ReduceByKey

package sparkcore

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

object Demo08ReduceByKey {
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf().setAppName("ReduceByKey").setMaster("local")

    val sc = new SparkContext(conf)

    val linesRDD: RDD[String] = sc.textFile("data/words.txt")

    val wordsRDD: RDD[String] = linesRDD.flatMap(_.split(","))

    val kvRDD: RDD[(String, Int)] = wordsRDD.map(word=>(word,1))

    /**
      * reduceByKey:对同一个key的value进行聚合处理
      */
    val countRDD: RDD[(String, Int)] = kvRDD.reduceByKey((i:Int,j:Int)=>i+j)

    countRDD.foreach(println)
    //简写，如果参数只是用了溢出，可以通过下划线代替
    val count2: RDD[(String, Int)] = kvRDD.reduceByKey(_+_)
  }

}