spark--Actions算子--countByKey

import org.apache.log4j.{Level, Logger}
import org.apache.spark.{SparkConf, SparkContext}

/**
  * Created by liupeng on 2017/6/17.
  */
object A_countByKey {
  System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")
  Logger.getLogger("org").setLevel(Level.ERROR)

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("countByKey_test").setMaster("local")
    val sc = new SparkContext(conf)
    //准备一下数据
    val nameList = List(("A",1),("A",2),("B",1))
    val data = sc.parallelize(nameList)
    //仅适用于类型（K，V）的RDD,返回与每个键的计数的（K，Int）对的hashmap
    val num = data.countByKey()
    for (x <- num) {
      println(x)
    }
  }
}

运行结果：

(B,1)
(A,2)