eliminate duplicates SQL? - sql

How do I eliminate the duplicates?
It must be 10 rows, show every student ID (1x).
Ive tried this 2 diff ways. (see below)
( the common field is class_id)
SQL> select distinct(student_id),event.class_id, event.event_id, event.event_name
2 from student_class
3 inner join event on event.class_id = student_class.class_id
4 where student_class.class_id = '10'
5 order by student_id desc;
STUDENT_ID CLASS_ID EVENT_ID EVENT_NAME
---------- ---------- ---------- --------------------------------------------------
20 10 5 PICKUP SOCCER GAME
20 10 2 Flag FOOtball Game
18 10 2 Flag FOOtball Game
18 10 5 PICKUP SOCCER GAME
16 10 2 Flag FOOtball Game
16 10 5 PICKUP SOCCER GAME
12 10 5 PICKUP SOCCER GAME
12 10 2 Flag FOOtball Game
9 10 5 PICKUP SOCCER GAME
9 10 2 Flag FOOtball Game
8 10 2 Flag FOOtball Game
8 10 5 PICKUP SOCCER GAME
6 10 2 Flag FOOtball Game
6 10 5 PICKUP SOCCER GAME
4 10 5 PICKUP SOCCER GAME
4 10 2 Flag FOOtball Game
3 10 2 Flag FOOtball Game
3 10 5 PICKUP SOCCER GAME
2 10 5 PICKUP SOCCER GAME
2 10 2 Flag FOOtball Game
SQL> select distinct(student_id), student_class.class_id,
event.event_id, event.event_date_time
from student_class
inner join event on event.class_id = student_class.class_id
order by student_id desc;
STUDENT_ID CLASS_ID EVENT_ID EVENT_DAT
---------- ---------- ---------- ---------
22 9 1 09-NOV-99
21 2 6 20-NOV-99
21 9 1 09-NOV-99
20 9 1 09-NOV-99
20 10 2 19-JAN-99
20 10 5 09-JUL-99
18 9 1 09-NOV-99
18 10 2 19-JAN-99
18 10 5 09-JUL-99
17 9 1 09-NOV-99
16 2 6 20-NOV-99
16 9 1 09-NOV-99
16 10 2 19-JAN-99
16 10 5 09-JUL-99
15 9 1 09-NOV-99
14 9 1 09-NOV-99
13 9 1 09-NOV-99
12 2 6 20-NOV-99
12 9 1 09-NOV-99
12 10 2 19-JAN-99
12 10 5 09-JUL-99
11 2 6 20-NOV-99
11 9 1 09-NOV-99
9 10 2 19-JAN-99
9 10 5 09-JUL-99
8 2 6 20-NOV-99
8 10 2 19-JAN-99
8 10 5 09-JUL-99
7 2 6 20-NOV-99
6 10 2 19-JAN-99
6 10 5 09-JUL-99
4 10 2 19-JAN-99
4 10 5 09-JUL-99
3 10 2 19-JAN-99
3 10 5 09-JUL-99
2 2 6 20-NOV-99
2 9 1 09-NOV-99
2 10 2 19-JAN-99
2 10 5 09-JUL-99


you can do this by following methods
create table table_name2 as select distinct * from table_name1;
drop table table_name1;
rename table_name2 to table_name1;
or by this query
DELETE FROM table_name A WHERE ROWID > (SELECT min(rowid) FROM table_name B WHERE A.key_values = B.key_values);

Related

Query for extra column that contains auto increment number for individual records for each date of each person [duplicate]

This question already has answers here:
Get top 1 row of each group
(19 answers)
Closed 6 months ago.
I have table like this
PK_Log_ID FK_Emp_ID LogTime Direction
13 3 2022-08-10 09:25:54.563 0
14 3 2022-08-10 13:25:54.563 1
15 3 2022-08-11 09:25:54.563 0
16 3 2022-08-11 11:25:54.563 1
17 3 2022-08-11 12:25:54.563 0
18 3 2022-08-11 13:25:54.563 1
19 3 2022-08-11 14:25:54.563 0
20 3 2022-08-11 18:25:54.563 1
21 4 2022-08-07 09:25:54.563 0
22 4 2022-08-07 13:25:54.563 1
23 4 2022-08-07 14:25:54.563 0
24 4 2022-08-07 18:25:54.563 1
25 4 2022-08-08 09:25:54.563 0
26 4 2022-08-08 13:25:54.563 1
I want like this
PK_Log_ID FK_Emp_ID LogTime Direction Rowmunber
13 3 2022-08-10 09:25:54.563 0 1
14 3 2022-08-10 13:25:54.563 1 2
15 3 2022-08-11 09:25:54.563 0 1
16 3 2022-08-11 11:25:54.563 1 2
17 3 2022-08-11 12:25:54.563 0 3
18 3 2022-08-11 13:25:54.563 1 4
19 3 2022-08-11 14:25:54.563 0 5
20 3 2022-08-11 18:25:54.563 1 6
21 4 2022-08-07 09:25:54.563 0 1
22 4 2022-08-07 13:25:54.563 1 2
23 4 2022-08-07 14:25:54.563 0 3
24 4 2022-08-07 18:25:54.563 1 4
25 4 2022-08-08 09:25:54.563 0 1
26 4 2022-08-08 13:25:54.563 1 2
27 4 2022-08-08 14:25:54.563 0 3

You may use ROW_NUMBER() here, partition by the the employee and date, and order by the timestamp ascending:
SELECT *, ROW_NUMBER() OVER (PARTITION BY FK_Emp_ID, CONVERT(date, LogTime)
ORDER BY LogTime) Rowmunber
FROM yourTable
ORDER BY FK_Emp_ID, LogTime;

Transposing multiple related columns

While transposing single columns is pretty straight forward I need to transpose a large amount of data with 3 sets of , 10+ related columns needed to be transposed.
create table test
(month int,year int,po1 int,po2 int,ro1 int,ro2 int,mo1 int,mo2 int, mo3 int);
insert into test
values
(5,2013,100,20,10,1,3,4,5),(4,2014,200,30,20,2,4,5,6),(6,2015,200,80,30,3,5,6,7) ;
select * FROM test;
gives
month
year
po1
po2
ro1
ro2
mo1
mo2
mo3
5
2013
100
20
10
1
3
4
5
4
2014
200
30
20
2
4
5
6
6
2015
200
80
30
3
5
6
7
Transposing using UNPIVOT
select
month, year,
PO, RO, MO
from ( SELECT * from test) src
unpivot
( PO for Description in (po1, po2))unpiv1
unpivot
(RO for Description1 in (ro1, ro2)) unpiv2
unpivot
(MO for Description2 in (mo1, mo2, mo3)) unpiv3
order by year
Gives me this
month
year
PO
RO
MO
5
2013
100
10
3
5
2013
100
10
4
5
2013
100
10
5
5
2013
100
1
3
5
2013
100
1
4
5
2013
100
1
5
5
2013
20
10
3
5
2013
20
10
4
5
2013
20
10
5
5
2013
20
1
3
5
2013
20
1
4
5
2013
20
1
5
4
2014
200
20
4
4
2014
200
20
5
4
2014
200
20
6
4
2014
200
2
4
4
2014
200
2
5
4
2014
200
2
6
4
2014
30
20
4
4
2014
30
20
5
4
2014
30
20
6
4
2014
30
2
4
4
2014
30
2
5
4
2014
30
2
6
6
2015
200
30
5
6
2015
200
30
6
6
2015
200
30
7
6
2015
200
3
5
6
2015
200
3
6
6
2015
200
3
7
6
2015
80
30
5
6
2015
80
30
6
6
2015
80
30
7
6
2015
80
3
5
6
2015
80
3
6
6
2015
80
3
7
I will like to turn it to something like this. Is that possible?
month
year
PO
RO
MO
5
2013
100
10
3
5
2013
20
1
4
5
2013
0
0
5
4
2014
200
20
4
4
2014
30
2
5
4
2014
0
0
6
6
2015
200
30
5
6
2015
80
3
6
6
2015
0
0
7

Maybe use a query like below which creates rows as per your design using CROSS APPLY
select month,year,po,ro,mo from
test cross apply
(values (po1,ro1,mo1), (po2,ro2,mo2),(0,0,mo3))v(po,ro,mo)
see demo here

Unpivot acts similar as union,Use union all in your case
SELECT month,
year,
po1 AS PO,
ro1 AS RO,
mo1 AS MO
FROM test
UNION ALL
SELECT month,
year,
po2,
ro2,
mo2
FROM test
UNION ALL
SELECT month,
year,
0,
0,
mo2
FROM test

Need to Roll Parent Quantities to Calculate Total Quantity

Thanks in advance for any assistance you can provide. I have spent hours on this with no luck.
I'm working with an indented bill of material table which has an end part id, a sequence number, a level and a quantity. The goal is to determine the total cumulative quantity of each row on this table.
What makes this difficult is that to determine the total quantity, the child quantity needs to be multiplied by it's parent quantity. The parent quantity of that parent needs to be multiplied by it's parent quantity and so on.
For example, a level 3 part has a component quantity of 5. It's parent the level 2 part has a component quantity of 2. It's parent the level 1 part has a component quantity of 3. This means the level 3 part total quantity is 30 (3 X 2 X 5).
With the assistance of SO (specifically #KKK) the parent quantity was able to be calculated in the below query. After this was resolved I realized I now need two additional columns, one that shows the Rolled/Cumulative quantities of the parent rows and one that shows the total quantity of the child.
The attached screenshot has the two columns that need to be added highlighted in yellow. Here is the current SQL (using Oracle 10.2) for the columns that are not in yellow:
select
end_part_id, sort_seq_no, indented_lvl, comp_qty,
(select distinct first_value(a.comp_qty) over (order by a.sort_seq_no desc, TRIM(a.indented_lvl) desc)
from
report_table a
where
a.end_part_id = b.end_part_id
and a.sort_seq_no < b.sort_seq_no
and TRIM(a.indented_lvl) < TRIM(b.indented_lvl)) as "PARENT_QTY"
from report_table b
Expected Results
END_PART_ID SORT_SEQ_NO INDENTED_LVL COMP_QTY PARENT_QTY ROLLED_PARENT QTY TOTAL_QTY
PARTX 1 1 2 1 1 2
PARTX 2 2 5 2 2 10
PARTX 3 3 2 5 10 20
PARTX 4 4 1 2 20 20
PARTX 5 5 1 1 20 20
PARTX 6 6 1 1 20 20
PARTX 7 5 4 1 20 80
PARTX 8 6 1 4 80 80
PARTX 9 2 7 2 2 14
PARTX 10 3 2 7 14 28
PARTX 11 3 2 7 14 28
PARTX 12 4 1 2 28 28
PARTX 13 4 1 2 28 28
PARTX 14 3 8 7 14 112
PARTX 15 1 1 1 1 1
PARTX 16 2 7 1 1 7
PARTX 17 3 2 7 7 14
PARTX 18 3 2 7 7 14
PARTX 19 4 1 2 14 14
PARTX 20 4 1 2 14 14

SQL : How to find number of occurrences without using HAVING or COUNT?

This is a trivial example, but I am trying to understand how to think creatively using SQL.
For example, I have the following tables below, and I want to query the names of folks who have three or more questions. How can I do this without using HAVING or COUNT? I wonder if this is possible using JOINS or something similar?
FOLKS
folkID name
---------- --------------
01 Bill
02 Joe
03 Amy
04 Mike
05 Chris
06 Elizabeth
07 James
08 Ashley
QUESTION
folkID questionRating questionDate
---------- ---------- ----------
01 2 2011-01-22
01 4 2011-01-27
02 4
03 2 2011-01-20
03 4 2011-01-12
03 2 2011-01-30
04 3 2011-01-09
05 3 2011-01-27
05 2 2011-01-22
05 4
06 3 2011-01-15
06 5 2011-01-19
07 5 2011-01-20
08 3 2011-01-02

Using SUM or CASE seems to be cheating to me!
I'm not sure if it's possible in your current formulation, but if you add a primary key to the question table (questionid) then the following seems to work:
SELECT DISTINCT Folks.folkid, Folks.name
FROM ((Folks
INNER JOIN Question AS Question_1 ON Folks.folkid = Question_1.folkid)
INNER JOIN Question AS Question_2 ON Folks.folkid = Question_2.folkid)
INNER JOIN Question AS Question_3 ON Folks.folkid = Question_3.folkid
WHERE (((Question_1.questionid) <> [Question_2].[questionid] And
(Question_1.questionid) <> [Question_3].[questionid]) AND
(Question_2.questionid) <> [Question_3].[questionid]);
Sorry, this is in MS Access SQL, but it should translate to any flavour of SQL.
Returns:
folkid name
3 Amy
5 Chris
Update: Just to explain why this works. Each join will return all the question ids asked by that person. The where clauses then leaves only unique rows of question ids. If there are less than three questions asked then there will be no unique rows.
For example, Bill:
folkid name Question_3.questionid Question_1.questionid Question_2.questionid
1 Bill 1 1 1
1 Bill 1 1 2
1 Bill 1 2 1
1 Bill 1 2 2
1 Bill 2 1 1
1 Bill 2 1 2
1 Bill 2 2 1
1 Bill 2 2 2
There are no rows where all the ids are different.
however for Amy:
folkid name Question_3.questionid Question_1.questionid Question_2.questionid
3 Amy 4 4 5
3 Amy 4 4 4
3 Amy 4 4 6
3 Amy 4 5 4
3 Amy 4 5 5
3 Amy 4 5 6
3 Amy 4 6 4
3 Amy 4 6 5
3 Amy 4 6 6
3 Amy 5 4 4
3 Amy 5 4 5
3 Amy 5 4 6
3 Amy 5 5 4
3 Amy 5 5 5
3 Amy 5 5 6
3 Amy 5 6 4
3 Amy 5 6 5
3 Amy 5 6 6
3 Amy 6 4 4
3 Amy 6 4 5
3 Amy 6 4 6
3 Amy 6 5 4
3 Amy 6 5 5
3 Amy 6 5 6
3 Amy 6 6 4
3 Amy 6 6 5
3 Amy 6 6 6
There are several rows which have different ids and hence these get returned by the above query.

you can try sum , to replace count.
SELECT SUM(CASE WHEN Field_name >=3 THEN field_name ELSE 0 END)
FROM tabel_name

SELECT f.*
FROM (
SELECT DISTINCT
COUNT(*) OVER (PARTITION BY folkID) AS [Count] --count questions for folks
,a.folkID
FROM QUESTION AS q
) AS p
INNER JOIN FOLKS as f ON f.folkID = q.folkID
WHERE p.[Count] > 3

List the name of employee who workon one project sponsored by his/her division and also work on one project that is not sponsord by his/her division

The code I have for this is
select name
from employee e, workon w
where e.empid = w.empid
and pid in
(select pid
from workon
where did in
(select did
from employee ee
where e.did = ee.did))
group by name
But I know that isn't right, since I also need to find someone who works in a project outside of his division. The problem is that I'm not too sure how to do that.
Tables
Employee
EMPID NAME SALARY DID
1 kevin 32000 2
2 joan 46200 1
3 brian 37000 3
4 larry 82000 5
5 harry 92000 4
6 peter 45000 2
7 peter 68000 3
8 smith 39000 4
9 chen 71000 1
10 kim 46000 5
11 smith 46000 1
Workon
PID EMPID HOURS
3 1 30
2 3 40
5 4 30
6 6 60
4 3 70
2 4 45
5 3 90
3 3 100
6 8 30
4 4 30
5 8 30
6 7 30
6 9 40
5 9 50
4 6 45
2 7 30
2 8 30
2 9 30
1 9 30
1 8 30
1 7 30
1 5 30
1 6 30
2 6 30
Project
PID PNAME BUDGET DID
1 DB development 8000 2
2 network development 6000 2
3 Web development 5000 3
4 Wireless development 5000 1
5 security system 6000 4
6 system development 7000 1

select e.name
from employee e
where
-- Projects in department
exists (
select *
from
workon w
join project p
on w.pid = p.pid
and p.did = e.did
where w.empid = e.empid
)
-- Projects out of department
and exists (
select *
from
workon w
join project p
on w.pid = p.pid
and p.did != e.did
where w.empid = e.empid
)