Top N --Scala版本

Point 1：Top N

package com.scala.top

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext

object TopN {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("TopN").setMaster("local")
    val sc = new SparkContext(conf)

    val file = sc.textFile("./data/top.txt")
    val word = file.map( t => (t.toInt,t))
    val sorted = word.sortByKey(false)
    val result = sorted.map(pair => pair._2)
    result.take(3).foreach(x => println(x))
  }
}

Point 2：分组取Top N

package com.scala.top

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import java.util.ArrayList

object GroupTopN {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("GroupTopN").setMaster("local")
    val sc = new SparkContext(conf)

    val file = sc.textFile("./data/score.txt")
    val word = file.map(line =>(line.split(" ")(0),line.split(" ")(1))).groupByKey()
    val test = word.map(f =>{
      var t = List[Int]()
      for(temp <- f._2){
        t = temp.toInt :: t
      }
      (f._1,t.sortBy(x => -x).take(2))
    })
    test.foreach(println(_))
  }
}