Spark开发_构建TypeSafe的Dataset

Dataset的数据构建

构建Dataset数据

代码示例

`
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import java.io.Serializable;
import java.util.Arrays;
import java.util.List;

/**
 * 输入数据类型 IN：输入数据类型
 */
public  class WeSpark implements Serializable {
public static class EmployeeSpark implements Serializable {
    private String name;
    private long salary;

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public long getSalary() {
        return salary;
    }

    public void setSalary(long salary) {
        this.salary = salary;
    }
  public   EmployeeSpark(){}
  private   EmployeeSpark(String name, long salary){
        this.name = name;
        this.salary = salary;
    }

}
    public static void main(String[] args) {
        SparkSession spark = SparkSession
                .builder()
                .appName("Java Spark sql data sources example")
                .config("spark.some.config.option", "some-value")
                .master("local[2]")
                .getorCreate();
        //构建原始的DataFrame
        // Create an instance of a Bean class
        List<EmployeeSpark> Da = Arrays.asList(
                new EmployeeSpark("CFF",300L),
                new EmployeeSpark("ADD",200L)
        );
        Encoder<EmployeeSpark> personEncoder = Encoders.bean(EmployeeSpark.class);
        Dataset<EmployeeSpark> items2Dataset = spark.createDataset( Da, personEncoder);
        items2Dataset.printSchema();
        items2Dataset.show();
        // EmployeeSpark 无参数构造
        System.out.println(items2Dataset.head().getName());
        System.out.println(items2Dataset.head().getSalary());
    }
 }
  `

报错解决

 caused by: org.codehaus.commons.compiler.CompileException: File 'generated.java', Line 24, Column 87: 
出现动态代码生成报错
  1.把 age/depID的类型改为
  2.权限
  3.构造函数

参考

 https://www.jianshu.com/p/dc166fdfe840