Given that I am using Redshift, how would I get the counts for a query that asks:
Given table A and table B, give me all the count of values in Table A for that grouping that aren't in table B;
So if table A and B look like:
Table A
Id | Value
==========
1 | "A"
1 | "B"
2 | "C"
And table B:
Id | Value
==========
1 | "A"
1 | "D"
2 | "C"
I would want:
Id | Count
==========
1 | 1
2 | 0
You can use left join and group by:
select a.id, sum( (b.id is null)::int )
from a left join
b
on a.id = b.id and a.value = b.value
group by a.id;
Use except and subquery
with a as
(
select 1 as id, 'A' as v
union all
select 1,'B'
union all
select 2,'C'
),b as
(
select 1 as id, 'A' as v
union all
select 1,'D'
union all
select 2,'C'
), c as
(
select id,v from a except select id,v from b
)
select id,sum ( (select count(*) from c where c.id=a.id and c.v=a.v))
from a group by id
output
id cnt
1 1
2 0
online demo which will work in redshift
Related
Given a table with 2 columns a, b.
I want to select rows that for a given a, I can have different values of b.
In this example, I want the first 2 lines
a | b
-----
1 | 1
1 | 2
2 | 1
2 | 1
3 | 1
Try this:
SELECT t1.*
FROM mytable AS t1
JOIN (
SELECT a
FROM mytable
GROUP BY a
HAVING COUNT(DISTINCT b) > 1
) AS t2 ON t1.a = t2.a
You didn't mention your DBMS, but in Oracle you can do:
select a,b
from (
select a,b,
count(distinct b) over (partition by a) as num_b
from the_table
) t
where num_b > 1
Unfortunately Postgres or SQL Server do not support distinct for window functions.
In a table there are two columns:
-----------
| A | B |
-----------
| 1 | 5 |
| 2 | 1 |
| 3 | 2 |
| 4 | 1 |
-----------
Want a table where if A=B then
-------------------
|Match | notMatch|
-------------------
| 1 | 5 |
| 2 | 3 |
| Null | 4 |
-------------------
How can i do this?
I tried something which shows the Matched part
select distinct C.A as A from Table c inner join Table d on c.A=d.B
Try this:
;WITH TempTable(A, B) AS(
SELECT 1, 5 UNION ALL
SELECT 2, 1 UNION ALL
SELECT 3, 2 UNION ALL
SELECT 4, 1
)
,CTE(Val) AS(
SELECT A FROM TempTable UNION ALL
SELECT B FROM TempTable
)
,Match AS(
SELECT
Rn = ROW_NUMBER() OVER(ORDER BY Val),
Val
FROM CTE c
GROUP BY Val
HAVING COUNT(Val) > 1
)
,NotMatch AS(
SELECT
Rn = ROW_NUMBER() OVER(ORDER BY Val),
Val
FROM CTE c
GROUP BY Val
HAVING COUNT(Val) = 1
)
SELECT
Match = m.Val,
NotMatch= n.Val
FROM Match m
FULL JOIN NotMatch n
ON n.Rn = m.Rn
Try with EXCEPT, MINUS and INTERSECT Statements.
like this:
SELECT A FROM TABLE1 INTERSECT SELECT B FROM TABLE1;
You might want this:
SELECT DISTINCT
C.A as A
FROM
Table c
LEFT OUTER JOIN
Table d
ON
c.A=d.B
WHERE
d.ID IS NULL
Please Note that I use d.ID as an example because I don't see your schema. An alternate is to explicitly state all d.columns IS NULL in WHERE clause.
Your requirement is kind of - let's call it - interesting. Here is a way to solve it using pivot. Personally I would have chosen a different table structure and another way to select data:
Test data:
DECLARE #t table(A TINYINT, B TINYINT)
INSERT #t values
(1,5),(2,1),
(3,2),(4,1)
Query:
;WITH B AS
(
( SELECT A FROM #t
EXCEPT
SELECT B FROM #t)
UNION ALL
( SELECT B FROM #t
EXCEPT
SELECT A FROM #t)
), A AS
(
SELECT A val
FROM #t
INTERSECT
SELECT B
FROM #t
), combine as
(
SELECT val, 'A' col, row_number() over (order by (select 1)) rn FROM A
UNION ALL
SELECT A, 'B' col, row_number() over (order by (select 1)) rn
FROM B
)
SELECT [A], [B]
FROM combine
PIVOT (MAX(val) FOR [col] IN ([A], [B])) AS pvt
Result:
A B
1 3
2 4
NULL 5
I have a simple table with two columns, like the one below:
Id | Name
0 | A
1 | A
2 | B
3 | B
4 | C
5 | D
6 | E
7 | E
I want to make a SQL query which will count how many times each "Name" appears on the table. However, I need a few of these values to count as if they were the same. For example, a normal group by query would be:
select Name, count(*)
from table
group by Name
The above query would produce the result:
Name | Count
A | 2
B | 2
C | 1
D | 1
E | 2
but I need the query to count "A" and "B" as if they were only "A", and to count "D" and "E" as if they were only "D", so that the result would be like:
Name | Count
A | 4 // (2 "A"s + 2 "B"s)
C | 1
D | 3 // (1 "D" + 2 "E"s)
How can I make this kind of query?
You can make translation with case. Also, you can use subquery or CTE so you don't have to repeat yourself:
with cte as (
select
case Name
when 'B' then 'A'
when 'E' then 'D'
else Name
end as Name
from table
)
select Name, count(*)
from cte
group by Name
or with with online translation table:
select
isnull(R.B, t.Name), count(*)
from table as t
left outer join (
select 'A', 'B' union all
select 'E', 'D'
) as R(A, B) on R.A = t.Name
group by isnull(R.B, t.Name)
If you need A and B, D and E, to count the same, you can build a query like this:
SELECT
CASE Name WHEN 'B' THEN 'A' WHEN 'E' THEN 'D' ELSE Name END as Name
, COUNT(*)
FROM table
GROUP BY CASE Name WHEN 'B' THEN 'A' WHEN 'E' THEN 'D' ELSE Name END
Demo on sqlfiddle.
With a layer of abstraction and a CASE (SQL Fiddle example):
;WITH x AS
(
SELECT CASE Name WHEN 'B' THEN 'A'
WHEN 'E' THEN 'D'
ELSE Name
END AS Name
FROM Table1
)
SELECT Name, COUNT(1)
FROM x
GROUP BY Name
With a translation table (SQL Fiddle):
CREATE TABLE Translate(FromName char(1), ToName char(1));
INSERT INTO Translate VALUES ('B', 'A'), ('E', 'D');
SELECT COALESCE(t.ToName, a.Name) Name, COUNT(1)
FROM Table1 a
LEFT OUTER JOIN Translate t ON a.Name = t.FromName
GROUP BY COALESCE(t.ToName, a.Name)
FWIW, you can also do this with a VALUES derived table instead of a real table (SQL Fiddle):
SELECT COALESCE(t.ToName, a.Name) Name, COUNT(1)
FROM Table1 a
LEFT OUTER JOIN
(
VALUES ('B', 'A'),
('E', 'D')
) t(FromName, ToName) ON a.Name = t.FromName
GROUP BY COALESCE(t.ToName, a.Name)
this works
select t.a,count(t.id) from (
select case name when 'A' then 'A' when 'B' then 'A'
when 'C' then 'C' when 'D' then 'C'
when 'D' then 'D' when 'E' then 'D' end as A,id
from test) as t
group by A;
I have these tables:
Table A
Num Letter
1 A
2 B
3 C
Table B
Num Letter
2 C
3 D
4 E
I want to union these two tables, but I only want each number to appear once. If the same number appears in both tables, I want it from Table B instead of table A.
Result
Num Letter
1 A
2 C
3 D
4 E
How could I accomplish this? A union will keep duplicates and an intersect would only catch the same rows -- I consider a row a duplicate when it has the same number, regardless of the letter.
Try this: http://www.sqlfiddle.com/#!4/0b796/1
with a as
(
select Num, 'A' as src, Letter
from tblA
union
select Num, 'B' as src, Letter
from tblB
)
select
Num
,case when count(*) > 1 then
min(case when src = 'B' then Letter end)
else
min(Letter)
end as Letter
from a
group by Num
order by Num;
Output:
| NUM | LETTER |
----------------
| 1 | A |
| 2 | C |
| 3 | D |
| 4 | E |
And another one:
SELECT COALESCE(b.num, a.num) num, COALESCE(b.letter, a.letter) letter
FROM a FULL JOIN b ON a.num = b.num
ORDER BY 1;
With your data:
WITH a AS
(SELECT 1 num, 'A' letter FROM dual
UNION ALL SELECT 2, 'B' FROM dual
UNION ALL SELECT 3, 'C' FROM dual),
b AS
(SELECT 2 num, 'C' letter FROM dual
UNION ALL SELECT 3, 'D' FROM dual
UNION ALL SELECT 4, 'E' FROM dual)
SELECT COALESCE(b.num, a.num) num, COALESCE(b.letter, a.letter) letter
FROM a FULL JOIN b ON a.num = b.num
ORDER BY 1;
NUM L
---------- -
1 A
2 C
3 D
4 E
The efficiency might be lacking, but it produces the correct answer.
select nums.num, coalesce(b.letter, a.letter)
from
(select num from b
union
select num from a) nums
left outer join b
on (b.num = nums.num)
left outer join a
on (a.num = nums.num);
Or you can use Oracle-specific technique to make the code shorter: http://www.sqlfiddle.com/#!4/0b796/11
with a as
(
select Num, 'A' as src, Letter
from tblA
union
select Num, 'B' as src, Letter
from tblB
)
select Num, min(Letter) keep(dense_rank first order by src desc) as Letter
from a
group by Num
order by Num;
Output:
| NUM | LETTER |
----------------
| 1 | A |
| 2 | C |
| 3 | D |
| 4 | E |
The code works regardless of min(letter) or max(letter), it has the same output, it gives the same output. Important is you use keep dense_rank. Another important thing is, the order matter, we use order by src desc to give priority to source table B when keeping a row.
And to really make it shorter, use keep dense_rank last, and omit the desc on order by, asc is the default anyway http://www.sqlfiddle.com/#!4/0b796/12
with a as
(
select Num, 'A' as src, Letter
from tblA
union
select Num, 'B' as src, Letter
from tblB
)
select Num, min(Letter) keep(dense_rank last order by src) as Letter
from a
group by Num
order by Num;
Again, using min or max on Letter doesn't matter, as long as your keep dense_rank get the prioritized/preferred row
Another option is to combine the UNION and MINUS commands as follows:
SELECT
NUM, LETTER
FROM
TABLE B
UNION
( SELECT
NUM, LETTER
FROM
TABLE A
WHERE
NUM IN (SELECT
NUM
FROM
TABLE A
MINUS
SELECT
NUM
FROM
TABLE B ))
SELECT A.*
FROM A
WHERE A.NUM NOT IN
(SELECT A.NUM
FROM B
WHERE A.NUM=B.NUM
AND B.NUM IS NOT NULL
AND A.NUM IS NOT NULL
)
UNION
SELECT * FROM B;
Say I have the following table:
MyTable
---------
| 1 | A |
| 2 | A |
| 3 | A |
| 4 | B |
| 5 | B |
| 6 | B |
| 7 | A |
| 8 | A |
---------
I need the sql query to output the following:
---------
| 3 | A |
| 3 | B |
| 2 | A |
---------
Basically I'm doing a group by but only for rows which are together in the sequence. Any ideas?
Note that the database is on sql server 2008. There is a post on this topic however it uses oracle's lag() function.
This is known as the "islands" problem. Using Itzik Ben Gan's approach:
;WITH YourTable AS
(
SELECT 1 AS N, 'A' AS C UNION ALL
SELECT 2 AS N, 'A' AS C UNION ALL
SELECT 3 AS N, 'A' AS C UNION ALL
SELECT 4 AS N, 'B' AS C UNION ALL
SELECT 5 AS N, 'B' AS C UNION ALL
SELECT 6 AS N, 'B' AS C UNION ALL
SELECT 7 AS N, 'A' AS C UNION ALL
SELECT 8 AS N, 'A' AS C
),
T
AS (SELECT N,
C,
DENSE_RANK() OVER (ORDER BY N) -
DENSE_RANK() OVER (PARTITION BY C ORDER BY N) AS Grp
FROM YourTable)
SELECT COUNT(*),
C
FROM T
GROUP BY C,
Grp
ORDER BY MIN(N)
this will work for you...
SELECT
Total=COUNT(*), C
FROM
(
SELECT
NGroup = ROW_NUMBER() OVER (ORDER BY N) - ROW_NUMBER() OVER (PARTITION BY C ORDER BY N),
N,
C
FROM MyTable
)RegroupedTable
GROUP BY C,NGroup
Just for fun, without any SQL-specific functions and NOT assuming that the ID column is monotonically increasing:
WITH starters(name, minid, maxid) AS (
SELECT
a.name, MIN(a.id), MAX(a.id)
FROM
mytable a RIGHT JOIN
mytable b ON
(a.name <> b.name AND a.id < b.id)
WHERE
a.id IS NOT NULL
GROUP BY
a.name
),
both(name, minid, maxid) AS (
SELECT
name, minid, maxid
FROM
starters
UNION ALL
SELECT
name, MIN(id), MAX(id)
FROM
mytable
WHERE
id > (SELECT MAX(maxid) from starters)
GROUP BY
name
)
SELECT
COUNT(*), m.name, minid
FROM
both INNER JOIN
mytable m ON
id BETWEEN minid AND maxid
GROUP BY
m.name, minid
Result (ignore the midid column):
(No column name) name minid
3 A 1
3 B 4
2 A 7