year(date),
result,
total = count(*) over(partition by name)
from list
) d
cross apply
(
select 'dt', dt union all
select 'result', result
) c (old_col_name, new_col)
) src
pivot
(
count(new_col)
for new_col in([1], [2], [3], [2014], [2013], [2012])
) piv
order by [2014];
See SQL Fiddle with Demo
Now since your years are dynamic, then you'll need to use dynamic sql. But it appears that you have 3 results and potentially multiple years - so I'd use a combination of static/dynamic sql to make this easier:
DECLARE #cols AS NVARCHAR(MAX),
#query AS NVARCHAR(MAX),
#orderby nvarchar(max)
select #cols
= STUFF((SELECT ',' + QUOTENAME(year(date))
from list
group by year(date)
order by year(date) desc
FOR XML PATH(''), TYPE
).value('.', 'NVARCHAR(MAX)')
,1,1,'')
select #orderby = 'ORDER BY ['+cast(year(getdate()) as varchar(4)) + '] desc'
set #query = 'SELECT name, lost = [1],
draw=[2], won = [3],' + #cols + ', Total
from
(
select
name,
new_col,
total
from
(
select name,
dt = year(date),
result,
total = count(*) over(partition by name)
from list
) d
cross apply
(
select ''dt'', dt union all
select ''result'', result
) c (old_col_name, new_col)
) x
pivot
(
count(new_col)
for new_col in ([1], [2], [3],' + #cols + ')
) p '+ #orderby
exec sp_executesql #query;
See SQL Fiddle with Demo. This gives a result:
| NAME | LOST | DRAW | WON | 2014 | 2013 | 2012 | TOTAL |
|----------|------|------|-----|------|------|------|-------|
| Person B | 7 | 1 | 2 | 6 | 2 | 2 | 10 |
| Person A | 5 | 3 | 3 | 4 | 3 | 4 | 11 |
| Person C | 2 | 1 | 1 | 3 | 1 | 0 | 4 |
If you want to only filter the result columns for the current year, then you can perform this filtering a variety of ways but the easiest you be to include a filter in the unpivot. The hard-coded version would be:
select name, lost = [1],
draw=[2], won = [3],
[2014], [2013], [2012], Total
from
(
select
name,
new_col,
total
from
(
select name,
dt = year(date),
result,
total = count(*) over(partition by name)
from list
) d
cross apply
(
select 'dt', dt union all
select 'result', case when dt = 2014 then result end
) c (old_col_name, new_col)
) src
pivot
(
count(new_col)
for new_col in([1], [2], [3], [2014], [2013], [2012])
) piv
order by [2014] desc;
See SQL Fiddle with Demo. Then the dynamic sql version would be:
DECLARE #cols AS NVARCHAR(MAX),
#query AS NVARCHAR(MAX),
#orderby nvarchar(max),
#currentYear varchar(4)
select #currentYear = cast(year(getdate()) as varchar(4))
select #cols
= STUFF((SELECT ',' + QUOTENAME(year(date))
from list
group by year(date)
order by year(date) desc
FOR XML PATH(''), TYPE
).value('.', 'NVARCHAR(MAX)')
,1,1,'')
select #orderby = 'ORDER BY ['+ #currentYear + '] desc'
set #query = 'SELECT name, lost = [1],
draw=[2], won = [3],' + #cols + ', Total
from
(
select
name,
new_col,
total
from
(
select name,
dt = year(date),
result,
total = count(*) over(partition by name)
from list
) d
cross apply
(
select ''dt'', dt union all
select ''result'', case when dt = '+#currentYear+' then result end
) c (old_col_name, new_col)
) x
pivot
(
count(new_col)
for new_col in ([1], [2], [3],' + #cols + ')
) p '+ #orderby
exec sp_executesql #query;
See SQL Fiddle with Demo. This version will give a result:
| NAME | LOST | DRAW | WON | 2014 | 2013 | 2012 | TOTAL |
|----------|------|------|-----|------|------|------|-------|
| Person B | 4 | 0 | 2 | 6 | 2 | 2 | 10 |
| Person A | 2 | 1 | 1 | 4 | 3 | 4 | 11 |
| Person C | 1 | 1 | 1 | 3 | 1 | 0 | 4 |
I need to alter view that show user count(ScheduleID) by period on same row. Now the Period table content can grow and contain more than 3 periods.
The actual SQL is:
SELECT r.Code,
SUM(CASE WHEN s.PeriodID=1 THEN 1 ELSE 0 END) AS PeriodID1,
SUM(CASE WHEN s.PeriodID=2 THEN 1 ELSE 0 END) AS PeriodID2,
SUM(CASE WHEN s.PeriodID=3 THEN 1 ELSE 0 END) AS PeriodID3,
SUM(CASE WHEN s.PeriodID IN (1,2,3) THEN 1 ELSE 0 END) AS Total
FROM Schedules s
JOIN Periods p ON p.PeriodID = s.PeriodID
JOIN Resources r ON r.ResourceID = s.ResourceID
GROUP BY r.Code;
Example data:
Table Schedules
ScheduleID(int) ResourceID(int) ResourceCode(varchar 4) PeriodID(int)
1 1 AA 1
2 1 AA 3
3 1 AA 3
4 2 BB 1
5 3 CC 1
6 1 AA 1
7 3 CC 2
8 3 CC 3
9 2 BB 1
10 2 BB 2
11 2 BB 3
12 1 AA 3
Table Periods
PeriodID(int) Code (varchar 4)
1 P1
2 P2
3 P3
4 P4
5 P5
6 P6
7 P7
8 P8
The result I need is:
ResourceCode PeriodID1 PeriodID2 PeriodID3 ... PeriodID8 TOTAL
AA 2 0 3 0 5
BB 2 1 1 0 4
CC 1 1 1 0 3
The Periods table content is now dynamic.
The database version is an Microsoft SQL 2008
I like to know if is possible to do that without create stored procedure...and doing this in one query like this:
SELECT *
FROM (
SELECT R.Code, P.PeriodID, COUNT(S.ScheduleID) AS RPCount
FROM Schedules S INNER JOIN Periods P ON S.PeriodID = P.PeriodID
JOIN Resources R ON S.ResourceID = R.ResourceID
WHERE S.ResourceID is not null
GROUP BY R.Code, P.PeriodID
) as data
PIVOT
(
SUM(RPCount)
--FOR PeriodID IN ([1],[2],[3])
FOR PeriodID IN (SELECT PeriodID From Periods)
)AS pvt
ORDER BY Code
Since you are using SQL Server then you can implement the PIVOT function and if you have an unknown number of period values, then you will need to use dynamic SQL:
DECLARE #cols AS NVARCHAR(MAX),
#query AS NVARCHAR(MAX)
select #cols = STUFF((SELECT distinct ',' + QUOTENAME('PeriodId'+cast(periodid as varchar(10)))
from Periods
FOR XML PATH(''), TYPE
).value('.', 'NVARCHAR(MAX)')
,1,1,'')
set #query = 'SELECT resourcecode, ' + #cols + ' , Total
from
(
select s.resourcecode,
''PeriodId''+cast(p.periodid as varchar(10)) period,
count(*) over(partition by s.resourcecode) Total
from periods p
left join schedules s
on p.periodid = s.periodid
) x
pivot
(
count(period)
for period in (' + #cols + ')
) p
where resourcecode is not null
order by resourcecode'
execute(#query)
See SQL Fiddle with Demo. This gives a result:
| RESOURCECODE | PERIODID1 | PERIODID2 | PERIODID3 | PERIODID4 | PERIODID5 | PERIODID6 | PERIODID7 | PERIODID8 | TOTAL |
------------------------------------------------------------------------------------------------------------------------
| AA | 2 | 0 | 3 | 0 | 0 | 0 | 0 | 0 | 5 |
| BB | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 4 |
| CC | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 3 |
Based on your previous question that was tagged with MySQL, I am assuming you are using MySQL as the database. If so, then you do not have a PIVOT function so you will have to use an aggregate function with a CASE expression to transform the rows of data into columns.
If your column values are known, then you can hard-code the query:
select resourcecode,
sum(case when period = 'PeriodId1' then 1 else 0 end) PeriodId1,
sum(case when period = 'PeriodId2' then 1 else 0 end) PeriodId2,
sum(case when period = 'PeriodId3' then 1 else 0 end) PeriodId3,
sum(case when period = 'PeriodId4' then 1 else 0 end) PeriodId4,
sum(case when period = 'PeriodId5' then 1 else 0 end) PeriodId5,
sum(case when period = 'PeriodId6' then 1 else 0 end) PeriodId6,
sum(case when period = 'PeriodId7' then 1 else 0 end) PeriodId7,
sum(case when period = 'PeriodId8' then 1 else 0 end) PeriodId8,
count(*) Total
from
(
select concat('PeriodId', p.periodid) Period,
s.resourcecode
from periods p
left join schedules s
on p.periodid = s.periodid
) d
where resourcecode is not null
group by resourcecode;
See SQL Fiddle with Demo. But if the values will be unknown or dynamic then you will need to use a prepared statement to generate a sql string to execute:
SET #sql = NULL;
SELECT
GROUP_CONCAT(DISTINCT
CONCAT(
'sum(CASE WHEN period = ''',
concat('PeriodId', periodid),
''' THEN 1 else 0 END) AS `',
concat('PeriodId', periodid), '`'
)
) INTO #sql
FROM periods;
SET #sql
= CONCAT('SELECT resourcecode, ', #sql, ' , count(*) Total
from
(
select concat(''PeriodId'', p.periodid) Period,
s.resourcecode
from periods p
left join schedules s
on p.periodid = s.periodid
) d
where resourcecode is not null
group by resourcecode');
PREPARE stmt FROM #sql;
EXECUTE stmt;
DEALLOCATE PREPARE stmt;
See SQL Fiddle with Demo.
Use PIVOT
try this
SELECT *
FROM (
SELECT
S.ResourceCode ,
P.PeriodID AS period,
COUNT(*) AS PCount
FROM Schedules S INNER JOIN Periods P ON S.PeriodID =P.PeriodID
GROUP BY S.ResourceCode ,P.PeriodID
) as s
PIVOT
(
PCount,
FOR [period] IN (SELECT DISTINCT PeriodID From Periods)
)AS pivot
Please try below code for MS Sql server:
DECLARE #column VARCHAR(MAX), #SumQuery VARCHAR(MAX)
SELECT
#column = COALESCE(#column + '], [', '')+ CAST(PeriodID as nvarchar(10)),
#SumQuery = COALESCE(#SumQuery + ']+[', '')+ CAST(PeriodID as nvarchar(10))
FROM
Periods
GROUP BY PeriodID
EXEC ('select *, ['+#SumQuery+'] as [Total] From
(
select * From Schedules
)up
pivot (count(ScheduleID) for PeriodID in (['+#column+'])) as pvt')
I have a table in my database with the following structure.
ID COMPANY_ID Status
-----------------------
1 10 1
2 10 2
3 12 2
4 12 2
5 12 1
6 13 3
7 14 3
8 14 3
9 10 1
10 10 2
I want to group my results on company ID and count each status and list them as separate columns.
i.e.
COMPANY_ID Status 1 Status 2 Status 3
-------------------------------------------
10 2 2 0
12 1 2 0
13 0 0 1
14 0 0 2
My question is how do I get the results above from my table? and probably join in with the company table.
Tried several possibilities, but didn't get the results.
select company_id
, count(case when status = 1 then 1 end) as [Status 1]
, count(case when status = 2 then 1 end) as [Status 2]
, count(case when status = 3 then 1 end) as [Status 3]
from YourTable
group by
company_id
This type of data transformation is known as a PIVOT. There are several ways that you are pivot the data.
You can use an aggregate function with a CASE expression:
select company_id,
sum(case when status = 1 then 1 else 0 end) status1,
sum(case when status = 2 then 1 else 0 end) status2,
sum(case when status = 3 then 1 else 0 end) status3
from yourtable
group by company_id;
See SQL Fiddle with Demo
Starting in SQL Server 2005+ you can use the PIVOT function:
select company_id,
[1] as Status1,
[2] as Status2,
[3] as Status3
from
(
select company_id, status
from yourtable
)src
pivot
(
count(status)
for status in ([1], [2], [3])
) piv
See SQL Fiddle with Demo.
The two versions above work well if you have a known number of values to transform into columns. But if it is unknown, then you can use dynamic SQL to generate the result:
DECLARE #cols AS NVARCHAR(MAX),
#query AS NVARCHAR(MAX)
select #cols = STUFF((SELECT distinct ',' + QUOTENAME('Status'+cast(status as varchar(10)))
from yourtable
FOR XML PATH(''), TYPE
).value('.', 'NVARCHAR(MAX)')
,1,1,'')
set #query = 'SELECT company_id,' + #cols + ' from
(
select company_id, ''Status''+cast(status as varchar(10)) Status
from yourtable
) x
pivot
(
count(Status)
for Status in (' + #cols + ')
) p '
execute(#query)
See SQL Fiddle with Demo.
All give the result:
| COMPANY_ID | STATUS1 | STATUS2 | STATUS3 |
--------------------------------------------
| 10 | 2 | 2 | 0 |
| 12 | 1 | 2 | 0 |
| 13 | 0 | 0 | 1 |
| 14 | 0 | 0 | 2 |