SQL: Group b=By Result are different - mysql

Hey everyone Im having a trouble to understand why my result are different when im changing the group by from days to months
'''
SELECT U.USERNAME, COUNTER_MOVEMENTS.USER_BUNDLE_ID,COUNTER_MOVEMENTS.USER_ID,COUNTER_MOVEMENTS.PAYMENT_CURRENCY,FROM_UNIXTIME(COUNTER_MOVEMENTS.CREATE_TIME-25200, '%m/%Y')AS SHORT_DATE ,COUNT(DISTINCT COUNTER_MOVEMENTS.USER_ID) AS COUNTER
FROM `COUNTER_MOVEMENTS` INNER JOIN USERS U ON U.ID = COUNTER_MOVEMENTS.USER_ID
AND U.DISTRIBUTOR ='canopy'
AND U.FINANCE_SYSTEM_ID = 2
AND U.IS_TEST_USER = 0
AND COUNTER_MOVEMENTS.TYPE='bundle_add'
INNER JOIN USERS_BUNDLES UB ON UB.ID = COUNTER_MOVEMENTS.USER_BUNDLE_ID
INNER JOIN DEVICES_PRODUCTS DP ON DP.ID = UB.MAIN_DEVICE_PRODUCT_ID
LEFT JOIN COUPONS C ON C.ID = DP.COUPON_ID
GROUP BY FROM_UNIXTIME(COUNTER_MOVEMENTS.CREATE_TIME-25200, '%m/%Y')
HAVING SHORT_DATE = '10/2022'
'''
The count is 337
But if Im doing the same query but group by days and not months and then sums the count, the result are different
'''
WITH
X AS (SELECT U.USERNAME , COUNTER_MOVEMENTS.USER_BUNDLE_ID,COUNTER_MOVEMENTS.USER_ID,COUNTER_MOVEMENTS.PAYMENT_CURRENCY,FROM_UNIXTIME(COUNTER_MOVEMENTS.CREATE_TIME-25200, '%m/%Y')AS SHORT_DATE ,COUNT(DISTINCT COUNTER_MOVEMENTS.USER_ID) AS COUNTER
FROM `COUNTER_MOVEMENTS` INNER JOIN USERS U ON U.ID = COUNTER_MOVEMENTS.USER_ID
AND U.DISTRIBUTOR ='canopy'
AND U.FINANCE_SYSTEM_ID = 2
AND U.IS_TEST_USER = 0
AND COUNTER_MOVEMENTS.TYPE='bundle_add'
INNER JOIN USERS_BUNDLES UB ON UB.ID = COUNTER_MOVEMENTS.USER_BUNDLE_ID
INNER JOIN DEVICES_PRODUCTS DP ON DP.ID = UB.MAIN_DEVICE_PRODUCT_ID
LEFT JOIN COUPONS C ON C.ID = DP.COUPON_ID
GROUP BY FROM_UNIXTIME(COUNTER_MOVEMENTS.CREATE_TIME-25200, '%d/%m/%Y'))
SELECT SUM(X.COUNTER) FROM X
WHERE SHORT_DATE = '10/2022';
'''
The result here are 344.
Any idea why the result not the same?

Related

Complex query containing multiple joins is not executing right outer join

I'm writing a query with multiple joins where I want every user to show entries against all category Types. When I execute the query below only 1 record is returned because the employee u.employee_id = "0079-P" has only worked on 1 project but I want to get data for all the category_types with users workhours displayed as null for the categories he didn't work on.
Select u.employee_id As Employee_ID, u.user_name As UserName, COALESCE(primaryDept.ctd_name, primaryProj.ctd_name) As PrimaryDeptOrProj, region.region_name As Region, categoryType.ctd_id, categoryType.ctd_name, SUM(tsdd.workhours)
From users u
LEFT JOIN category_type_details primaryDept ON u.user_primary_department = primaryDept.ctd_id
LEFT JOIN category_type_details primaryProj ON u.user_primary_project = primaryProj.ctd_id
LEFT JOIN regions region ON u.region_id = region.region_id
LEFT JOIN timesheets ts ON u.user_id = ts.timesheet_user
INNER JOIN timesheet_mr tsmr ON ts.timesheet_caller = tsmr.tsmr_id
INNER JOIN timesheet_details tsd ON ts.timesheet_id = tsd.tsd_timesheet_id
INNER JOIN timesheet_day_details tsdd ON tsd.tsd_id = tsdd.tsd_id
RIGHT OUTER JOIN category_type_details categoryType ON tsd.tsd_category_type_id = categoryType.ctd_id
WHERE tsmr.tsmr_id = 14 and u.employee_id = "0079-P"
GROUP BY u.user_id, tsd.tsd_category_type_id;
I tried this query with variations and it returns 1 record in any case.
You could change your query to this:
SELECT u.employee_id AS Employee_ID, u.user_name AS UserName,
COALESCE(pd.ctd_name, pp.ctd_name) AS PrimaryDeptOrProj,
r.region_name AS Region, ct.ctd_id, ct.ctd_name, SUM(tsdd.workhours)
FROM users u
LEFT JOIN category_type_details pd ON u.user_primary_department = pd.ctd_id
LEFT JOIN category_type_details pp ON u.user_primary_project = pp.ctd_id
LEFT JOIN regions r ON u.region_id = r.region_id
LEFT JOIN timesheets ts ON u.user_id = ts.timesheet_user
INNER JOIN timesheet_mr tsmr ON ts.timesheet_caller = tsmr.tsmr_id AND tsmr.tsmr_id = 14
INNER JOIN timesheet_details tsd ON ts.timesheet_id = tsd.tsd_timesheet_id
INNER JOIN timesheet_day_details tsdd ON tsd.tsd_id = tsdd.tsd_id
RIGHT OUTER JOIN category_type_details ct ON tsd.tsd_category_type_id = ct.ctd_id AND u.employee_id = "0079-P"
GROUP BY ct.ctd_id, u.user_id, u.employee_id, u.user_name,
COALESCE(pd.ctd_name, pp.ctd_name), r.region_name, ct.ctd_name
ORDER BY ct.ctd_id, u.user_id, u.employee_id, u.user_name,
COALESCE(pd.ctd_name, pp.ctd_name), r.region_name, ct.ctd_name;
You only got 1 row because the condition in WHERE clause filter all the NULL user_id rows for other category.
For MySQL, you could omit other columns in GROUP BY clause:
SELECT u.employee_id AS Employee_ID, u.user_name AS UserName,
COALESCE(pd.ctd_name, pp.ctd_name) AS PrimaryDeptOrProj,
r.region_name AS Region, ct.ctd_id, ct.ctd_name, SUM(tsdd.workhours)
FROM users u
LEFT JOIN category_type_details pd ON u.user_primary_department = pd.ctd_id
LEFT JOIN category_type_details pp ON u.user_primary_project = pp.ctd_id
LEFT JOIN regions r ON u.region_id = r.region_id
LEFT JOIN timesheets ts ON u.user_id = ts.timesheet_user
INNER JOIN timesheet_mr tsmr ON ts.timesheet_caller = tsmr.tsmr_id AND tsmr.tsmr_id = 14
INNER JOIN timesheet_details tsd ON ts.timesheet_id = tsd.tsd_timesheet_id
INNER JOIN timesheet_day_details tsdd ON tsd.tsd_id = tsdd.tsd_id
RIGHT OUTER JOIN category_type_details ct ON tsd.tsd_category_type_id = ct.ctd_id AND u.employee_id = "0079-P"
GROUP BY ct.ctd_id, u.user_id
ORDER BY ct.ctd_id, u.user_id;

mysql join with multiple tables and count query

I have total 6 tables in which different info has been saved
Now i need a result in which get count from 5 tables and select all info from main table but if record does not exist than it must be need to return 0 instead of no row found that's the problem here
I have tried below query but didn't get success
SELECT
u.*,
COUNT(DISTINCT c.id) as comments,
COUNT(DISTINCT d.id) as dislikes,
COUNT(DISTINCT l.id) as likes,
COUNT(DISTINCT s.id) as shares,
COUNT(DISTINCT t.id) as tags
FROM
job_details as u
JOIN job_comments as c ON u.id = c.job_id
JOIN job_dislike as d ON u.id = d.job_id
JOIN job_like as l ON u.id = l.job_id
JOIN job_share as s ON u.id = s.job_id
JOIN job_tags as t ON u.id = t.job_id
WHERE
u.id = c.job_id AND
u.id = d.job_id AND
u.id = l.job_id AND
u.id = s.job_id AND
u.id = t.job_id
GROUP BY
u.id
This query is executed, but didn't get exact result.
I don't quite understand why.
I was hoping somebody here could help me out?
Thanks!
You probably didn't get the exact result because some tables may be missing values.
Although you can solve this problem with a LEFT JOIN, the safer solution is to pre-aggregate the data:
SELECT u.*, c.comments, d.dislikes, l.likes, s.shares, t.tags
FROM job_details as u LEFT JOIN
(select c.job_id, count(*) as comments from job_comments group by c.job_id
) c
ON u.id = c.job_id LEFT JOIN
(select d.job_id, count(*) as dislikes from job_dislike d group by d.job_id
) d
ON u.id = d.job_id LEFT JOIN
(select l.job_id, count(*) as likes from job_like l group by l.job_id
) l
ON u.id = l.job_id LEFT JOIN
(select s.job_id, count(*) as shares from job_share s group by s.job_id
) s
ON u.id = s.job_id LEFT JOIN
(select t.job_id, count(*) as tags from job_tags t group by t.job_id
) t
ON u.id = t.job_id;
Why is this better? Consider an id that has 5 comments, likes, dislikes, shares and tags. The JOIN approach produces an intermediate result with 5*5*5*5*5 = 3,125 intermediate rows. Things can really get out of hand for popular ids.
Use LEFT JOIN instead of JOIN. and you don't need WHERE clause since you have joined those tables. And, use IFNULL function to return 0 for null values. You need to modify you query like this :
SELECT u.id,
IFNULL(COUNT(DISTINCT c.id),0) as comments,
IFNULL(COUNT(DISTINCT d.id),0) as dislikes,
IFNULL(COUNT(DISTINCT l.id),0) as likes,
IFNULL(COUNT(DISTINCT s.id),0) as shares,
IFNULL(COUNT(DISTINCT t.id),0) as tags
FROM job_details as u
LEFT JOIN job_comments as c ON u.id = c.job_id
LEFT JOIN job_dislike as d ON u.id = d.job_id
LEFT JOIN job_like as l ON u.id = l.job_id
LEFT JOIN job_share as s ON u.id = s.job_id
LEFT JOIN job_tags as t ON u.id = t.job_id
GROUP BY u.id

Problems with reusing LEFT JOIN results in WHERE and ORDER BY Clause

SELECT s.*,
u.username,
u.fullname,
c.title AS ctitle,
c.description AS cdescription,
sa.attention,
sp.popularity,
COUNT(DISTINCT f.id) AS favorites,
COUNT(DISTINCT st.id) AS stars,
COUNT(DISTINCT v.id) AS views
FROM shots s
INNER JOIN users u ON u.id = s.user_id
INNER JOIN categories c ON c.id = s.cat_id
LEFT OUTER JOIN(
SELECT shot_id, round(AVG(count),2) AS attention
FROM points
WHERE date > DATE_SUB(CURDATE(),INTERVAL 2 DAY)
GROUP BY shot_id
) sa ON sa.shot_id = s.id
LEFT OUTER JOIN(
SELECT shot_id, SUM(count) AS popularity
FROM points
GROUP BY shot_id
) sp ON sp.shot_id = s.id
LEFT OUTER JOIN favorites f ON f.shot_id = s.id
LEFT OUTER JOIN stars st ON st.shot_id = s.id
LEFT OUTER JOIN views v ON v.shot_id = s.id
**WHERE s.library = 1 AND sa.attention > 40
ORDER BY sa.attention DESC
LIMIT 0,50**
GROUP BY s.id
I can't use the sa.attention in a condition and for ordering. Why?
(I removed the marked part, and the query works!)
What do I have to change in my Query? And if you could give a explanation for it, that would be very nice!
You are negating your OUTER JOIN by putting that in your WHERE criteria. Move it to your JOIN and you'll get your NULL records back:
SELECT s.*,
u.username,
u.fullname,
c.title AS ctitle,
c.description AS cdescription,
sa.attention,
sp.popularity,
COUNT(DISTINCT f.id) AS favorites,
COUNT(DISTINCT st.id) AS stars,
COUNT(DISTINCT v.id) AS views
FROM shots s
INNER JOIN users u ON u.id = s.user_id
INNER JOIN categories c ON c.id = s.cat_id
LEFT OUTER JOIN(
SELECT shot_id, round(AVG(count),2) AS attention
FROM points
WHERE date > DATE_SUB(CURDATE(),INTERVAL 2 DAY)
GROUP BY shot_id
) sa ON sa.shot_id = s.id AND sa.attention > 40
LEFT OUTER JOIN(
SELECT shot_id, SUM(count) AS popularity
FROM points
GROUP BY shot_id
) sp ON sp.shot_id = s.id
LEFT OUTER JOIN favorites f ON f.shot_id = s.id
LEFT OUTER JOIN stars st ON st.shot_id = s.id
LEFT OUTER JOIN views v ON v.shot_id = s.id
WHERE s.library = 1
GROUP BY s.id
ORDER BY sa.attention DESC
LIMIT 0,50
A second note, GROUP BY cannot go at the end. I moved that to the correct spot as well.

Query goes wrong when checking if the user exists in other table

I have a query that shows a list of revisions and employees for every revision..
Now I'm trying to show if the given employee already has a row in the answers table..
This is the overview of the database
This is my working query that shows the list of revisions and employees
SELECT l.id, l.naam, r.id as revision_id, r.beschrijving, e.id as employee_id, e.voornaam, e.achternaam,
FROM lists l
INNER JOIN revisions r ON l.id = r.list_id
INNER JOIN employeelists el ON el.list_id= l.id
INNER JOIN employees e ON e.id = el.employee_id
INNER JOIN customers c ON c.id = e.customer_id
WHERE customer_id = :id AND r.actief = 1
Now I've tried several things to see if the employee already has a record in the answers table.. But It's failing the whole time..
Try 1 : Adding the Answers table with a left outer join
SELECT l.id, l.naam, r.id as revision_id, r.beschrijving, e.id as employee_id, e.voornaam, e.achternaam,
**CASE WHEN a.coach_id != 0 THEN 1 ELSE 0 END as FILLED IN**
FROM lists l"""
INNER JOIN revisions r ON l.id = r.list_id
**LEFT OUTER JOIN answers a ON a.revision_id = r.id**
INNER JOIN employeelists el ON el.list_id= l.id
INNER JOIN employees e ON e.id = el.employee_id
INNER JOIN customers c ON c.id = e.customer_id
WHERE customer_id = :id AND r.actief = 1
now the problem is that every employee is shown multiple times...
This is the SQLFiddle of the working database, The only thing i can't do is check if the given employee ( werknemer ) exists in the answers ( antwoorden ) table..
http://sqlfiddle.com/#!2/0c01c/4
Any idea on how i can solve this? I tried a subquery, but that didn't work out either.. Thanks!
Problem with Query Now
I thought i was correct but there's one more error. in the answers table, it shows results for werknemer_id ( employee_id ) = 78. For the revisie ( revision ) 1 and 2
While there is only results for revisie 1 (screenshot below)
Thanks!
How about this exist column will have 0 if not in antwoorden and 1 if exist
SELECT l.id, l.naam, r.revisie as revisie, r.id as revisie_id, r.beschrijving, w.id as werknemer, w.voornaam, w.achternaam
, a.werknemer_id,
(CASE WHEN a.werknemer_id IS NULL THEN 0 ELSE 1 END ) AS `exist`
FROM lijsten l
INNER JOIN revisies r ON l.id = r.lijst_id
INNER JOIN werknemerlijsten wl ON wl.lijst_id = l.id
INNER JOIN werknemers w ON w.id = wl.werknemer_id
INNER JOIN klanten k ON k.id = w.klant_id
LEFT JOIN antwoorden a ON w.id = a.werknemer_id
WHERE klant_id = 39 AND r.actief = 1
GROUP BY r.beschrijving, w.id
Fiddle
Final solution
This is the final outcome, only see 'ingevuld' is 1 if the desired coach (1 in thise case) is in the answers table.
SELECT l.id, l.naam, r.revisie AS revisie, r.id AS revisie_id, r.beschrijving, w.id AS werknemer, w.voornaam, w.achternaam, a.coach_id,
CASE WHEN a.coach_id = 1 THEN 1 ELSE 0 END AS ingevuld
FROM lijsten l
INNER JOIN revisies r ON l.id = r.lijst_id
INNER JOIN werknemerlijsten wl ON wl.lijst_id = l.id
INNER JOIN werknemers w ON w.id = wl.werknemer_id
INNER JOIN klanten k ON k.id = w.klant_id
LEFT JOIN antwoorden a ON w.id = a.werknemer_id AND r.id=a.revisie_id
WHERE klant_id = 39 AND r.actief = 1
group by r.id, w.id, a.coach_id

only returning records when s.id = u.summary_id

select
s.id, s.description, s.improvement, s.previous_year_id,
s.current_year_id, s.first_name, s.last_name, s.username,
s.finding, s.action, s.share, s.learned, s.timestamp,
d.title as department_title,
group_concat(g.title SEPARATOR \' | \') as strategic_goals,
y1.year as current_year_title, y2.year as previous_year_title,
u.summary_id, u.file_name as file_name
from
summary s, year y1, year y2, strategic_goal_entries sge,
goal g, department d, uploads u
where
s.id = sge.summary_id
and
s.current_year_id = y1.id
and
s.previous_year_id = y2.id
and
sge.goal_id = g.id
and
s.id = u.summary_id
and
s.department_id = d.id
and
s.department_id = '4'
group by
s.id
This only returns records from the summary table that has a relating record in the uploads table (s.id = uploads.summary_id) that contain a value within the uploads.summary_id field
I want to return all records, whether or not it has a file associated with it.
Any help is appreciated.
Suggest refactoring this SQL query to use ANSI joins. To achive your goal, you'd want a LEFT JOIN instead:
SELECT /*your columns*/
from summary s
INNER JOIN year y1 ON s.current_year_id = y1.id
INNER JOIN year y2 ON s.previous_year_id = y2.id
INNER JOIN strategic_goal_entries sge ON s.id = sge.summary_id
INNER JOIN goal g ON sge.goal_id = g.id
INNER JOIN department d ON s.department_id = d.id
LEFT JOIN uploads u ON s.id = u.summary_id
WHERE s.department_id = '4'
group by s.id