StarRocks Sample CSV Data load using API

카테고리

Simple Guide

생성자

Untitled

1. 데이터 다운로드
2. StarRocks DB 및 Table 생성
3. CURL을 통한 업로드
4. 쿼리를 통한 데이터 확인

1. 데이터 다운로드

New York City crash data

curl -O https://raw.githubusercontent.com/StarRocks/demo/master/documentation-samples/quickstart/datasets/NYPD_Crash_Data.csv

Weather data

curl -O https://raw.githubusercontent.com/StarRocks/demo/master/documentation-samples/quickstart/datasets/725053

2. StarRocks DB 및 Table 생성

-- DB 생성
CREATE DATABASE IF NOT EXISTS quickstart;

USE quickstart;

--사고데이터 테이블 생성
CREATE TABLE IF NOT EXISTS crashdata (
    CRASH_DATE DATETIME,
    BOROUGH STRING,
    ZIP_CODE STRING,
    LATITUDE INT,
    LONGITUDE INT,
    LOCATION STRING,
    ON_STREET_NAME STRING,
    CROSS_STREET_NAME STRING,
    OFF_STREET_NAME STRING,
    CONTRIBUTING_FACTOR_VEHICLE_1 STRING,
    CONTRIBUTING_FACTOR_VEHICLE_2 STRING,
    COLLISION_ID INT,
    VEHICLE_TYPE_CODE_1 STRING,
    VEHICLE_TYPE_CODE_2 STRING
);

--날씨데이터 테이블 생성
CREATE TABLE IF NOT EXISTS weatherdata (
    DATE DATETIME,
    NAME STRING,
    HourlyDewPointTemperature STRING,
    HourlyDryBulbTemperature STRING,
    HourlyPrecipitation STRING,
    HourlyPresentWeatherType STRING,
    HourlyPressureChange STRING,
    HourlyPressureTendency STRING,
    HourlyRelativeHumidity STRING,
    HourlySkyConditions STRING,
    HourlyVisibility STRING,
    HourlyWetBulbTemperature STRING,
    HourlyWindDirection STRING,
    HourlyWindGustSpeed STRING,
    HourlyWindSpeed STRING
);

3. CURL을 통한 업로드

New York City crash data

curl --location-trusted -u root             \
    -T ./NYPD_Crash_Data.csv                \
    -H "label:crashdata-0"                  \
    -H "column_separator:,"                 \
    -H "skip_header:1"                      \
    -H "enclose:\""                         \
    -H "max_filter_ratio:1"                 \
    -H "columns:tmp_CRASH_DATE, tmp_CRASH_TIME, CRASH_DATE=str_to_date(concat_ws(' ', tmp_CRASH_DATE, tmp_CRASH_TIME), '%m/%d/%Y %H:%i'),BOROUGH,ZIP_CODE,LATITUDE,LONGITUDE,LOCATION,ON_STREET_NAME,CROSS_STREET_NAME,OFF_STREET_NAME,NUMBER_OF_PERSONS_INJURED,NUMBER_OF_PERSONS_KILLED,NUMBER_OF_PEDESTRIANS_INJURED,NUMBER_OF_PEDESTRIANS_KILLED,NUMBER_OF_CYCLIST_INJURED,NUMBER_OF_CYCLIST_KILLED,NUMBER_OF_MOTORIST_INJURED,NUMBER_OF_MOTORIST_KILLED,CONTRIBUTING_FACTOR_VEHICLE_1,CONTRIBUTING_FACTOR_VEHICLE_2,CONTRIBUTING_FACTOR_VEHICLE_3,CONTRIBUTING_FACTOR_VEHICLE_4,CONTRIBUTING_FACTOR_VEHICLE_5,COLLISION_ID,VEHICLE_TYPE_CODE_1,VEHICLE_TYPE_CODE_2,VEHICLE_TYPE_CODE_3,VEHICLE_TYPE_CODE_4,VEHICLE_TYPE_CODE_5" \
    -XPUT http://localhost:8030/api/quickstart/crashdata/_stream_load

Weather data

curl --location-trusted -u root             \
    -T ./72505394728.csv                    \
    -H "label:weather-0"                    \
    -H "column_separator:,"                 \
    -H "skip_header:1"                      \
    -H "enclose:\""                         \
    -H "max_filter_ratio:1"                 \
    -H "columns: STATION, DATE, LATITUDE, LONGITUDE, ELEVATION, NAME, REPORT_TYPE, SOURCE, HourlyAltimeterSetting, HourlyDewPointTemperature, HourlyDryBulbTemperature, HourlyPrecipitation, HourlyPresentWeatherType, HourlyPressureChange, HourlyPressureTendency, HourlyRelativeHumidity, HourlySkyConditions, HourlySeaLevelPressure, HourlyStationPressure, HourlyVisibility, HourlyWetBulbTemperature, HourlyWindDirection, HourlyWindGustSpeed, HourlyWindSpeed, Sunrise, Sunset, DailyAverageDewPointTemperature, DailyAverageDryBulbTemperature, DailyAverageRelativeHumidity, DailyAverageSeaLevelPressure, DailyAverageStationPressure, DailyAverageWetBulbTemperature, DailyAverageWindSpeed, DailyCoolingDegreeDays, DailyDepartureFromNormalAverageTemperature, DailyHeatingDegreeDays, DailyMaximumDryBulbTemperature, DailyMinimumDryBulbTemperature, DailyPeakWindDirection, DailyPeakWindSpeed, DailyPrecipitation, DailySnowDepth, DailySnowfall, DailySustainedWindDirection, DailySustainedWindSpeed, DailyWeather, MonthlyAverageRH, MonthlyDaysWithGT001Precip, MonthlyDaysWithGT010Precip, MonthlyDaysWithGT32Temp, MonthlyDaysWithGT90Temp, MonthlyDaysWithLT0Temp, MonthlyDaysWithLT32Temp, MonthlyDepartureFromNormalAverageTemperature, MonthlyDepartureFromNormalCoolingDegreeDays, MonthlyDepartureFromNormalHeatingDegreeDays, MonthlyDepartureFromNormalMaximumTemperature, MonthlyDepartureFromNormalMinimumTemperature, MonthlyDepartureFromNormalPrecipitation, MonthlyDewpointTemperature, MonthlyGreatestPrecip, MonthlyGreatestPrecipDate, MonthlyGreatestSnowDepth, MonthlyGreatestSnowDepthDate, MonthlyGreatestSnowfall, MonthlyGreatestSnowfallDate, MonthlyMaxSeaLevelPressureValue, MonthlyMaxSeaLevelPressureValueDate, MonthlyMaxSeaLevelPressureValueTime, MonthlyMaximumTemperature, MonthlyMeanTemperature, MonthlyMinSeaLevelPressureValue, MonthlyMinSeaLevelPressureValueDate, MonthlyMinSeaLevelPressureValueTime, MonthlyMinimumTemperature, MonthlySeaLevelPressure, MonthlyStationPressure, MonthlyTotalLiquidPrecipitation, MonthlyTotalSnowfall, MonthlyWetBulb, AWND, CDSD, CLDD, DSNW, HDSD, HTDD, NormalsCoolingDegreeDay, NormalsHeatingDegreeDay, ShortDurationEndDate005, ShortDurationEndDate010, ShortDurationEndDate015, ShortDurationEndDate020, ShortDurationEndDate030, ShortDurationEndDate045, ShortDurationEndDate060, ShortDurationEndDate080, ShortDurationEndDate100, ShortDurationEndDate120, ShortDurationEndDate150, ShortDurationEndDate180, ShortDurationPrecipitationValue005, ShortDurationPrecipitationValue010, ShortDurationPrecipitationValue015, ShortDurationPrecipitationValue020, ShortDurationPrecipitationValue030, ShortDurationPrecipitationValue045, ShortDurationPrecipitationValue060, ShortDurationPrecipitationValue080, ShortDurationPrecipitationValue100, ShortDurationPrecipitationValue120, ShortDurationPrecipitationValue150, ShortDurationPrecipitationValue180, REM, BackupDirection, BackupDistance, BackupDistanceUnit, BackupElements, BackupElevation, BackupEquipment, BackupLatitude, BackupLongitude, BackupName, WindEquipmentChangeDate" \
    -XPUT http://localhost:8030/api/quickstart/weatherdata/_stream_load

4. 쿼리를 통한 데이터 확인

시간당 사고 숫자 확인해보기

SELECT COUNT(*),
       date_trunc("hour", crashdata.CRASH_DATE) AS Time
FROM crashdata
GROUP BY Time
ORDER BY Time ASC
LIMIT 200;

NYC의 평균 온도 확인해보기

SELECT avg(HourlyDryBulbTemperature),
       date_trunc("hour", weatherdata.DATE) AS Time
FROM weatherdata
GROUP BY Time
ORDER BY Time ASC
LIMIT 100;

NYC 가시성 데이터와 함께 확인하기

SELECT COUNT(DISTINCT c.COLLISION_ID) AS Crashes,
       truncate(avg(w.HourlyDryBulbTemperature), 1) AS Temp_F,
       truncate(avg(w.HourlyVisibility), 2) AS Visibility,
       max(w.HourlyPrecipitation) AS Precipitation,
       date_format((date_trunc("hour", c.CRASH_DATE)), '%d %b %Y %H:%i') AS Hour
FROM crashdata c
LEFT JOIN weatherdata w
ON date_trunc("hour", c.CRASH_DATE)=date_trunc("hour", w.DATE)
WHERE w.HourlyVisibility BETWEEN 0.0 AND 1.0
GROUP BY Hour
ORDER BY Crashes DESC
LIMIT 100;

빙판길이 높은 시간과 같이 확인하기

SELECT COUNT(DISTINCT c.COLLISION_ID) AS Crashes,
       truncate(avg(w.HourlyDryBulbTemperature), 1) AS Temp_F,
       truncate(avg(w.HourlyVisibility), 2) AS Visibility,
       max(w.HourlyPrecipitation) AS Precipitation,
       date_format((date_trunc("hour", c.CRASH_DATE)), '%d %b %Y %H:%i') AS Hour
FROM crashdata c
LEFT JOIN weatherdata w
ON date_trunc("hour", c.CRASH_DATE)=date_trunc("hour", w.DATE)
WHERE w.HourlyDryBulbTemperature BETWEEN 0.0 AND 40.5 
GROUP BY Hour
ORDER BY Crashes DESC
LIMIT 100;