ClickHouse系列教程二：使用航班飞行数据

ClickHouse系列教程: ClickHouse系列教程

---

根据官方提供的教程：ClickHouse Quick Start Guide

先下载数据：ontime.csv.xz — Yandex.Disk
压缩包大小是3G，解压后61G。
解压命令如下：

root@ubuntu:/home/zhang# xz -v  -d ontime.csv.xz
ontime.csv.xz (1/1)
  100 %      3,368.8 MiB / 61.6 GiB = 0.053   101 MiB/s      10:26   

然后在数据库中建表：

root@ubuntu:/home/zhang# clickhouse-client --password     --multiline
ClickHouse client version 19.9.3.31 (official build).
Password for user (default): 
Connecting to localhost:9000 as user default.
Connected to ClickHouse server version 19.9.3 revision 54421.

ubuntu :) 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