The HackerRank Question is here.
My code for this challenge is in MySQL:
SELECT c.hacker_id as id, h.name as name, COUNT(c.hacker_id) as cnt
FROM hackers h INNER JOIN challenges c
ON h.hacker_id = c.hacker_id
GROUP BY c.hacker_id
HAVING cnt in (
SELECT MAX(Counter1)
FROM (
SELECT COUNT(*) as Counter1
FROM challenges c1
GROUP BY c1.hacker_id
ORDER BY Counter1, c1.hacker_id
) LIMIT 1
) OR IN (
SELECT Counter2
FROM (
SELECT COUNT(*) as Counter2
FROM challenges c2
GROUP BY c2.hacker_id
HAVING Counter2=1
)
)
ORDER BY cnt DESC, id;
But the error says
ERROR 1064 (42000) at line 1: You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near 'IN (
SELECT Counter2
FROM (
SELECT COUNT(*) as Counter2
' at line 13
How shall I correct my answer? How do I improve my running speed? and I am confused about the rules that when shall I give alias to subqueries table and when shall not?
Thank you!
Use a with clause and define your counts there and pass it in the having clause.
It sux.. they have a pretty low version of mysql -> see the output for "select version()"
5.7.27-0ubuntu0.18.04.1
Anyway.. if you wanna stick with MySQL you would have to repeat your "core" query multiple times :( this version does not support WITH clause .. which makes it more readable ...
/*
Enter your query here.
*/
SELECT a.hacker_id
, a.name
, a.ch_cnt as challenges_created
FROM ( -- get all challenges
SELECT h.hacker_id
, h.name
, count(c.challenge_id) as ch_cnt
FROM hackers h
LEFT JOIN challenges c
ON c.hacker_id = h.hacker_id
WHERE 1=1
GROUP BY h.hacker_id
, h.name
) a
--
LEFT JOIN ( -- tag challenges with duplicate numbers (>1)
SELECT ch_cnt
, count(*) as dupl
FROM (
SELECT h.hacker_id
, h.name
, count(c.challenge_id) as ch_cnt
FROM hackers h
LEFT JOIN challenges c
ON c.hacker_id = h.hacker_id
WHERE 1=1
GROUP BY h.hacker_id
, h.name
) bb
GROUP BY ch_cnt
HAVING count(*) > 1
) b
ON a.ch_cnt = b.ch_cnt
--
LEFT JOIN ( -- tag challenges with the max count
SELECT max(ch_cnt) ch_cnt
FROM (
SELECT h.hacker_id
, h.name
, count(c.challenge_id) as ch_cnt
FROM hackers h
LEFT JOIN challenges c
ON c.hacker_id = h.hacker_id
WHERE 1=1
GROUP BY h.hacker_id
, h.name
) cc
) c
ON a.ch_cnt = c.ch_cnt
--
WHERE 1=1
AND (
b.ch_cnt IS NULL -- remove duplicates
OR c.ch_cnt IS NOT NULL -- keep the duplicates for the max nbr of challenges
)
--
ORDER BY 3 DESC, 1 ASC
winning query: Congratulations!
The following question is based on a HackerRank question here. It is written as follows:
Julia asked her students to create some coding challenges. Write a
query to print the hacker_id, name, and the total number of challenges
created by each student. Sort your results by the total number of
challenges in descending order. If more than one student created the
same number of challenges, then sort the result by hacker_id. If more
than one student created the same number of challenges and the count
is less than the maximum number of challenges created, then exclude
those students from the result.
In the challenge, I submitted the following, but for some reason there is a syntax error. What is the problem?
select h.hacker_id
, h.name
, count(c.challenge_id) count1
from hackers h
join challenges c
on c.hacker_id = h.hacker_id
where h.hacker_id not in
(select hh.hacker_id
from hackers hh
join challenges cc
on cc.hacker_id = hh.hacker_id
join
( select hhh.hacker_id
, count(ccc.challenge_id) count2
from hackers hhh
join challenges ccc
on ccc.hacker_id = hhh.hacker_id
group
by hhh.hacker_id
having count(ccc.challenge_id) <
(select max(count2)
from
( select count(cc.challenge_id) count2
from hackers hh
join challenges cc
on hh.hacker_id = cc.hacker_id
) a
) b
) t
on t.hacker_id <> hh.hacker_id
) c
group
by h.hacker_id
, h.name
order
by count(c.challenge_id)
, h.hacker_id desc
I can't comment on the validity of what follows, but it is at least syntactically valid...
select c.hacker_id
, h.name
, count(c.hacker_id) c_count
from hackers h
join challenges c
on c.hacker_id = h.hacker_id
group
by c.hacker_id
, h.name
having c_count =
( SELECT MAX(temp1.cnt)
from
( SELECT COUNT(hacker_id) cnt
from challenges
group
by hacker_id
) temp1
)
or c_count in
(select t.cnt
from
( select count(*) cnt
from challenges
group
by hacker_id
) t
group
by t.cnt
having count(t.cnt) = 1)
order
by c_count DESC
, c.hacker_id
I have tested the below two methods and they both worked fine. Just different approach to the question.
/*
Working platform:- MySQL
/
/
SELECT H.HACKER_ID,
H.NAME,
COUNT(C.CHALLENGE_ID) AS C_COUNT
FROM HACKERS H
JOIN CHALLENGES C ON C.HACKER_ID = H.HACKER_ID
GROUP BY H.HACKER_ID, H.NAME
HAVING C_COUNT =
(SELECT COUNT(C2.CHALLENGE_ID) AS C_MAX
FROM CHALLENGES AS C2
GROUP BY C2.HACKER_ID
ORDER BY C_MAX DESC LIMIT 1)
OR C_COUNT IN
(SELECT DISTINCT C_COMPARE AS C_UNIQUE
FROM (SELECT H2.HACKER_ID,
H2.NAME,
COUNT(CHALLENGE_ID) AS C_COMPARE
FROM HACKERS H2
JOIN CHALLENGES C ON C.HACKER_ID = H2.HACKER_ID
GROUP BY H2.HACKER_ID, H2.NAME) COUNTS
GROUP BY C_COMPARE
HAVING COUNT(C_COMPARE) = 1)
ORDER BY C_COUNT DESC, H.HACKER_ID;
*/
/*
The above is the original code
The following is the code I suggest
The idea is instead of looking for unique counts, you eliminate counts that are not unique
Credit: https://medium.com/jen-li-chen-in-data-science/hackerrank-sql-bd819dfcaee7
*/
SELECT c.hacker_id, h.name, count(c.challenge_id) AS cnt
FROM Hackers AS h JOIN Challenges AS c ON h.hacker_id = c.hacker_id
GROUP BY c.hacker_id, h.name
HAVING cnt = (SELECT count(c1.challenge_id) FROM Challenges AS c1 GROUP BY c1.hacker_id
ORDER BY count(*) desc limit 1) or
cnt NOT IN (SELECT count(c2.challenge_id) FROM Challenges AS c2 GROUP BY c2.hacker_id
HAVING c2.hacker_id <> c.hacker_id)
ORDER BY cnt DESC, c.hacker_id;
I don't understand what's the meaning of this clause:
cn = (select count(c1.challenge_id) from challenges as c1
group by c1.hacker_id
order by count(c1.challenge_id) desc limit 1) "?
Whole SQL:
select c.hacker_id, h.name, count(c.challenge_id) as cn
from challenges as c join hackers as h
on c.hacker_id = h.hacker_id
group by c.hacker_id having
cn =
(select count(c1.challenge_id) from challenges as c1
group by c1.hacker_id
order by count(c1.challenge_id) desc limit 1)
or
cn not in
(select count(c2.challenge_id) from challenges as c2
group by c2.hacker_id having
c.hacker_id != c2.hacker_id)
order by cn desc, c.hacker_id
select count(c1.challenge_id) from challenge
It counts the number of challenges.
select count(c1.challenge_id) from challenges as c1
group by c1.hacker_id
It counts challenges created by hacker.
E.g Hacker A has created 56 challenges
Hacker B has create 36 challenges
order by count(c1.challenge_id) desc limit 1
It orders the count of challenges by hackers in descending order. Limit 1 picks up the first element in this order.
It's a query of finding the maximum challenges.
Write a query to print the hacker_id, name, and the total number of challenges created by each student. Sort your results by the total number of challenges in descending order. If more than one student created the same number of challenges, then sort the result by hacker_id. If more than one student created the same number of challenges and the count is less than the maximum number of challenges created, then exclude those students from the result.
I have also attached the images for the respective tables
Table Hackers:
hacker_id name
5077 Rose
21283 Angela
62743 Frank
88255 Patrick
96196 Lisa
Table Challenges:
challenge_id hacker_id
61654 5077
58302 21283
40587 88255
29477 5077
1220 21283
69514 21283
46561 62743
58077 62743
18483 88255
76766 21283
52382 5077
74467 21283
33625 96196
26053 88255
42665 62743
12859 62743
70094 21283
34599 88255
54680 88255
61881 5077
So, far I have done this
SELECT c.hacker_id, h.name, COUNT(c.challenge_id) AS challenge_count
FROM Challenges c LEFT JOIN Hackers h on c.hacker_id = h.hacker_id
GROUP by 1,c.hacker_id HAVING challenge_count >=
MAX(challenge_count) ORDER BY challenge_count DESC ,c.hacker_id DESC;
But not getting expected output. My output
I need to exclude duplicate results from output such as hackers with same number of challenges should be excluded.
There are several criteria here:
hacker_id, name, and the total number of challenges created by each student
sort your results by the total number of challenges in descending order.
If more than one student created the same number of challenges, then sort the result by hacker_id.
If more than one student created the same number of challenges then exclude those students from the result.
Except if the count equals the maximum number of challenges created,
The following deals with items 1,2, & 3...
SELECT h.*
, COUNT(c.challenge_id) challenge_count
FROM hackers h
JOIN challenges c
ON c.hacker_id = h.hacker_id
GROUP
BY h.hacker_id
ORDER
BY challenge_count DESC, hacker_id;
We can join this query to itself once, to resolve criteria 4, and again to resolve item 5, as follows:
SELECT DISTINCT a.*
FROM
( SELECT h.*
, COUNT(c.challenge_id) challenge_count
FROM hackers h
JOIN challenges c
ON c.hacker_id = h.hacker_id
GROUP
BY h.hacker_id
) a
LEFT
JOIN
( SELECT h.*
, COUNT(c.challenge_id) challenge_count
FROM hackers h
JOIN challenges c
ON c.hacker_id = h.hacker_id
GROUP
BY h.hacker_id
) b
ON b.hacker_id <> a.hacker_id AND b.challenge_count = a.challenge_count
LEFT
JOIN
( SELECT h.*
, COUNT(c.challenge_id) challenge_count
FROM hackers h
JOIN challenges c
ON c.hacker_id = h.hacker_id
GROUP
BY h.hacker_id
) c
ON c.challenge_count > a.challenge_count
WHERE b.hacker_id IS NULL
OR c.hacker_id IS NULL
ORDER
BY challenge_count DESC, hacker_id;
SELECT t1.name,
t1.hacker_id,
COALESCE(t2.challengeCount, 0) AS challengeCount
FROM Hackers t1
LEFT JOIN
(
SELECT hacker_id, COUNT(*) AS challengeCount
FROM Challenges
GROUP BY hacker_id
) t2
ON t1.hacker_id = t2.hacker_id
WHERE COALESCE(t2.challengeCount, 0) IN
(
SELECT t1.challengeCount
FROM
(
SELECT t1.hacker_id,
COALESCE(t2.challengeCount, 0) AS challengeCount
FROM Hackers t1
LEFT JOIN
(
SELECT hacker_id, COUNT(*) AS challengeCount
FROM Challenges
GROUP BY hacker_id
) t2
ON t1.hacker_id = t2.hacker_id
) t1
GROUP BY t1.challengeCount
HAVING COUNT(*) = 1
) OR COALESCE(t2.challengeCount, 0) =
(
SELECT MAX(t.challengeCount) FROM
(
SELECT COUNT(*) AS challengeCount
FROM Challenges GROUP BY hacker_id
) t
)
ORDER BY COALESCE(t2.challengeCount, 0) DESC,
t1.hacker_id
I am stuck at some problem. The problem has two tables, namely hackers and challenges.
Here is the schema:
Hackers(hacker_id: int, name string)
Challenges(challenge_id: int, hacker_id int)
I am trying to write a query to print the hacker_id, name, and the total number of challenges created by each student. Sort your results by the total number of challenges in descending order. If more than one student created the same number of challenges, then sort the result by hacker_id. If more than one student created the same number of challenges and the count is less than the maximum number of challenges created, then exclude those students from the result.
Here is my query:
select hackers.hacker_id ,
hackers.name ,
count(challenges.challenge_id) as challenges_created
from
hackers left join challenges
on
hackers.hacker_id = challenges.hacker_id
having
count(challenges_created) >= max(challenges_created)
order by challenges_created desc, hackers.hacker_id asc
I am getting wrong output!
Please tell me where I am getting wrong!
Sample Input :
Hackers Table:image
Challengers Table :image
Sample Output:
21283 Angela 6
88255 Patrick 5
96196 Lisa 1
It's a crazy requirement to solve in mysql only. With CTE (not supported by mysql) you could reuse your query:
with tmp as (
select h.hacker_id, h.name, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id, h.name
order by challenges_created desc, h.hacker_id asc
), max_challenges_created as (
select max(challenges_created) as challenges_created
from tmp
), count_per_challenges_created as (
select challenges_created, count(1) as c
from tmp
group by challenges_created
)
select *
from tmp
cross join max_challenges_created m
left join count_per_challenges_created c on c.challenges_created = tmp.challenges_created
where tmp.challenges_created = m.challenges_created
or c.c = 1
http://rextester.com/XGYQ11641
In MySQL you can't even use a temporary table, because you couldn't use it multiple times in one query. So you have to copy&paste the same query three times (and hope that mysql will execute it only once using cache):
select *
from (
select h.*, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id
order by challenges_created desc, h.hacker_id
) tmp
cross join (
select max(challenges_created) as challenges_created
from (
select h.*, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id
order by challenges_created desc, h.hacker_id asc
) tmp
) m
left join (
select challenges_created, count(1) as c
from (
select h.*, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id
order by challenges_created desc, h.hacker_id asc
) tmp
group by challenges_created
) c on c.challenges_created = tmp.challenges_created
where tmp.challenges_created = m.challenges_created
or c.c = 1
http://rextester.com/IDUMRB49795
Try start solving smallest part of the query and keep joining them.
You can try my code which is in SQL(Oracle)
SELECT h.hacker_id,
h.name,
COUNT(c.challenge_id) AS challenge_count
FROM Hackers h
JOIN Challenges c ON c.hacker_id = h.hacker_id
GROUP BY h.hacker_id, h.name
HAVING challenge_count =
(SELECT COUNT(challenge_id) AS count_max
FROM Challenges
GROUP BY hacker_id
ORDER BY count_max DESC limit 1)
OR challenge_count IN
(SELECT DISTINCT c_compare AS c_unique
FROM (SELECT h2.hacker_id,
h2.name,
COUNT(challenge_id) AS c_compare
FROM Hackers h2
JOIN Challenges c ON c.hacker_id = h2.hacker_id
GROUP BY h2.hacker_id, h2.name) counts
GROUP BY c_compare
HAVING COUNT(c_compare) = 1)
ORDER BY challenge_count DESC, h.hacker_id;
try this it's very simple....
select
h.hacker_id,
h.name
from hackers h, difficulty d, challenges c, submissions s
where
h.hacker_id=s.hacker_id
and s.challenge_id=c.challenge_id
and d.difficulty_level=c.difficulty_level
and d.score=s.score
group by h.hacker_id, h.name
having count(*)>1
ORDER BY COUNT(*) DESC, h.hacker_id;
This is not the real answer, but the start point for you:
http://sqlfiddle.com/#!9/6910c/5
SELECT h.hacker_id ,
h.name ,
COUNT(challenges.challenge_id) as challenges_created
FROM hackers h
LEFT JOIN challenges
ON h.hacker_id = challenges.hacker_id
GROUP BY h.hacker_id
#HAVING challenges_created >= max(challenges_created)
ORDER BY challenges_created desc, h.hacker_id asc
I've commented out your HAVING clause, because can not understand what you are trying to achieve.
Explain please why do you expect only 3 rows in result? Why Rose and Frank should be excluded from the result set?
The solution is easy when you use multiple joins on the necessary tables. I like to group results as derived tabled for clarity but it can be done without those derived tables too.
select hckid, nme
from
(select h.name as nme, h.hacker_id as hckid, cnt
from (select s.hacker_id as hackerid, count(d.score) as cnt
from submissions s
join challenges c
on c.challenge_id = s.challenge_id
join difficulty d
on c.difficulty_level = d.difficulty_level
where d.score = s.score
group by s.hacker_id
having count(d.score) > 1) ft
join hackers h
on ft.hackerid = h.hacker_id) t
order by t.cnt desc, t.hckid asc
select hacker_id, name, tmp.challenges_created
from (
select h.*, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id, h.name
order by challenges_created desc, h.hacker_id
) tmp
cross join (
select max(challenges_created) as challenges_created
from (
select h.*, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id, h.name
order by challenges_created desc, h.hacker_id asc
) tmp
) m
left join (
select challenges_created, count(1) as c
from (
select h.*, count(1) as challenges_created
from hackers h
left join challenges c on c.hacker_id = h.hacker_id
group by h.hacker_id, h.name
order by challenges_created desc, h.hacker_id asc
) tmp
group by challenges_created
) c on c.challenges_created = tmp.challenges_created
where tmp.challenges_created = m.challenges_created
or c.c = 1
SELECT a.hacker_id, a.name, b.id
FROM Hackers a
INNER JOIN (SELECT hacker_id, id
FROM (SELECT hacker_id, count(challenge_id) AS id
FROM Challenges
GROUP BY hacker_id) x
WHERE id = 50
UNION ALL
SELECT hacker_id,id
FROM (SELECT hacker_id, count(challenge_id) AS id
FROM Challenges
GROUP BY hacker_id) y
WHERE id IN (SELECT id
FROM (SELECT hacker_id, count(challenge_id) AS id
FROM Challenges
GROUP BY hacker_id) x
GROUP BY id
HAVING count(*) = 1)
) b ON a.hacker_id = b.hacker_id
ORDER BY id DESC, hacker_id
This is a question in hackerranck.com you can check it here [link]
in this site you can pass answer by many sql DBMS (oracale,maysql,sqlserver, and DB2)
It's Work very well for SQL-SERVER
with t
as(
Select s.hacker_id ,
s.score,d.Difficulty_level as Difficulty_level,
c.Challenge_id
From submissions s
inner join Challenges c on c.Challenge_id = s.Challenge_id
inner join Difficulty d on d.Difficulty_level = c.Difficulty_level and d.score = s.score
)
Select t.hacker_id, h.name
From t inner join hackers h ON t.hacker_id=h.hacker_id
Where t.score in (Select score from Difficulty)
Group by t.hacker_id,h.name
Having count(t.Challenge_id) > 1
Order by count(t.Challenge_id) desc,t.hacker_id asc
I have done in SQL Server
I have joined 2 different selects , the first one uses rank to determine the ones with rank 1 and the second finds duplicates , so in the join result I filtered the result to have either 1st rank or no duplicates (cnt = 1)
select s.hacker_id, s.name, s.challenge_created from (
select * ,rank() over (order by challenge_created desc) rn from (
select h.hacker_id, name, count(challenge_id) challenge_created from hackers h
inner join challenges c on h.hacker_id = c.hacker_id
group by h.hacker_id, name) as T) as S
inner join (select A.challenge_created , count(1) cnt from (select h.hacker_id, name, count(challenge_id) challenge_created from hackers h
inner join challenges c on h.hacker_id = c.hacker_id
group by h.hacker_id, name) as A group by A.challenge_created) as O
on s.challenge_created = O.challenge_created
where rn = 1 or O.cnt = 1
order by s.challenge_created desc , hacker_id
The below query works fine in mysql
For having clause condition
I have included the record in which the count is either equal to
maximum number of challenges created OR
the number of challenges created is unique
select c.hacker_id,h.name,count(c.challenge_id) as cnt from
challenges c join hackers h
on c.hacker_id = h.hacker_id
group by c.hacker_id,h.name
having cnt =
(select max(counts) from (select count(challenge_id) as counts from challenges group by hacker_id) as countstable1) or
cnt in (select counts from (select count(challenge_id) as counts from challenges group by hacker_id) as countstable2 group by counts having count(*)=1)
order by cnt desc,c.hacker_id