ClickHouse空间分析运用

ClickHouse

ClickHouse是一个用于联机分析(OLAP)的列式数据库管理系统(DBMS)。

OLAP场景的关键特征

ClickHouse安装和启动

sudo apt-get install apt-transport-https ca-certificates dirmngr
sudo apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv E0C56BD4
echo "deb https://repo.clickhouse.tech/deb/stable/ main/" | sudo tee \
    /etc/apt/sources.list.d/clickhouse.list
sudo apt-get update
sudo apt-get install -y clickhouse-server clickhouse-client
sudo service clickhouse-server start
clickhouse-client

sudo apt-get update如果更新不了可以修改下源，然后修改source.list，clickhouse.list

新建表导入所需要的数据(120038310条经纬度)

create table pnts (Lon  Float64, Lat Float64) engine = MergeTree() order by (Lon, Lat);
time clickhouse-client --query="INSERT INTO pnts FORMAT CSVWithNames" < test_data.csv

ClickHouse空间分析运用

计算最大小经纬度

select min(Lon), max(Lon),min(Lat), max(Lat)FROM pnts

select geohashesInBox(-150.0565255, 24.5449115001 , -66.950609997, 65.1341342731, 4)

面筛选

SELECT count(1) FROM pnts WHERE -122.1603396012797162<=Lon and -122.1414371044578786>=Lon and 37.7842593304459271  <=Lat and 37.7965938218938646  >=Lat  and pointInPolygon((Lon, Lat), [( -122.158001836655117, 37.796593821893865 ), ( -122.151099864906271, 37.793632653369357 ), ( -122.146446600082044, 37.792029614769625 ), ( -122.141437104457879, 37.789224297220095 ), ( -122.143485431557536, 37.788534100045212 ), ( -122.14290655650764, 37.786641623920524 ), ( -122.143797133507491, 37.786196335420598 ), ( -122.147648879031848, 37.784437445845896 ), ( -122.14862851373168, 37.784259330445927 ), ( -122.15312592758093, 37.788734479870179 ), ( -122.154728966180656, 37.789736378995009 ), ( -122.156443326905375, 37.788801273145168 ), ( -122.160094692604758, 37.789335619345074 ), ( -122.15915958675491, 37.792185465744602 ), ( -122.160339601279716, 37.793788504344327 ), ( -122.159293173304889, 37.795369278519068 ), ( -122.159048264629931, 37.795525129494038 ), ( -122.159048264629931, 37.795525129494038 ), ( -122.158001836655117, 37.796593821893865 )]) = 1

缓冲区计算

SELECT count(1) from pnts WHERE greatCircleDistance(Lon, Lat, -122.158001836655117, 37.796593821893865 )<=2000

select geoToH3(Lon, Lat, 3),count(1) FROM pnts group by geoToH3(Lon, Lat, 3)

geohash聚合

SELECT geohashEncode(Lon, Lat, 5),count(1) FROM pnts group by geohashEncode(Lon, Lat, 5)