CountByKeyOperator

package com.bjsxt.scala.spark.operator

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

/**
  * Created by root on 2016/6/13.
  */
object CountByKeyOperator {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("CountByKeyOperator")
      .setMaster("local")
    val sc = new SparkContext(conf)
    val studentList = Array(Tuple2("80s","yulei"),Tuple2("80s","fengqili")
      ,Tuple2("80s","gaohaitao"),Tuple2("70s","wangfei"),Tuple2("70s","xuruyun")
      ,Tuple2("70s","xuwei"))
      /**
       * students 是一个KV格式的RDD
       * k:s
       * v:name
       * reducebykey,countByKey区别：
       * 	相同点：都会根据key来分组
       * 	不同点：
       * 			1、reducebykey会根据用户传入的聚合逻辑对组内的数据进行聚合、countByKey不需要用户传入聚合逻辑，他是直接对组内的数据进行统计记录数
       * 			2、reducebykey是transformation类算子  countByKey是action类算子
       */
    val students = sc.parallelize(studentList)
    val counts = students.countByKey()
    /**
     * 80s 3
     * 70s 3
     */
    println(counts)
  }
}