spark ds<->df

最新推荐文章于 2022-10-14 02:10:03 发布

dataastron

最新推荐文章于 2022-10-14 02:10:03 发布

阅读量371

点赞数

分类专栏： Spark

本文链接：https://blog.csdn.net/dataastron/article/details/80181630

版权

Spark 专栏收录该内容

14 篇文章 0 订阅

订阅专栏

import org.apache.spark.sql.SparkSession

object DF2DS1 {

  case class Employee(name: String, age: Long, depId: Long, gender: String, salary: Long)
  def main(args: Array[String]): Unit = {
    println("astron")
    val spark = SparkSession
      .builder()
      .master("local")
      .appName("star")
      .getOrCreate()
    import spark.implicits._
    // DF->DS
    val demoDf = spark.read.json("d://employee.json")
    println(demoDf)
    //demoDf.printSchema()
    val demoDs = demoDf.as[Employee]
    println(demoDs)
    //demoDs.printSchema()

    //DS->DF
    val newDemoDf = demoDs.toDF();
    println(newDemoDf)
    //newDemoDf.printSchema()
  }

astron
[age: bigint, depId: bigint ... 3 more fields]
[age: bigint, depId: bigint ... 3 more fields]
[age: bigint, depId: bigint ... 3 more fields]
root
 |-- age: long (nullable = true)
 |-- depId: long (nullable = true)
 |-- gender: string (nullable = true)
 |-- name: string (nullable = true)
 |-- salary: long (nullable = true)