for i in *.zip; do echo $i; unzip -cq $i '*.csv' | sed 's/\.00//g' | clickhouse-client --host=example-perftest01j --query="INSERT INTO ontime FORMAT CSVWithNames"; done
```
Запросы:
Q0.
```sql
select avg(c1) from (select Year, Month, count(*) as c1 from ontime group by Year, Month);
```
Q1. Количество полетов в день с 2000 по 2008 года
```sql
SELECT DayOfWeek, count(*) AS c FROM ontime WHERE Year >= 2000 AND Year <= 2008 GROUP BY DayOfWeek ORDER BY c DESC;
```
Q2. Количество полетов, задержанных более чем на 10 минут, с группировкой по дням неделе, за 2000-2008 года
```sql
SELECT DayOfWeek, count(*) AS c FROM ontime WHERE DepDelay>10 AND Year >= 2000 AND Year <= 2008 GROUP BY DayOfWeek ORDER BY c DESC
```
Q3. Количество задержек по аэропортам за 2000-2008
```sql
SELECT Origin, count(*) AS c FROM ontime WHERE DepDelay>10 AND Year >= 2000 AND Year <= 2008 GROUP BY Origin ORDER BY c DESC LIMIT 10
```
Q4. Количество задержек по перевозчикам за 2007 год
```sql
SELECT Carrier, count(*) FROM ontime WHERE DepDelay>10 AND Year = 2007 GROUP BY Carrier ORDER BY count(*) DESC
```
Q5. Процент задержек по перевозчикам за 2007 год
```sql
SELECT Carrier, c, c2, c*1000/c2 as c3
FROM
(
SELECT
Carrier,
count(*) AS c
FROM ontime
WHERE DepDelay>10
AND Year=2007
GROUP BY Carrier
)
ANY INNER JOIN
(
SELECT
Carrier,
count(*) AS c2
FROM ontime
WHERE Year=2007
GROUP BY Carrier
) USING Carrier
ORDER BY c3 DESC;
```
Более оптимальная версия того же запроса:
```sql
SELECT Carrier, avg(DepDelay > 10) * 1000 AS c3 FROM ontime WHERE Year = 2007 GROUP BY Carrier ORDER BY Carrier
```
Q6. Предыдущий запрос за более широкий диапазон лет, 2000-2008
```sql
SELECT Carrier, c, c2, c*1000/c2 as c3
FROM
(
SELECT
Carrier,
count(*) AS c
FROM ontime
WHERE DepDelay>10
AND Year >= 2000 AND Year <= 2008
GROUP BY Carrier
)
ANY INNER JOIN
(
SELECT
Carrier,
count(*) AS c2
FROM ontime
WHERE Year >= 2000 AND Year <= 2008
GROUP BY Carrier
) USING Carrier
ORDER BY c3 DESC;
```
Более оптимальная версия того же запроса:
```sql
SELECT Carrier, avg(DepDelay > 10) * 1000 AS c3 FROM ontime WHERE Year >= 2000 AND Year <= 2008 GROUP BY Carrier ORDER BY Carrier
```
Q7. Процент полетов, задержанных на более 10 минут, в разбивке по годам
```sql
SELECT Year, c1/c2
FROM
(
select
Year,
count(*)*1000 as c1
from ontime
WHERE DepDelay>10
GROUP BY Year
)
ANY INNER JOIN
(
select
Year,
count(*) as c2
from ontime
GROUP BY Year
) USING (Year)
ORDER BY Year
```
Более оптимальная версия того же запроса:
```sql
SELECT Year, avg(DepDelay > 10) FROM ontime GROUP BY Year ORDER BY Year
```
Q8. Самые популярные направления по количеству напрямую соединенных городов для различных диапазонов лет
```sql
SELECT DestCityName, uniqExact(OriginCityName) AS u FROM ontime WHERE Year >= 2000 and Year <= 2010 GROUP BY DestCityName ORDER BY u DESC LIMIT 10;
```
Q9.
```sql
select Year, count(*) as c1 from ontime group by Year;
```
Q10.
```sql
select
min(Year), max(Year), Carrier, count(*) as cnt,
sum(ArrDelayMinutes>30) as flights_delayed,
round(sum(ArrDelayMinutes>30)/count(*),2) as rate
FROM ontime
WHERE
DayOfWeek not in (6,7) and OriginState not in ('AK', 'HI', 'PR', 'VI')
and DestState not in ('AK', 'HI', 'PR', 'VI')
and FlightDate < '2010-01-01'
GROUP by Carrier
HAVING cnt > 100000 and max(Year) > 1990
ORDER by rate DESC
LIMIT 1000;
```
Бонус:
```sql
SELECT avg(cnt) FROM (SELECT Year,Month,count(*) AS cnt FROM ontime WHERE DepDel15=1 GROUP BY Year,Month)
select avg(c1) from (select Year,Month,count(*) as c1 from ontime group by Year,Month)
SELECT DestCityName, uniqExact(OriginCityName) AS u FROM ontime GROUP BY DestCityName ORDER BY u DESC LIMIT 10;
SELECT OriginCityName, DestCityName, count() AS c FROM ontime GROUP BY OriginCityName, DestCityName ORDER BY c DESC LIMIT 10;
SELECT OriginCityName, count() AS c FROM ontime GROUP BY OriginCityName ORDER BY c DESC LIMIT 10;
