mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-09-30 13:40:50 +00:00
395 lines
8.9 KiB
Markdown
395 lines
8.9 KiB
Markdown
|
||
<div dir="rtl" markdown="1">
|
||
|
||
# OnTime
|
||
|
||
دانلود داده ها:
|
||
|
||
</div>
|
||
|
||
```bash
|
||
for s in `seq 1987 2018`
|
||
do
|
||
for m in `seq 1 12`
|
||
do
|
||
wget https://transtats.bts.gov/PREZIP/On_Time_Reporting_Carrier_On_Time_Performance_1987_present_${s}_${m}.zip
|
||
done
|
||
done
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
(از <https://github.com/Percona-Lab/ontime-airline-performance/blob/master/download.sh> )
|
||
|
||
ساخت جدول:
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
CREATE TABLE `ontime` (
|
||
`Year` UInt16,
|
||
`Quarter` UInt8,
|
||
`Month` UInt8,
|
||
`DayofMonth` UInt8,
|
||
`DayOfWeek` UInt8,
|
||
`FlightDate` Date,
|
||
`UniqueCarrier` FixedString(7),
|
||
`AirlineID` Int32,
|
||
`Carrier` FixedString(2),
|
||
`TailNum` String,
|
||
`FlightNum` String,
|
||
`OriginAirportID` Int32,
|
||
`OriginAirportSeqID` Int32,
|
||
`OriginCityMarketID` Int32,
|
||
`Origin` FixedString(5),
|
||
`OriginCityName` String,
|
||
`OriginState` FixedString(2),
|
||
`OriginStateFips` String,
|
||
`OriginStateName` String,
|
||
`OriginWac` Int32,
|
||
`DestAirportID` Int32,
|
||
`DestAirportSeqID` Int32,
|
||
`DestCityMarketID` Int32,
|
||
`Dest` FixedString(5),
|
||
`DestCityName` String,
|
||
`DestState` FixedString(2),
|
||
`DestStateFips` String,
|
||
`DestStateName` String,
|
||
`DestWac` Int32,
|
||
`CRSDepTime` Int32,
|
||
`DepTime` Int32,
|
||
`DepDelay` Int32,
|
||
`DepDelayMinutes` Int32,
|
||
`DepDel15` Int32,
|
||
`DepartureDelayGroups` String,
|
||
`DepTimeBlk` String,
|
||
`TaxiOut` Int32,
|
||
`WheelsOff` Int32,
|
||
`WheelsOn` Int32,
|
||
`TaxiIn` Int32,
|
||
`CRSArrTime` Int32,
|
||
`ArrTime` Int32,
|
||
`ArrDelay` Int32,
|
||
`ArrDelayMinutes` Int32,
|
||
`ArrDel15` Int32,
|
||
`ArrivalDelayGroups` Int32,
|
||
`ArrTimeBlk` String,
|
||
`Cancelled` UInt8,
|
||
`CancellationCode` FixedString(1),
|
||
`Diverted` UInt8,
|
||
`CRSElapsedTime` Int32,
|
||
`ActualElapsedTime` Int32,
|
||
`AirTime` Int32,
|
||
`Flights` Int32,
|
||
`Distance` Int32,
|
||
`DistanceGroup` UInt8,
|
||
`CarrierDelay` Int32,
|
||
`WeatherDelay` Int32,
|
||
`NASDelay` Int32,
|
||
`SecurityDelay` Int32,
|
||
`LateAircraftDelay` Int32,
|
||
`FirstDepTime` String,
|
||
`TotalAddGTime` String,
|
||
`LongestAddGTime` String,
|
||
`DivAirportLandings` String,
|
||
`DivReachedDest` String,
|
||
`DivActualElapsedTime` String,
|
||
`DivArrDelay` String,
|
||
`DivDistance` String,
|
||
`Div1Airport` String,
|
||
`Div1AirportID` Int32,
|
||
`Div1AirportSeqID` Int32,
|
||
`Div1WheelsOn` String,
|
||
`Div1TotalGTime` String,
|
||
`Div1LongestGTime` String,
|
||
`Div1WheelsOff` String,
|
||
`Div1TailNum` String,
|
||
`Div2Airport` String,
|
||
`Div2AirportID` Int32,
|
||
`Div2AirportSeqID` Int32,
|
||
`Div2WheelsOn` String,
|
||
`Div2TotalGTime` String,
|
||
`Div2LongestGTime` String,
|
||
`Div2WheelsOff` String,
|
||
`Div2TailNum` String,
|
||
`Div3Airport` String,
|
||
`Div3AirportID` Int32,
|
||
`Div3AirportSeqID` Int32,
|
||
`Div3WheelsOn` String,
|
||
`Div3TotalGTime` String,
|
||
`Div3LongestGTime` String,
|
||
`Div3WheelsOff` String,
|
||
`Div3TailNum` String,
|
||
`Div4Airport` String,
|
||
`Div4AirportID` Int32,
|
||
`Div4AirportSeqID` Int32,
|
||
`Div4WheelsOn` String,
|
||
`Div4TotalGTime` String,
|
||
`Div4LongestGTime` String,
|
||
`Div4WheelsOff` String,
|
||
`Div4TailNum` String,
|
||
`Div5Airport` String,
|
||
`Div5AirportID` Int32,
|
||
`Div5AirportSeqID` Int32,
|
||
`Div5WheelsOn` String,
|
||
`Div5TotalGTime` String,
|
||
`Div5LongestGTime` String,
|
||
`Div5WheelsOff` String,
|
||
`Div5TailNum` String
|
||
) ENGINE = MergeTree(FlightDate, (Year, FlightDate), 8192)
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Load داده ها:
|
||
|
||
</div>
|
||
|
||
```bash
|
||
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
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
query ها:
|
||
|
||
Q0.
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
select avg(c1) from (select Year, Month, count(*) as c1 from ontime group by Year, Month);
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q1. تعداد پروازهای به تفکیک روز از تاریخ 2000 تا 2008
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT DayOfWeek, count(*) AS c FROM ontime WHERE Year >= 2000 AND Year <= 2008 GROUP BY DayOfWeek ORDER BY c DESC;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q2. تعداد پروازهای بیش از 10 دقیقه تاخیر خورده، گروه بندی براساس روزهای هفته از سال 2000 تا 2008
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT DayOfWeek, count(*) AS c FROM ontime WHERE DepDelay>10 AND Year >= 2000 AND Year <= 2008 GROUP BY DayOfWeek ORDER BY c DESC
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q3. تعداد تاخیرها براساس airport از سال 2000 تا 2008
|
||
|
||
</div>
|
||
|
||
``` 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
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q4. تعداد تاخیرها براساس carrier در سال 78
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Carrier, count(*) FROM ontime WHERE DepDelay>10 AND Year = 2007 GROUP BY Carrier ORDER BY count(*) DESC
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q5. درصد تاخیر ها براساس carrier در سال 2007
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Carrier, c, c2, c*100/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;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
نسخه ی بهتر query
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Carrier, avg(DepDelay > 10) * 100 AS c3 FROM ontime WHERE Year = 2007 GROUP BY Carrier ORDER BY Carrier
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q6. مانند query قبلی اما برای طیف وسیعی از سال های 2000 تا 2008
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Carrier, c, c2, c*100/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;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
نسخه ی بهتر query
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Carrier, avg(DepDelay > 10) * 100 AS c3 FROM ontime WHERE Year >= 2000 AND Year <= 2008 GROUP BY Carrier ORDER BY Carrier
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q7. درصد تاخیر بیش از 10 دقیقه پروازها به تفکیک سال
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Year, c1/c2
|
||
FROM
|
||
(
|
||
select
|
||
Year,
|
||
count(*)*100 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
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
نسخه ی بهتر query
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT Year, avg(DepDelay > 10) FROM ontime GROUP BY Year ORDER BY Year
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q8. مقصدهای پرطرفدار براساس تعداد اتصال های مستقیم شهرها برای سال 2000 تا 2010
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
SELECT DestCityName, uniqExact(OriginCityName) AS u FROM ontime WHERE Year >= 2000 and Year <= 2010 GROUP BY DestCityName ORDER BY u DESC LIMIT 10;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q9.
|
||
|
||
</div>
|
||
|
||
``` sql
|
||
select Year, count(*) as c1 from ontime group by Year;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
Q10.
|
||
|
||
</div>
|
||
|
||
``` 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;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
query های بیشتر:
|
||
|
||
</div>
|
||
|
||
``` 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;
|
||
```
|
||
|
||
<div dir="rtl" markdown="1">
|
||
|
||
این تست های performance توسط Vadim Tkachenko انجام شده است. برای اطلاعات بیشتر به لینک های زیر مراجعه کنید:
|
||
|
||
- <https://www.percona.com/blog/2009/10/02/analyzing-air-traffic-performance-with-infobright-and-monetdb/>
|
||
- <https://www.percona.com/blog/2009/10/26/air-traffic-queries-in-luciddb/>
|
||
- <https://www.percona.com/blog/2009/11/02/air-traffic-queries-in-infinidb-early-alpha/>
|
||
- <https://www.percona.com/blog/2014/04/21/using-apache-hadoop-and-impala-together-with-mysql-for-data-analysis/>
|
||
- <https://www.percona.com/blog/2016/01/07/apache-spark-with-air-ontime-performance-data/>
|
||
- <http://nickmakos.blogspot.ru/2012/08/analyzing-air-traffic-performance-with.html>
|
||
|
||
</div>
|
||
|
||
[مقاله اصلی](https://clickhouse.tech/docs/fa/getting_started/example_datasets/ontime/) <!--hide-->
|