Scala+Spark实现取出每个班级的top3

package com.scala.test
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD

/**
 * @author 零落尘土
 * @since 2019-10-10
 */
object ScoreCount {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("ScoreCount").setMaster("local")
    val sc = new SparkContext(conf)
    //读取文件的路径
    val lines: RDD[String] = sc.textFile("D:\\scalaProjects\\scalademo\\score.txt")
    
    lines.flatMap(line=>line.split(" ")).map(word=>(word,1)).reduceByKey((v1,v2)=>v1+v2).foreach(println)
    lines.map(line=>(line.split(" ")(0),line.split(" ")(1).toDouble)).groupByKey()
      .map(group=>{
        (group._1,group._2.toList.sortWith(_>_).take(3))
      })
      .foreach(println)
  }

}

score.txt的文件如下：

运行结果如下：