spark rddToPairRDDFunctions countByKey

标签：spark   countbykey   

package com.latrobe.spark

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

/**
 * Created by spark on 15-1-18.
 * 计算出每个key对应的value的数量
 */
object CountByKey {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("spark-demo").setMaster("local")
    val sc = new SparkContext(conf)

    /**
     * 引入implicit def rddToPairRDDFunctions，目的是使用countByKey方法
     */
    import org.apache.spark.SparkContext._

    val c = sc.parallelize(List((1,"java"),(2,"c"),(3,"c++"),(3,"iOS")))

    //打印结果Map(2 -> 1, 1 -> 1, 3 -> 2)
    println(c.countByKey())
  }
}

spark rddToPairRDDFunctions countByKey

标签：spark   countbykey   

原文地址：http://blog.csdn.net/hi_1234567/article/details/42835561