I am struggling with a PostgreSQL query to select the top 3 records by each category. I have 3 tables (as given below) and data,
geography:
formulary:
formulary_controller:
I want to select the top 3 formularies order by lives desc from each territory under a region.
The query I came up with so far is,
select
t.name territory, f.name formulary, sum(f.lives) lives
from formulary f join geography t on f.territory_id = t.id
where t.parent_id = '1'
group by t.name, f.name
order by lives desc, territory;
If I apply limit 3 top above query will give me the top 3 from all territories, but I want to select the top 3 formularies from each territory under the keystone region.
Queries to create a table and load dummy data:
create table formulary_controller
(
id SERIAL primary key,
name varchar(300)
);
create table geography
(
id SERIAL primary key,
name varchar(250),
parent_id integer references geography(id)
);
create table formulary
(
id SERIAL primary key,
name varchar(300),
lives integer,
controller_id integer references formulary_controller(id),
territory_id integer references geography(id)
);
insert into formulary_controller (id, name)
values(1, 'cont1'), (2, 'cont2');
insert into geography (id, name, parent_id)
values
(1, 'keystone', null),
(2, 'pittsburgh', 1),
(3, 'Baltimore', 1);
insert into formulary
(name, lives, controller_id, territory_id)
values
('PA FRM 1', 200, 1, 2),
('PA FRM 2', 1400, 1, 2),
('PA FRM 3', 1300, 1, 2),
('PA FRM 4', 100, 1, 2),
('PA FRM 5', 2430, 1, 2),
('BA FRM 1', 100, 2, 3),
('BA FRM 2', 2300, 2, 3),
('BA FRM 3', 1200, 2, 3),
('BA FRM 4', 1650, 2, 3),
('BA FRM 5', 1200, 2, 3);
you can find top 3 territory_id by using below query using row_number()
with cte (select a.*,
row_number() over(partition by territory_id order by lives desc) rn
from formulary a
) select cte.* from cte where rn<=3
You can try the below - DEMO HERE
select * from
(
select
t.name territory, f.name formulary, sum(f.lives) lives,
row_number() over(partition by t.name order by sum(f.lives) desc) as rn
from formulary f join geography t on f.territory_id = t.id
where t.parent_id = '1'
group by t.name,f.name
)A where rn<=3
Related
Here are the tables
Table: Status
ID, StatusDesc
1, New
2, Active
3, Cancelled
4, Complete
Table: Order (foreign key relationship with Status table above)
ID, OrderNumber, StatusID
1, 1001 , 1
2, 1002, 1
3, 1003, 2
4, 1004, 3
5, 1500, 4
Table: LineItem(foreign key relationship with Order and Status tables above)
ID, OrderNumber, LineItemNumber, StatusID
1, 1001 , 1, 1
2, 1001 , 2, 1
3, 1002 , 1, 2
4, 1002 , 2, 1
5, 1003 , 1, 2
6, 1004 , 1, 3
7, 1004 , 2, 4
8, 1500 , 1, 3
As you can see, the table Status holds the statuses common for both Order and LineItem tables.
I want to produce the result which will include columns like this, status description for both Order and LineItem:
OrderNumber, LineItemNumber, StatusDesc_Order, StatusDesc_LineItem
How to do this?
You could join the Status table twice to achieve this:
SELECT
o.OrderNumber
, li.LineItemNumber
, orderStatus.StatusDesc AS StatusDesc_Order
, lineItemStatus.StatusDesc AS StatusDesc_LineItem
FROM [LineItem] AS li
INNER JOIN [Status] AS lineItemStatus ON li.StatusID = lineItemStatus.ID
INNER JOIN [Order] AS o ON li.OrderNumber = o.OrderNumber
INNER JOIN [Status] AS orderStatus ON o.StatusID = orderStatus.ID
I do suggest however you try and stay away from table names using reserved keywords like Order and Status, it also is good practice to explcitly add schema prefixes before the table names in the query (i.e. dbo.Status or another user defined schema).
If the required results really are that simple then just use a couple of sub-queries e.g.
-- SETUP TEST DATA
declare #Order table (id int, OrderNumber int, StatusId int)
insert into #Order (id, OrderNumber, StatusId)
values (1, 1001, 1), (2, 1002, 1), (3, 1003, 2), (4, 1004, 3), (5, 1500, 4)
declare #LineItem table (id int, OrderNumber int, LineItemNumber int, StatusId int)
insert into #LineItem (id, OrderNumber, LineItemNumber, StatusId)
values (1, 1001, 1, 1), (2, 1001, 2, 1), (3, 1002, 1, 2), (4, 1002, 2, 1), (5, 1003, 1, 2), (6, 1004, 1, 3), (7, 1004, 2, 4), (8, 1500, 2, 3)
declare #Status table (id int, StatusDesc varchar(32))
insert into #Status(id, StatusDesc)
values (1,'New'), (2,'Active'), (3,'Cancelled'), (4,'Complete')
-- QUERY DATA
select LI.OrderNumber, LI.LineItemNumber
, (select S.StatusDesc from #Status S where S.id = StatusId) [StatusDesc_Order]
, (select S.StatusDesc from #Status S where S.id = (select O.StatusId from #Order O where O.OrderNumber = LI.OrderNumber)) [StatusDesc_LineItem]
from #LineItem LI
order by LI.OrderNumber, LI.LineItemNumber
Note: If you provide your sample data in this format in future questions you make your question much easier to answer.
I have a simple categories table as with the following columns:
Id
Name
ParentId
So, an infinite amount of Categories can be the child of a category. Take for example the following hierarchy:
I want, in a simple query that returns the category "Business Laptops" to also return a column with all it's parents, comma separator or something:
Or take the following example:
Recursive cte to the rescue....
Create and populate sample table (Please save us this step in your future questions):
DECLARE #T as table
(
id int,
name varchar(100),
parent_id int
)
INSERT INTO #T VALUES
(1, 'A', NULL),
(2, 'A.1', 1),
(3, 'A.2', 1),
(4, 'A.1.1', 2),
(5, 'B', NULL),
(6, 'B.1', 5),
(7, 'B.1.1', 6),
(8, 'B.2', 5),
(9, 'A.1.1.1', 4),
(10, 'A.1.1.2', 4)
The cte:
;WITH CTE AS
(
SELECT id, name, name as path, parent_id
FROM #T
WHERE parent_id IS NULL
UNION ALL
SELECT t.id, t.name, cast(cte.path +','+ t.name as varchar(100)), t.parent_id
FROM #T t
INNER JOIN CTE ON t.parent_id = CTE.id
)
The query:
SELECT id, name, path
FROM CTE
Results:
id name path
1 A A
5 B B
6 B.1 B,B.1
8 B.2 B,B.2
7 B.1.1 B,B.1,B.1.1
2 A.1 A,A.1
3 A.2 A,A.2
4 A.1.1 A,A.1,A.1.1
9 A.1.1.1 A,A.1,A.1.1,A.1.1.1
10 A.1.1.2 A,A.1,A.1.1,A.1.1.2
See online demo on rextester
I have a problem in this moment.
I have a table called places with this structure:
id
parent_id
name
I want to do a selection to have all the hierarchy of this table. There's a little example of data:
(1, null, '123 Barclay St')
(2, 1, 'Floor 1')
(3, 1, 'Floor 2')
(4, 1, 'Floor 3')
(5, 2, 'Hall 1')
(6, 2, 'Room 1')
(7, 2, 'Room 2')
(8, 3, 'Room 3')
(9, null, '10 Thames St')
Obviously the order in the table is not this one.
So I want to get this result with my SELECT (with the 9 rows):
123 Barclay St
Floor 1
Hall 1
Room 1
Room 2
Floor 2
Room 3
Floor 3
10 Thames St
And not this result (that I already know how to get) :
10 Thames St
123 Barclay St
Floor 1
Floor 2
Floor 3
Hall 1
Room 1
Room 2
Room 3
If you can help me, I thank you in advance.
Here is a solution using recursive CTEs:
WITH RECURSIVE cte AS (
SELECT LPAD(id::text, 3, '0') AS marker, ' ' AS buffer,
id, parent_id, name::text
FROM yourTable t WHERE parent_id IS NULL
FROM yourTable t WHERE parent_id IS NULL
UNION ALL
SELECT t2.marker || ':' || LPAD(t1.parent_id::text, 3, '0') || ':' ||
LPAD(t1.id::text, 3, '0') AS marker,
t2.buffer || ' ', t1.id, t1.parent_id, t2.buffer || t1.name
FROM yourTable t1
INNER JOIN cte t2
ON t1.parent_id = t2.id
)
SELECT name FROM cte ORDER BY marker;
Demo
The basic idea here is to build path strings which track the complete path from every node going to back its root (the root being given by a node whose parent_id is NULL). Then, we simply do a single ORDER BY on this path to generate the order you want.
You have not provided the queries you already came up with. But - as far as I can see you want a recursive tree structure.
https://www.db-fiddle.com/f/og5HZDHBhBRmP1cDnqgCBB/1
CREATE TABLE rooms (
id INTEGER, parent_id INTEGER, name TEXT
);
INSERT INTO rooms VALUES
(1, null, '123 Barclay St'),
(2, 1, 'Floor 1'),
(3, 1, 'Floor 2'),
(4, 1, 'Floor 3'),
(5, 2, 'Hall 1'),
(6, 2, 'Room 1'),
(7, 2, 'Room 2'),
(8, 3, 'Room 3'),
(9, null, '10 Thames St');
And the query:
WITH RECURSIVE tree AS (
SELECT
rooms.id,
rooms.parent_id,
rooms.name
FROM
rooms
WHERE
parent_id IS NULL
UNION ALL
SELECT
rooms.id,
rooms.parent_id,
rooms.name
FROM
tree
JOIN rooms ON rooms.parent_id = tree.id
)
SELECT
*
FROM
tree;
https://www.postgresql.org/docs/current/static/queries-with.html
I have a simple categories table as with the following columns:
Id
Name
ParentId
So, an infinite amount of Categories can be the child of a category. Take for example the following hierarchy:
I want, in a simple query that returns the category "Business Laptops" to also return a column with all it's parents, comma separator or something:
Or take the following example:
Recursive cte to the rescue....
Create and populate sample table (Please save us this step in your future questions):
DECLARE #T as table
(
id int,
name varchar(100),
parent_id int
)
INSERT INTO #T VALUES
(1, 'A', NULL),
(2, 'A.1', 1),
(3, 'A.2', 1),
(4, 'A.1.1', 2),
(5, 'B', NULL),
(6, 'B.1', 5),
(7, 'B.1.1', 6),
(8, 'B.2', 5),
(9, 'A.1.1.1', 4),
(10, 'A.1.1.2', 4)
The cte:
;WITH CTE AS
(
SELECT id, name, name as path, parent_id
FROM #T
WHERE parent_id IS NULL
UNION ALL
SELECT t.id, t.name, cast(cte.path +','+ t.name as varchar(100)), t.parent_id
FROM #T t
INNER JOIN CTE ON t.parent_id = CTE.id
)
The query:
SELECT id, name, path
FROM CTE
Results:
id name path
1 A A
5 B B
6 B.1 B,B.1
8 B.2 B,B.2
7 B.1.1 B,B.1,B.1.1
2 A.1 A,A.1
3 A.2 A,A.2
4 A.1.1 A,A.1,A.1.1
9 A.1.1.1 A,A.1,A.1.1,A.1.1.1
10 A.1.1.2 A,A.1,A.1.1,A.1.1.2
See online demo on rextester
I have a matter which seemed simple to solve but now I find it troublesome.
In simplification - I need to find a way to identify unique sets of rows within groups defined by another column. In basic example the source table contains only two columns:
routeID nodeID nodeName
1 1 a
1 2 b
2 1 a
2 2 b
3 1 a
3 2 b
4 1 a
4 2 c
5 1 a
5 2 c
6 1 a
6 2 b
6 3 d
7 1 a
7 2 b
7 3 d
So, the routeID column refers to set of nodes which define a route.
What I need to do is to somehow group the routes, so that there will be only one unique sequence of nodes for one routeID.
In my actual case I tried to use window function to add columns which help to identify nodes sequence, but I still have no idea how to get those unique sequences and group routes.
As a final effect I want to get only unique routes - for example routes 1,2 and 3 aggregated to one route.
Do you have any idea how to help me ?
EDIT:
The other table which I would like to join with the one from the example may look like that:
journeyID nodeID nodeName routeID
1 1 a 1
1 2 b 1
2 1 a 1
2 2 b 1
3 1 a 4
3 2 c 4
...........................
...........................
You can try this idea:
DECLARE #DataSource TABLE
(
[routeID] TINYINT
,[nodeID] TINYINT
,[nodeName] CHAR(1)
);
INSERT INTO #DataSource ([routeID], [nodeID], [nodeName])
VALUES ('1', '1', 'a')
,('1', '2', 'b')
,('2', '1', 'a')
,('2', '2', 'b')
,('3', '1', 'a')
,('3', '2', 'b')
,('4', '1', 'a')
,('4', '2', 'c')
,('5', '1', 'a')
,('5', '2', 'c')
,('6', '1', 'a')
,('6', '2', 'b')
,('6', '3', 'd')
,('7', '1', 'a')
,('7', '2', 'b')
,('7', '3', 'd');
SELECT DS.[routeID]
,nodes.[value]
,ROW_NUMBER() OVER (PARTITION BY nodes.[value] ORDER BY [routeID]) AS [rowID]
FROM
(
-- getting unique route ids
SELECT DISTINCT [routeID]
FROM #DataSource DS
) DS ([routeID])
CROSS APPLY
(
-- for each route id creating CSV list with its node ids
SELECT STUFF
(
(
SELECT ',' + [nodeName]
FROM #DataSource DSI
WHERE DSI.[routeID] = DS.[routeID]
ORDER BY [nodeID]
FOR XML PATH(''), TYPE
).value('.', 'VARCHAR(MAX)')
,1
,1
,''
)
) nodes ([value]);
The code will give you this output:
So, you simple need to filter by rowID = 1. Of course, you can change the code as you like in order to satisfy your bussness criteria (for example showing no the first route ID with same nodes, but the last).
Also, ROW_NUMBER function cannot be used directly in the WHERE clause, so you need to wrap the code before filtering:
WITH DataSource AS
(
SELECT DS.[routeID]
,nodes.[value]
,ROW_NUMBER() OVER (PARTITION BY nodes.[value] ORDER BY [routeID]) AS [rowID]
FROM
(
-- getting unique route ids
SELECT DISTINCT [routeID]
FROM #DataSource DS
) DS ([routeID])
CROSS APPLY
(
-- for each route id creating CSV list with its node ids
SELECT STUFF
(
(
SELECT ',' + [nodeName]
FROM #DataSource DSI
WHERE DSI.[routeID] = DS.[routeID]
ORDER BY [nodeID]
FOR XML PATH(''), TYPE
).value('.', 'VARCHAR(MAX)')
,1
,1
,''
)
) nodes ([value])
)
SELECT DS2.*
FROM DataSource DS1
INNER JOIN #DataSource DS2
ON DS1.[routeID] = DS2.[routeID]
WHERE DS1.[rowID] = 1;
ok, let's use some recursion to create a complete node list for each routeID
First of all let's populate source table and journeyes tale
-- your source
declare #r as table (routeID int, nodeID int, nodeName char(1))
-- your other table
declare #j as table (journeyID int, nodeID int, nodeName char(1), routeID int)
-- temp results table
declare #routes as table (routeID int primary key, nodeNames varchar(1000))
;with
s as (
select *
from (
values
(1, 1, 'a'),
(1, 2, 'b'),
(2, 1, 'a'),
(2, 2, 'b'),
(3, 1, 'a'),
(3, 2, 'b'),
(4, 1, 'a'),
(4, 2, 'c'),
(5, 1, 'a'),
(5, 2, 'c'),
(6, 1, 'a'),
(6, 2, 'b'),
(6, 3, 'd'),
(7, 1, 'a'),
(7, 2, 'b'),
(7, 3, 'd')
) s (routeID, nodeID, nodeName)
)
insert into #r
select *
from s
;with
s as (
select *
from (
values
(1, 1, 'a', 1),
(1, 2, 'b', 1),
(2, 1, 'a', 1),
(2, 2, 'b', 1),
(3, 1, 'a', 4),
(3, 2, 'c', 4)
) s (journeyID, routeID, nodeID, nodeName)
)
insert into #j
select *
from s
now let's exctract routes:
;with
d as (
select *, row_number() over (partition by r.routeID order by r.nodeID desc) n2
from #r r
),
r as (
select d.*, cast(nodeName as varchar(1000)) Names, cast(0 as bigint) i2
from d
where nodeId=1
union all
select d.*, cast(r.names + ',' + d.nodeName as varchar(1000)), r.n2
from d
join r on r.routeID = d.routeID and r.nodeId=d.nodeId-1
)
insert into #routes
select routeID, Names
from r
where n2=1
table #routes will be like this:
routeID nodeNames
1 'a,b'
2 'a,b'
3 'a,b'
4 'a,c'
5 'a,c'
6 'a,b,d'
7 'a,b,d'
an now the final output:
-- the unique routes
select MIN(r.routeID) routeID, nodeNames
from #routes r
group by nodeNames
-- the unique journyes
select MIN(journeyID) journeyID, r.nodeNames
from #j j
inner join #routes r on j.routeID = r.routeID
group by nodeNames
output:
routeID nodeNames
1 'a,b'
4 'a,c'
6 'a,b,d'
and
journeyID nodeNames
1 'a,b'
3 'a,c'