I have two tables.
USER: ID | NAME_USER
CAR: ID | ID_USER | NAME_CAR
I want print user which have max car, how can i do this?
My try (not working):
SELECT `NAME_USER`, NAME_CARFROM FROM USER, CAR
Thank you for your help
Should be this
select user.name_user
from user
inner join (select id_user, count(*) num
from car group by id_user order by num desc limit 1) as t on t.id_user = user.id
Join the tables, count the number of cars per user, and show the one with the highest number.
SELECT name_user
FROM user
JOIN car
GROUP BY id_user
ORDER BY COUNT(*) DESC
LIMIT 1
If multiple users have the same max number of cars, this will pick one of them arbitrarily.
Related
In a MySQL 5.7 database, I have the following User table:
Name
Id
David
1
Frank
2
And the following Order table:
Id
Price
UserId
1
55
1
2
68
1
3
50
1
4
10
2
For every user, I want to select the price of the order with the biggest ID.
I can use the following query which adds additional complexity due to the nested subquery :
SELECT
User.Name,
last_user_order.Price
FROM User
LEFT JOIN (
SELECT Price, UserId FROM Order
ORDER BY Id DESC LIMIT 1
) AS last_user_order ON last_user_order.UserId = User.Id
There exist many questions here where the column to be selected is the same than the one being ordered. Hence, it is possible to use MAX in the first SELECT statement to avoid a subquery. Is it possible to avoid a subquery in my case?
For every user, I want to select the price of the order with the biggest ID.
That looks like:
SELECT
u.*,
o.Price,
FROM
User u
INNER JOIN Order o ON u.ID = o.UserID
INNER JOIN
(
SELECT MAX(ID) as OrderID FROM Order GROUP BY UserId
) maxO ON o.Id = maxO.OrderId
SELECT User.Name,
( SELECT Order.Price
FROM Order
WHERE Order.UserId = User.Id
ORDER BY Order.Id DESC LIMIT 1 ) LastPrice
FROM User;
As I'm SQL beginner, I can't describe a problem in a simple way, so let me show you an example:
3 Tables:
PRODUCT
id
group_id
person_id
GROUP
id
name
PERSON
id
group_id
As you see, GROUP can have multiple PERSONs and PRODUCT can be connected with GROUP and PERSON.
From this point, I would like to count number of PERSONs having a PRODUCT within a GROUP
I don't really understand the background of IN or using another SELECT within FROM, so if that's the point, then I'm happy that I was one step before it lol.
SELECT
group.name as GROUP_name,
COUNT(DISTINCT person_id) AS PERSON_having_min_one_PRODUCT
FROM products
LEFT JOIN groups ON groups.id = products.group_id
LEFT JOIN persons ON persons.id = products.person_id;
With this data:
GROUP
ExampleGroupName1 has 3 PERSONs, but 2 of them has >0 PRODUCTS
ExampleGroupName2 has 3 PERSONs and all of them has >0 PRODUCTS
ExampleGroupName3 has 2 PERSONs, but none of them has the PRODUCT
ExampleGroupName4 has 2 PERSONs, but only 1 has >0 PRODUCT
I would like to have an output like this:
GROUP_name | PERSON_having_min_one_PRODUCT
ExampleGroupName1 | 2
ExampleGroupName2 | 3
ExampleGroupName4 | 1
I would like to count number of PERSONs having a PRODUCT within a GROUP
Note: I will assume the table product does not have the column group_id, since it is redundant and can lead to a lot of errors.
The following query will show you the result you want by joining the tables person and product:
select
count(distinct x.id)
from person x
join product p on p.person_id = x.id
where x.group_id = 123 -- choosing a specific group
and p.id = 456 -- choosing a specific product
This would rather be simple like below meaning all the groups with some group_id with count(persons) and those count who has some product via id used in having clause
Select group_id,
count( distinct id ) AS "PERSON_WITH_PRODUCT"
from
person group by group_id having id
in (Select id from product);
Okay, so I have two tables that I need to link together with a JOIN query. There is a table called likes and a table called users. The users table looks something like this
id name
----- ------
1 Mark
2 Mike
3 Paul
4 Dave
5 Chris
6 John
The likes table looks like this.
user_one user_two match_id
----- ------ --------
1 2 abc
2 1
1 3 acc
3 1 abb
1 5 aee
5 1
The expected result should be
id name
----- ------
1 Mark
The two tables should only be linked on the rows in the likes table where the users_one column is set to the value that is most commonly found in that column. In this case, the user with the id of 1 is in the likes table with the user_one column 3 times where the match_id isn't empty.
I've thought it out to be written something like this
SELECT users.*, likes.COUNT(*) AS count
FROM users
JOIN likes
ON users.id = likes.user_one
WHERE likes.match_id != ''
But, I know this isn't correct. Is there a way to link two tables with a JOIN only on the most common rows in one of the tables?
Would Grouping work for what you need... ?
SELECT users.id, users.name, count(*) AS count
FROM users
JOIN likes
ON users.id = likes.user_one
WHERE likes.match_id != ''
group by users.id, users.name
should give you something like
1 Mark 3
Should be something like this, if I understood the question
select top 1 user_one, name
from likes
inner join users ON users.id = likes.user_one
where match_id != ''
group by user_one
order by count(*) Desc
Are you looking for something like this?
select u.id, u.name, count(*)
from users u
inner join likes l
on l.id = l.user_one and l.match_id != ''
group by u.id, u.name
order by count(*) desc
limit 1
The limit 1, combined with sorting by the # of likes in descending order will result in getting one user - the one with the most matched likes.
Try:
select *
from users
where id in (
select id
from likes
group by id
order by count(*) desc, id
limit 1
)
The subquery returns the id of the row with the most appearances in the likes table (group by id and order by count(*) desc). I've added id to the order by to give predictable results in case there are multiple with the same number of appearances. This is used to join to the users table to give the resultset required.
having a hard time pulling articles based on user country views
i have the following tables with their fields
user: id, country_id
article: id
article_views: id, user_id, article_id
each time a user views an article I insert it into the article_views table, like this:
article_views.id article_id user_id
2 1 1
3 2 1
4 2 2
5 2 2
I want to pull the highest viewed article for current user.country_id. I imagine it will contain:
order by article_views.article_id DESC
Any suggestions?
This should work fine:
select article_id, count(*) as views
from article_views inner join user on article_views.user_id = user.id
group by user.country_id
order by views desc;
Edit. I forgot about grouping article_id as #Josien pointed, the correct query is:
select country_id, article_id, count(*) as views
from article_views inner join user on article_views.user_id = user.id
where country_id = ':countryID'
group by user.country_id, article_id
order by views desc;
select av.id, count(*) as views
from article_views av inner join user u on av.user_id = u.id
where u.country_id = 'cc'
group by u.country_id
order by views desc;
Let's say I have three tables (with the columns in each):
USERS: id, name, account_id
ACCOUNTS: id, name
EVENTS: event_id, user_id, date
And I want to get the total count of events from EVENTS for each user, within a date range, along with the user's name and account name.
I can use GROUP BY to group the results by user_id, but how do I then join that to the users and accounts to get that info in each row? I'm trying to get an output like:
+-------+---------------------+--------+
| name | account_name |count(*)|
+-------+---------------------+--------+
| Joe | XYZ, Inc. | 10 |
| Bob | Vandalay Industries | 21 |
| Mary | Account Name Here | 32 |
+-------+---------------------+--------+
where the third column is the total number of events in the EVENTS table for that user_id in a specified date range.
Sorry, I can never get the hang of joins like this..
Assuming that you have an id column on users and accounts tables
SELECT
users.name,
accounts.name,
count(events.event_id)
FROM
users
INNER JOIN events ON events.user_id = users.id
INNER JOIN accounts ON accounts.id = users.account_id
WHERE
events.date between <startdate> AND <enddate>
GROUP BY
users.name,
accounts.name
The obvious ways of doing it would be:
1) group the results of a join query:
SELECT users.name, accounts.name, COUNT(*)
FROM users, accounts, events
WHERE users.account_id=accounts.id
AND users.id=events.user_id
WHERE events.date>$START_DATE
AND events.date<$END_DATE
GROUP BY users.name, accounts.name;
2) ALternatively you could use the consolidated query on just events as a data source and join to that:
SELECT users.name, accounts.name, ilv.event_count
FROM (SELECT user_id, count(*)
FROM events
WHERE events.date>$START_DATE
AND events.date<$END_DATE
GROUP BY user_id) as ilv,
users, accounts
WHERE users.id=ilv.user_id
AND users.account_id=accounts.id;
HTH
C.