pipinstallduckdb

install.packages("duckdb")

# install from source using CRANinstall.packages("duckdb")# install from binaries using the Posit Public Package Manageroptions(HTTPUserAgent=sprintf("R/%s R (%s)",getRversion(),paste(getRversion(),R.version["platform"],R.version["arch"],R.version["os"])))install.packages("duckdb",repos="https://p3m.dev/cran/__linux__/manylinux_2_28/latest/")

install.packages("duckdb")

npminstall @duckdb/node-api

curlhttps://install.duckdb.org |sh

curlhttps://install.duckdb.org |sh

cargoaddduckdb--features bundled

go getgithub.com/duckdb/duckdb-go/v2

-- Get the top-3 busiest train stationsSELECTstation_name,count(*)ASnum_servicesFROMtrain_servicesGROUPBYALLORDERBYnum_servicesDESCLIMIT3;

-- Load CSV file to a table. DuckDB auto-detects-- the CSV's format, column name and typesCREATETABLEstationsASFROM'https://blobs.duckdb.org/stations.csv';

-- Directly query Parquet file over HTTPSSELECTstation_name,count(*)ASnum_servicesFROM'https://blobs.duckdb.org/train_services.parquet'GROUPBYALLORDERBYnum_servicesDESCLIMIT10;

-- Find the top-3 longest domestic train routesSELECTs1.name_short,s2.name_short,d.distanceFROMdistancesdJOINstationss1ONd.station1=s1.codeJOINstationss2ONd.station2=s2.codeWHEREs1.country=s2.countryANDs1.code<s2.codeORDERBYdistanceDESCLIMIT3;

-- List the closest IC stations (as the crow flies)SELECTs1.name_longASstation1,s2.name_longASstation2,ST_Distance(ST_Point(s1.geo_lng,s1.geo_lat),ST_Point(s2.geo_lng,s2.geo_lat))*111_139ASdistanceFROMstationss1,stationss2WHEREs1.typeLIKE'%Intercity%'ANDs2.typeLIKE'%Intercity%'ANDs1.id<s2.idORDERBYdistanceASCLIMIT3;

# Get the top-3 busiest train stationsimportduckdbduckdb.sql("""    SELECT station, count(*) AS num_services    FROM train_services    GROUP BY ALL    ORDER BY num_services DESC    LIMIT 3;    """)

# Reading and writing Pandas dataframesimportpandasaspdimportduckdbdf_in=pd.DataFrame({'station':['Delft','Delft','Gouda','Gouda'],'day':['Mon','Tue','Mon','Tue'],'num_services':[22,20,27,25]})# Run query on a dataframe and return a dataframedf_out=duckdb.sql("""    SELECT station, sum(num_services)    FROM df_in    GROUP BY station    """).to_df()

# Create custom user-defined functionimportduckdbdefplus_one(x):returnx+1con=duckdb.connect()con.create_function('plus_one',plus_one,['BIGINT'],'BIGINT',type='native')con.sql("""    SELECT sum(plus_one(i)) FROM range(10) tbl(i);    """)

# Find the largest sepals/petals in the Iris data setlibrary(duckdb)con<-dbConnect(duckdb())duckdb_register(con,"iris",iris)query<-r'(    SELECT count(*) AS num_observations,    max("Sepal.Width") AS max_width,    max("Petal.Length") AS max_petal_length    FROM iris    WHERE "Sepal.Length" > 5    GROUP BY ALL    )'dbGetQuery(con,query)

# Find the largest sepals/petals in the Iris data set# using duckplyrlibrary("duckplyr")iris|>filter(Sepal.Length>5)|>group_by(Species)|>summarize(num_observations=n(),max_width=max(Sepal.Width),max_petal_length=max(Petal.Length),na.rm=TRUE)|>collect()

# Find the largest sepals/petals in the Iris data set# using dplyrlibrary("duckdb")library("dplyr")con<-dbConnect(duckdb())duckdb_register(con,"iris",iris)tbl(con,"iris")|>filter(Sepal.Length>5)|>group_by(Species)|>summarize(num_observations=count(),max_width=max(Sepal.Width),max_petal_length=max(Petal.Length),na.rm=TRUE)|>collect()

// Get a list of train stations by trafficConnectionconn=DriverManager.getConnection("jdbc:duckdb:");Statementst=conn.createStatement();ResultSetrs=st.executeQuery("""    SELECT station_name,           count(*) AS num_services    FROM train_services    GROUP BY ALL    ORDER BY num_services DESC;    """);System.out.println(rs.next());

// Perform bulk inserts using the Appender APIDuckDBConnectionconn=(DuckDBConnection)DriverManager.getConnection("jdbc:duckdb:");Statementst=conn.createStatement();st.execute("CREATE TABLE person (name VARCHAR, age INT)");varappender=conn.createAppender(DuckDBConnection.DEFAULT_SCHEMA,"person");appender.beginRow();appender.append("MC Ducky");appender.append(49);appender.endRow();appender.close();

// Get the top-3 busiest train stations in Mayimport{DuckDBInstance}from'@duckdb/node-api';constinstance=awaitDuckDBInstance.create();constconnection=awaitinstance.connect();constreader=awaitconnection.runAndReadAll(`SELECT station_name, count(*) AS num_services   FROM   'https://blobs.duckdb.org/train_services.parquet'   WHERE monthname(date) = 'May'   GROUP BY ALL   ORDER BY num_services DESC   LIMIT 3;`);console.table(reader.getRows());

// Web Service Integration:// Create endpoint to generate numbersimportexpressfrom"express";import{DuckDBInstance}from'@duckdb/node-api';constapp=express();constinstance=awaitDuckDBInstance.create();constconnection=awaitinstance.connect();app.get("/getnumbers",async(req,res)=>{constreader=awaitconnection.runAndReadAll("SELECT random() AS num FROM range(10)");res.end(JSON.stringify(reader.getRows()));});app.listen(8082,()=>console.log("Go to: http://localhost:8082/getnumbers"));