T-SQL select process variable - tsql

In SQL Server 2008 I have a Table- Fruits
Items Orders
Bananas 6
Bananas 2
Bananas 1
Mangos 4
Mangos 3
Apples 7
Apples 1
Apples 3
Apples 3
Using variables, how I can get below output. I am requesting variables because I would like perform several mathematical operations not described in this example.
Items Number of Orders Total Order Quantity Average Order Quantity
Bananas 3 9 3
Mangos 2 7 3.5
Apples 4 14 3.5
'Total Order Quantity' shows sum of all orders for given item
'Average Order Quantity' = 'Total Order Quantity'/'Number of Orders'
Many thanks.
Create table Fruits (Items varchar(10), Orders int)
insert into Fruits values ('Bananas',6)
insert into Fruits values ('Bananas',2)
insert into Fruits values ('Bananas',1)
insert into Fruits values ('Mangos',4)
insert into Fruits values ('Mangos',3)
insert into Fruits values ('Apples',7)
insert into Fruits values ('Apples',1)
insert into Fruits values ('Apples',3)
insert into Fruits values ('Apples',3)

select Items, count(Orders) as NumberOfOrders, sum(Orders) as TotalOrderQuantity, avg(Orders + 0.0) as AverageOrderQuantity
from Fruits
group by Items

Yes, really should steer clear of cursors when possible. Something like this approach would probably be best, storing the results of the query in a temporary table, and then running update statements to get your calculations:
declare #Table table
(
#Item varchar(10)
#OrderCount int
#QuantityTotal int
#AvgQuantity numeric(9, 2)
#Calc1 numeric(9, 2)
#Calc2 numeric(9, 2)
)
insert into #Table (#Item, #OrderCount, #QuantityTotal, #AvgQuantity)
select Items, count(Orders) as NumberOfOrders, sum(Orders) as TotalOrderQuantity, avg(Orders + 0.0) as AverageOrderQuantity
from Fruits
group by Items
order by 1
update #Table set #Calc1 = #OrderCount / #AvgQuantity,
#Calc2 = ...
select * from #Table
or if you can get all your calculations in a single row or joins with another table, you can do it in a single statement, like:
select *, (OrderCount / AvgQuantity) as Calc1, (... as Calc2)
from
(
select Items, count(Orders) as OrderCount, sum(Orders) as TotalQuantity, avg(Orders + 0.0) as AvgQuantity
from Fruits
group by Items
) t

declare csrCursor cursor for
select Items, count(Orders) as NumberOfOrders, sum(Orders) as TotalOrderQuantity, avg(Orders + 0.0) as AverageOrderQuantity
from Fruits
group by Items
order by 1
declare #Item varchar(10)
declare #OrderCount int
declare #QuantityTotal int
declare #AvgQuantity numeric(9, 2)
open csrCursor
fetch next from csrCursor into #Item, #OrderCount, #QuantityTotal, #AvgQuantity
while (##fetch_status = 0)
-- Do stuff with variables #Item, #OrderCount, #QuantityTotal, #AvgQuantity
-- Insert results in Temp Table
fetch next from csrCursor into #Item, #OrderCount, #QuantityTotal, #AvgQuantity
end
close csrCursor
deallocate csrCursor

Related

Get day name based on custome ID of bigint[] datatype

I want to display Day name based on ID which is in bigint[] in the table as shown below:
Table:
create table tbl_days
(
day_ids bigint[]
);
Records:
insert into tbl_days values('{1,2}');
insert into tbl_days values('{1,2,3}');
insert into tbl_days values('{1,4}');
insert into tbl_days values('{4,7}');
insert into tbl_days values('{1,2,3,4,5,6,7}');
insert into tbl_days values('{2,4,7}');
Would like to display day name for:
1 for Monday
2 for Tuesday
.
..
7 for Sunday.
Query 1: Using replace(), which is taking 3 more seconds to get the main query result.
select replace(replace(replace(replace(replace(replace(replace(day_ids::varchar,'1','Monday'),'2','Tuesday'),'3','Wednesday'),'4','Thursday'),'5','Friday'),'6','Saturday'),'7','Sunday')
from tbl_days;
Query 2: Using string_agg(), here problem with an order.
Step 1: Add days into temp table
create temp table temp_days
(
id int,
days varchar
);
insert into temp_days values(1,'Monday'),(2,'Tuesday'),(3,'Wednesday'),(4,'Thursday'),(5,'Friday'),(6,'Saturday'),(7,'Sunday');
Step 2: Join with main table
select d.day_ids,string_agg(distinct t.days,',')
from tbl_days d
inner join temp_days t on t.id = any(d.day_ids)
group by d.day_ids
step-by-step demo:db<>fiddle
SELECT
id,
string_agg( -- 4
CASE day -- 3
WHEN 1 THEN 'Monday'
WHEN 2 THEN 'Tuesday'
WHEN 3 THEN 'Wednesday'
WHEN 4 THEN 'Thursday'
WHEN 5 THEN 'Friday'
WHEN 6 THEN 'Saturday'
WHEN 7 THEN 'Sunday'
END,
','
ORDER BY index_in_array -- 4
)
FROM (
SELECT
*,
row_number() OVER () as id -- 1
FROM tbl_days
) s,
unnest(day_ids) WITH ORDINALITY as t(day, index_in_array) -- 2
GROUP BY id
For my approach you need an id column. This creates one. If you already have one, you can ignore this step
unnest() expands the array into one row per element. The WITH ORDINALITY clause adds an index to the records which saves the position of the element in the original array
Replace the numbers with the related string using a CASE clause
Reaggregate the weekdays by their original ids. The order can be ensured by using the in (2) created index, which can be using in the ORDER BY clause of the aggregate

How to use a declare statement to update a table

I have this Declare Statement
declare #ReferralLevelData table([Type of Contact] varchar(10));
insert into #ReferralLevelData values ('f2f'),('nf2f'),('Travel'),('f2f'),('nf2f'),('Travel'),('f2f'),('nf2f'),('Travel');
select (row_number() over (order by [Type of Contact]) % 3) +1 as [Referral ID]
,[Type of Contact]
from #ReferralLevelData
order by [Referral ID]
,[Type of Contact];
It does not insert into the table so i feel this is not working as expect, i.e it doesn't modify the table.
If it did work I was hoping to modify the statement to make it update.
At the moment the table just prints this result
1 f2f
1 nf2f
1 Travel
2 f2f
2 nf2f
2 Travel
3 f2f
3 nf2f
3 Travel
EDIT:
I want TO Update the table to enter recurring data in groups of three.
I have a table of data, it is duplicated twice in the same table to make three sets.
Its "ReferenceID" is the primary key, i want to in a way group the 3 same ReferenceID's and inject these three values "f2f" "NF2F" "Travel" into the row called "Type" in any order but ensure that each ReferenceID only has one of those values.
Do you mean the following?
declare #ReferralLevelData table(
[Referral ID] int,
[Type of Contact] varchar(10)
);
insert into #ReferralLevelData([Referral ID],[Type of Contact])
select
(row_number() over (order by [Type of Contact]) % 3) +1 as [Referral ID]
,[Type of Contact]
from
(
values ('f2f'),('nf2f'),('Travel'),('f2f'),('nf2f'),('Travel'),('f2f'),('nf2f'),('Travel')
) v([Type of Contact]);
If it suits you then you also can use the next query to generate data:
select r.[Referral ID],ct.[Type of Contact]
from
(
values ('f2f'),('nf2f'),('Travel')
) ct([Type of Contact])
cross join
(
values (1),(2),(3)
) r([Referral ID]);

How can I SUM distinct records in a Postgres database where there are duplicate records?

Imagine a table that looks like this:
The SQL to get this data was just SELECT *
The first column is "row_id" the second is "id" - which is the order ID and the third is "total" - which is the revenue.
I'm not sure why there are duplicate rows in the database, but when I do a SUM(total), it's including the second entry in the database, even though the order ID is the same, which is causing my numbers to be larger than if I select distinct(id), total - export to excel and then sum the values manually.
So my question is - how can I SUM on just the distinct order IDs so that I get the same revenue as if I exported to excel every distinct order ID row?
Thanks in advance!
Easy - just divide by the count:
select id, sum(total) / count(id)
from orders
group by id
See live demo.
Also handles any level of duplication, eg triplicates etc.
You can try something like this (with your example):
Table
create table test (
row_id int,
id int,
total decimal(15,2)
);
insert into test values
(6395, 1509, 112), (22986, 1509, 112),
(1393, 3284, 40.37), (24360, 3284, 40.37);
Query
with distinct_records as (
select distinct id, total from test
)
select a.id, b.actual_total, array_agg(a.row_id) as row_ids
from test a
inner join (select id, sum(total) as actual_total from distinct_records group by id) b
on a.id = b.id
group by a.id, b.actual_total
Result
| id | actual_total | row_ids |
|------|--------------|------------|
| 1509 | 112 | 6395,22986 |
| 3284 | 40.37 | 1393,24360 |
Explanation
We do not know what the reasons is for orders and totals to appear more than one time with different row_id. So using a common table expression (CTE) using the with ... phrase, we get the distinct id and total.
Under the CTE, we use this distinct data to do totaling. We join ID in the original table with the aggregation over distinct values. Then we comma-separate row_ids so that the information looks cleaner.
SQLFiddle example
http://sqlfiddle.com/#!15/72639/3
Create custom aggregate:
CREATE OR REPLACE FUNCTION sum_func (
double precision, pg_catalog.anyelement, double precision
)
RETURNS double precision AS
$body$
SELECT case when $3 is not null then COALESCE($1, 0) + $3 else $1 end
$body$
LANGUAGE 'sql';
CREATE AGGREGATE dist_sum (
pg_catalog."any",
double precision)
(
SFUNC = sum_func,
STYPE = float8
);
And then calc distinct sum like:
select dist_sum(distinct id, total)
from orders
SQLFiddle
You can use DISTINCT in your aggregate functions:
SELECT id, SUM(DISTINCT total) FROM orders GROUP BY id
Documentation here: https://www.postgresql.org/docs/9.6/static/sql-expressions.html#SYNTAX-AGGREGATES
If we can trust that the total for 1 order is actually 1 row. We could eliminate the duplicates in a sub-query by selecting the the MAX of the PK id column. An example:
CREATE TABLE test2 (id int, order_id int, total int);
insert into test2 values (1,1,50);
insert into test2 values (2,1,50);
insert into test2 values (5,1,50);
insert into test2 values (3,2,100);
insert into test2 values (4,2,100);
select order_id, sum(total)
from test2 t
join (
select max(id) as id
from test2
group by order_id) as sq
on t.id = sq.id
group by order_id
sql fiddle
In difficult cases:
select
id,
(
SELECT SUM(value::int4)
FROM jsonb_each_text(jsonb_object_agg(row_id, total))
) as total
from orders
group by id
I would suggest just use a sub-Query:
SELECT "a"."id", SUM("a"."total")
FROM (SELECT DISTINCT ON ("id") * FROM "Database"."Schema"."Table") AS "a"
GROUP BY "a"."id"
The Above will give you the total of each id
Use below if you want the full total of each duplicate removed:
SELECT SUM("a"."total")
FROM (SELECT DISTINCT ON ("id") * FROM "Database"."Schema"."Table") AS "a"
Using subselect (http://sqlfiddle.com/#!7/cef1c/51):
select sum(total) from (
select distinct id, total
from orders
)
Using CTE (http://sqlfiddle.com/#!7/cef1c/53):
with distinct_records as (
select distinct id, total from orders
)
select sum(total) from distinct_records;

T-SQL query, multiple values in a field

I have two tables in a database. The first table tblTracker contains many columns, but the column of particular interest is called siteAdmin and each row in that column can contain multiple loginIDs of 5 digits like 21457, 21456 or just one like 21444. The next table users contains columns like LoginID, fname, and lname.
What I would like to be able to do is take the loginIDs contained in tblTracker.siteAdmin and return fname + lname from users. I can successfully do this when there is only one loginID in the row such as 21444 but I cannot figure out how to do this when there is more than one like 21457, 21456.
Here is the SQL statement I use for when there is one loginID in that column
SELECT b.FName + '' '' + b.LName AS siteAdminName,
FROM tblTracker a
LEFT OUTER JOIN users b ON a.siteAdmin= b.Login_Id
However this doesn't work when it tries to join a siteAdmin with more than one LoginID in it
Thanks!
I prefer the number table approach to split a string in TSQL
For this method to work, you need to do this one time table setup:
SELECT TOP 10000 IDENTITY(int,1,1) AS Number
INTO Numbers
FROM sys.objects s1
CROSS JOIN sys.objects s2
ALTER TABLE Numbers ADD CONSTRAINT PK_Numbers PRIMARY KEY CLUSTERED (Number)
Once the Numbers table is set up, create this split function:
CREATE FUNCTION [dbo].[FN_ListToTable]
(
#SplitOn char(1) --REQUIRED, the character to split the #List string on
,#List varchar(8000)--REQUIRED, the list to split apart
)
RETURNS TABLE
AS
RETURN
(
----------------
--SINGLE QUERY-- --this will not return empty rows
----------------
SELECT
ListValue
FROM (SELECT
LTRIM(RTRIM(SUBSTRING(List2, number+1, CHARINDEX(#SplitOn, List2, number+1)-number - 1))) AS ListValue
FROM (
SELECT #SplitOn + #List + #SplitOn AS List2
) AS dt
INNER JOIN Numbers n ON n.Number < LEN(dt.List2)
WHERE SUBSTRING(List2, number, 1) = #SplitOn
) dt2
WHERE ListValue IS NOT NULL AND ListValue!=''
);
GO
You can now easily split a CSV string into a table and join on it:
select * from dbo.FN_ListToTable(',','1,2,3,,,4,5,6777,,,')
OUTPUT:
ListValue
-----------------------
1
2
3
4
5
6777
(6 row(s) affected)
Your can now use a CROSS APPLY to split every row in your table like:
DECLARE #users table (LoginID int, fname varchar(5), lname varchar(5))
INSERT INTO #users VALUES (1, 'Sam', 'Jones')
INSERT INTO #users VALUES (2, 'Don', 'Smith')
INSERT INTO #users VALUES (3, 'Joe', 'Doe')
INSERT INTO #users VALUES (4, 'Tim', 'White')
INSERT INTO #users VALUES (5, 'Matt', 'Davis')
INSERT INTO #users VALUES (15,'Sue', 'Me')
DECLARE #tblTracker table (RowID int, siteAdmin varchar(50))
INSERT INTO #tblTracker VALUES (1,'1,2,3')
INSERT INTO #tblTracker VALUES (2,'2,3,4')
INSERT INTO #tblTracker VALUES (3,'1,5')
INSERT INTO #tblTracker VALUES (4,'1')
INSERT INTO #tblTracker VALUES (5,'5')
INSERT INTO #tblTracker VALUES (6,'')
INSERT INTO #tblTracker VALUES (7,'8,9,10')
INSERT INTO #tblTracker VALUES (8,'1,15,3,4,5')
SELECT
t.RowID, u.LoginID, u.fname+' '+u.lname AS YourAdmin
FROM #tblTracker t
CROSS APPLY dbo.FN_ListToTable(',',t.siteAdmin) st
LEFT OUTER JOIN #users u ON st.ListValue=u.LoginID --to get all rows even if missing siteAdmin
--INNER JOIN #users u ON st.ListValue=u.LoginID --to remove rows without any siteAdmin
ORDER BY t.RowID,u.fname,u.lname
OUTPUT:
RowID LoginID YourAdmin
----------- ----------- -----------
1 2 Don Smith
1 3 Joe Doe
1 1 Sam Jones
2 2 Don Smith
2 3 Joe Doe
2 4 Tim White
3 5 Matt Davis
3 1 Sam Jones
4 1 Sam Jones
5 5 Matt Davis
7 NULL NULL
7 NULL NULL
7 NULL NULL
8 3 Joe Doe
8 5 Matt Davis
8 1 Sam Jones
8 15 Sue Me
8 4 Tim White
(18 row(s) affected)

Find duplicate row "details" in table

OrderId OrderCode Description
-------------------------------
1 Z123 Stuff
2 ABC999 Things
3 Z123 Stuff
I have duplicates in a table like the above. I'm trying to get a report of which Orders are duplicates, and what Order they are duplicates of, so I can figure out how they got into the database.
So ideally I'd like to get an output something like;
OrderId IsDuplicatedBy
-------------------------
1 3
3 1
I can't work out how to code this in SQL.
You can use the same table twice in one query and join on the fields you need to check against. T1.OrderID <> T2.OrderID is needed to not find a duplicate for the same row.
declare #T table (OrderID int, OrderCode varchar(10), Description varchar(50))
insert into #T values
(1, 'Z123', 'Stuff'),
(2, 'ABC999', 'Things'),
(3, 'Z123', 'Stuff')
select
T1.OrderID,
T2.OrderID as IsDuplicatedBy
from #T as T1
inner join #T as T2
on T1.OrderCode = T2.OrderCode and
T1.Description = T2.Description and
T1.OrderID <> T2.OrderID
Result:
OrderID IsDuplicatedBy
1 3
3 1