sparkSql之RDD、DataFrame、DataSet转化(一)

RDD转化DataFrame

DataFrame转化DataSet

DataSet转化RDD

打印RDD

package com.bfd.sql

import org.apache.spark.SparkConf
import org.apache.spark.sql.SparkSession

object SparkSQL03_transform {
  def main(args: Array[String]): Unit = {
    //sparkSQL
    //sparkConf
    //创建配置对象
    val sparkConf = new SparkConf()
      .setMaster("local[*]")
      .setAppName("sparkSql_03")

    val spark=
      SparkSession.builder().config(sparkConf).getOrCreate()
    //创建RDD
    val rdd = spark.sparkContext.makeRDD(List(
      (1,"张三",20),
      (2,"李四",30),
      (3,"王五",40)
    ))

    //引入隐式转化
    import spark.implicits._
    //转化DF
    val df = rdd.toDF("id","name","age")
    //转化DS
    val ds = df.as[User]

    //转化RDD
    val rdd1 = ds.toDF().rdd

    rdd1.foreach(
      row =>{
        println(row.getString(1))
      }
    )
    //释放资源
    spark.stop

  }
}
//样例类：构造dataSet的数据结构
case class  User(id:Int,name:String,age:Int)