thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-12-15 02:41:59 +00:00
Code Issues Packages Projects Releases Wiki Activity
259de4aa95
ClickHouse/docs/tr/getting-started/example-datasets/ontime.md
Ivan Blinkov d91c97d15d
[docs] replace underscores with hyphens (#10606) 
* Replace underscores with hyphens

* remove temporary code

* fix style check

* fix collapse
2020-04-30 21:19:18 +03:00

8.8 KiB
Raw Blame History

machine_translated machine_translated_rev toc_priority toc_title
true e8cd92bba3 15 OnTime

OnTime

Bu veri kümesi iki şekilde elde edilebilir:

  • ham verilerden içe aktarma
  • hazırlanan bölüm downloadlerin indir downloadilmesi

Ham Verilerden İçe Aktarma

Veri indirme:

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

(from https://github.com/Percona-Lab/ontime-airline-performance/blob/master/download.sh )

Tablo oluşturma:

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
PARTITION BY Year
ORDER BY (Carrier, FlightDate)
SETTINGS index_granularity = 8192;

Veri yükleme:

$ 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

Hazırlanan Bölüm Downloadlerin Indir Downloadilmesi

$ curl -O https://clickhouse-datasets.s3.yandex.net/ontime/partitions/ontime.tar
$ tar xvf ontime.tar -C /var/lib/clickhouse # path to ClickHouse data directory
$ # check permissions of unpacked data, fix if required
$ sudo service clickhouse-server restart
$ clickhouse-client --query "select count(*) from datasets.ontime"

!!! info "Bilgin" Aşağıda açıklanan sorguları çalıştıracaksanız, tam tablo adını kullanmanız gerekir, datasets.ontime.

Sorgular

Q0.

SELECT avg(c1)
FROM
(
    SELECT Year, Month, count(*) AS c1
    FROM ontime
    GROUP BY Year, Month
);

Q1. 2000 yılından 2008 yılına kadar günlük uçuş sayısı

SELECT DayOfWeek, count(*) AS c
FROM ontime
WHERE Year>=2000 AND Year<=2008
GROUP BY DayOfWeek
ORDER BY c DESC;

S2. 2000-2008 için haftanın gününe göre gruplandırılmış 10 dakikadan fazla geciken uçuş sayısı

SELECT DayOfWeek, count(*) AS c
FROM ontime
WHERE DepDelay>10 AND Year>=2000 AND Year<=2008
GROUP BY DayOfWeek
ORDER BY c DESC;

Q3. 2000-2008 için havaalanı tarafından gecikme sayısı

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;

S4. 2007 yılı için taşıyıcı tarafından gecikme sayısı

SELECT Carrier, count(*)
FROM ontime
WHERE DepDelay>10 AND Year=2007
GROUP BY Carrier
ORDER BY count(*) DESC;

Q5. 2007 yılı için taşıyıcı tarafından gecikme yüzdesi

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
)
JOIN
(
    SELECT
        Carrier,
        count(*) AS c2
    FROM ontime
    WHERE Year=2007
    GROUP BY Carrier
) USING Carrier
ORDER BY c3 DESC;

Aynı sorgunun daha iyi sürümü:

SELECT Carrier, avg(DepDelay>10)*100 AS c3
FROM ontime
WHERE Year=2007
GROUP BY Carrier
ORDER BY c3 DESC

S6. Daha geniş bir yıl aralığı için önceki talep, 2000-2008

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
)
JOIN
(
    SELECT
        Carrier,
        count(*) AS c2
    FROM ontime
    WHERE Year>=2000 AND Year<=2008
    GROUP BY Carrier
) USING Carrier
ORDER BY c3 DESC;

Aynı sorgunun daha iyi sürümü:

SELECT Carrier, avg(DepDelay>10)*100 AS c3
FROM ontime
WHERE Year>=2000 AND Year<=2008
GROUP BY Carrier
ORDER BY c3 DESC;

Q7. Yıla göre 10 dakikadan fazla gecikmeli uçuş yüzdesi

SELECT Year, c1/c2
FROM
(
    select
        Year,
        count(*)*100 as c1
    from ontime
    WHERE DepDelay>10
    GROUP BY Year
)
JOIN
(
    select
        Year,
        count(*) as c2
    from ontime
    GROUP BY Year
) USING (Year)
ORDER BY Year;

Aynı sorgunun daha iyi sürümü:

SELECT Year, avg(DepDelay>10)*100
FROM ontime
GROUP BY Year
ORDER BY Year;

S8. Çeşitli yıl aralıkları için doğrudan bağlı şehirlerin sayısına göre en popüler yerler

SELECT DestCityName, uniqExact(OriginCityName) AS u
FROM ontime
WHERE Year >= 2000 and Year <= 2010
GROUP BY DestCityName
ORDER BY u DESC LIMIT 10;

Q9.

SELECT Year, count(*) AS c1
FROM ontime
GROUP BY Year;

Q10.

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;

Bonus:

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;

Bu performans testi Vadim Tkachenko tarafından oluşturuldu. Görmek:

Orijinal makale