大数据学习之Spark实现自定义排序 49

SparkRDD实现自定义排序实现Order接口,

原始方法:元组输出

部分代码如下:

方法一:自定义一个类, 实现Ordered自定义的排序

代码如下:

package day04

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * @author Dawn
  * @version 1.0, 2019年6月23日20:39:03
  *
  *          实现自定义的排序
  *          按照年龄进行排序
  */
object MySort1 {
  def main(args: Array[String]): Unit = {
    //1.Spark程序入口
    val conf:SparkConf=new SparkConf().setAppName("MySort1").setMaster("local[2]")
    val sc:SparkContext=new SparkContext(conf)

    //2.创建数组
    val girl:Array[String]=Array("dawn,20,65","yaya,20,55","susu,25,50","liuyang,18,45")

    //3.转换RDD
    val grdd: RDD[String] = sc.parallelize(girl)

    //4.切分数据
    val grdd2 = grdd.map(line => {
      val  fields: Array[String] = line.split(",")
      //拿到每个属性
      val name=fields(0).toString
      val age=fields(1).toInt
      val weight=fields(2).toInt

      //原始方法:元组输出
//      (name,age,weight)
      //自定义排序,通过实现Order接口
      new Girl(name,age,weight)
    })

    //5.按照年龄排序  倒序
//    val sortedRdd: RDD[(String, Int, Int)] = grdd2.sortBy(t => t._2,false)
//    val r=sortedRdd.collect()
//    println( r.toBuffer)

    val sortedRdd = grdd2.sortBy(t => t)
    val r = sortedRdd.collect()
    println(r.toBuffer)
    //6.关闭资源
    sc.stop()
  }
}

//自定义类 scala Ordered
class Girl(val name:String,val age:Int,val weight:Int)extends Ordered[Girl] with Serializable {
  override def compare(that: Girl): Int = {
    //如果年龄相同 体重重的往前排
    if (this.age==that.age){
      //如果正数 正序 负数 倒序
      -(this.weight-that.weight)
    }else{
      //年龄小的往前排
      this.age-that.age
    }
  }

  override def toString: String = s"名字:$name,年龄:$age,体重:$weight"
}

  

方法二:模式匹配方式进行排序

代码如下:

package day04

import org.apache.spark.{SparkConf, SparkContext}

/**
  * @author Dawn
  * @version 1.0, 2019年6月23日21:03:30
  *          模式匹配方式进行排序
  */
object MySort2 {
  def main(args: Array[String]): Unit = {
    //1.spark程序入口
    val conf:SparkConf = new SparkConf().setAppName("MySort2").setMaster("local[2]")
    val sc:SparkContext=new SparkContext(conf)

    //2.创建数组
    val girl:Array[String]=Array("dawn,20,65","yaya,20,55","susu,25,50","liuyang,18,45")

    //3.装换成RDD
    val grdd=sc.parallelize(girl)

    //4.切分数据
    val grdd1 = grdd.map(line => {
      val fields: Array[String] = line.split(",")

      val name:String=fields(0).toString
      val age:Int=fields(1).toInt
      val weight:Int=fields(2).toInt

      //元组输出
      (name,age,weight)
    })

    //5.模式匹配方式进行排序
    val sortedRdd=grdd1.sortBy(s => Girl1(s._1,s._2,s._3))
    val r = sortedRdd.collect()
    println(r.toBuffer)
    sc.stop()
  }
}

case class Girl1(val name:String,val age:Int,val weight:Int) extends Ordered[Girl1]{

  override def compare(that: Girl1) = {
    //如果年龄相同 体重重的往前排
    if (this.age==this.age){
      -(this.weight-that.weight)
    }else{
      this.age-that.age
    }

  }

  override def toString: String = s"名字:$name,年龄:$age,体重:$weight"
}

  

方法三:专门定义一个隐世类来排序

建议写成隐式类,应为可以将你需要的隐世装换全写在一个隐式类中,直接导入就行了!!

 

编写隐式类:

package day04

//定义一个专门处理隐式的类
object ImplicitRules{
  //定义隐世规则
  implicit object OrderingGirl extends Ordering[Girl2]{
    override def compare(x: Girl2, y: Girl2): Int = {
      if(x.age==y.age){
        //体重重的往前排
        -(x.weight-y.weight)
      }else{
        //年龄小的往前排
        x.age-y.age
      }
    }
  }
}

  

编写主程序:

package day04

import org.apache.spark.{SparkConf, SparkContext}

/**
  * @author Hunter
  * @version 1.0, 20:55 2019/1/16
  *          专门定义一个隐世类来排序
  *          建议写成隐式类,应为可以将你需要的隐世装换全写在一个隐式类中,直接导入就行了
  */

object MySort3 {
  def main(args: Array[String]): Unit = {
    //1.spark程序的入口
    val conf:SparkConf=new SparkConf().setAppName("MySort3").setMaster("local[2]")
    val sc:SparkContext=new SparkContext(conf)

    //2.创建数组
    val girl:Array[String]=Array("dawn,20,65","yaya,20,55","susu,25,50","liuyang,18,45")

    //3.转换RDD
    val grdd1=sc.parallelize(girl)

    //4.切分数据
    val grdd2 = grdd1.map(line => {
      val fields = line.split(",")

      val name:String=fields(0).toString
      val age:Int=fields(1).toInt
      val weight:Int=fields(2).toInt
      //元祖输出
      (name,age,weight)
    })

    import ImplicitRules.OrderingGirl
    val sortedRdd=grdd2.sortBy(s => Girl2(s._1,s._2,s._3))
    val r=sortedRdd.collect()
    println(r.toBuffer)
  }
}

case class Girl2(val name:String,val age:Int,val weight:Int)

  

posted @ 2019-07-06 21:20  大魔王阿黎  阅读(325)  评论(0编辑  收藏  举报