ClickHouse/docs/ja/getting_started/example_datasets/ontime.md
2020-04-04 12:15:31 +03:00

8.9 KiB

machine_translated machine_translated_rev toc_priority toc_title
true d734a8e46d 15 オンタイム

オンタイム

このデータセットは二つの方法で取得できます:

  • 生データからインポート
  • ダウンロード調の間仕切り

生データからインポート

データ:

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

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

テーブルの作成:

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;

データのロード:

$ 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

ダウンロード調の間仕切り

$ 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 "情報" 以下で説明するクエリを実行する場合は、完全なテーブル名を使用する必要があります, datasets.ontime.

クエリ

Q0.

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

Q1. 2000年から2008年までの一日あたりの便数

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

Q2. 10分以上遅れたフライトの数は、2000年から2008年まで、曜日ごとにグループ化されています

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のための空港による遅延数

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 2007年のキャリアによる遅延の数

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

Q5 2007年のキャリアによる遅延の割合

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;

同じクエリのより良いバージョン:

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

Q6 年のより広い範囲のための以前の要求,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;

同じクエリのより良いバージョン:

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

Q7 年間で10分以上遅れたフライトの割合

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;

同じクエリのより良いバージョン:

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

Q8 様々な年の範囲のための直接接続された都市の数によって最も人気のある目的地

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;

ボーナス:

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;

この性能試験はvadim tkachenkoによって作成されました。 見る:

元の記事