spark求各科目平均成绩

object Avg {
  System.setProperty("hadoop.home.dir","D:\\hadoop\\hadoop-2.9.2")
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local").setAppName("SortAndDistinct")
    val sc = new SparkContext(conf)
    val lineRdd = sc.textFile(args(0))

    val pairRdd = lineRdd.map(line=>(line.split(" ")(1),line.split(" ")(2)))
    val groupRdd = pairRdd.groupByKey()

    val resultRdd = groupRdd.map(tuple=>{
      var sum = 0.0
      val num = tuple._2.size
      for (score<-tuple._2){
        sum+= score.toDouble
      }
      val avg = sum/num
      val formatAvg = f"$avg%.2f"
      (tuple._1,formatAvg)
    }).coalesce(1)

    resultRdd.saveAsTextFile(args(1))

    sc.stop()
  }
}