dataframes.java

///usr/bin/env jbang "$0" "$@" ; exit $?
//DEPS info.picocli:picocli:4.5.0
//DEPS org.slf4j:slf4j-nop:1.7.30

//DEPS org.datavec:datavec-local:1.0.0-beta7

//DEPS joinery:joinery-dataframe:1.9
//DEPS org.apache.poi:poi:4.1.2

//DEPS tech.tablesaw:tablesaw-core:0.38.1

import static java.lang.System.out;

import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.StandardCopyOption;
import java.util.concurrent.Callable;

import org.datavec.api.records.reader.RecordReader;
import org.datavec.api.records.reader.impl.csv.CSVRecordReader;
import org.datavec.api.split.FileSplit;
import org.datavec.api.transform.TransformProcess;
import org.datavec.api.transform.schema.InferredSchema;
import org.datavec.api.transform.schema.Schema;
import org.datavec.local.transforms.LocalTransformProcessRecordReader;

import joinery.DataFrame;
import picocli.CommandLine;
import picocli.CommandLine.Command;
import picocli.CommandLine.Parameters;
import tech.tablesaw.api.Table;

@Command(name = "dataframes", mixinStandardHelpOptions = true, version = "dataframes 0.1", description = "datavec made with jbang")
class dataframes implements Callable<Integer> {

    @Parameters(index = "0", description = "The greeting to print", defaultValue = "World!")
    private String greeting;

    public static void main(String... args) {
        int exitCode = new CommandLine(new dataframes()).execute(args);
        System.exit(exitCode);
    }

    @Override
    public Integer call() throws Exception { // your business logic goes here...

        Path data = Paths.get("data.csv");
        URL url = new URL("https://people.sc.fsu.edu/~jburkardt/data/csv/airtravel.csv");
        InputStream in = url.openStream();
        Files.copy(in, data, StandardCopyOption.REPLACE_EXISTING);

        out.println("datavec:");
        readWithDatavec(data);

        out.println("joinery:");
        readWithJoinery(data);
        
        out.println("tablesaw:");
        readWithTableSaw(data);
        
        return 0;
    }

    private void readWithTableSaw(Path data) throws IOException {
        out.println(Table.read().csv(data.toFile()));
    }

    private void readWithJoinery(Path data) throws IOException {
        out.println(DataFrame.readCsv(data.toString()));
    }

    void readWithDatavec(Path data) throws IOException, InterruptedException {
        RecordReader rr = new CSVRecordReader(1);
        rr.initialize(new FileSplit(data.toFile()));

        Schema schema = new InferredSchema(data.toString()).build();        
        
        //TransformProcess even if empty seem to be required.
        TransformProcess tp = new TransformProcess.Builder(schema).build(); 

        LocalTransformProcessRecordReader tprr =
        new LocalTransformProcessRecordReader(rr, tp);
        
        while(tprr.hasNext()) {
            out.println(tprr.next());
        }
    }
}