输入数据：

Hello World Bye World
Hello Hadoop Bye Hadoop
Bye Hadoop Hello Hadoop

输出结果：

(Hadoop,4)
(Bye,3)
(Hello,3)
(World,2)

/**
  * 一是统计词频，二是找出词频最高的前K个词
  */
object TopNBasic {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName(TopNBasic.getClass.getSimpleName)
    conf.setMaster("local")
    val sc = new SparkContext(conf)
    val textFile = sc.textFile("E:\\newcode\\MyFirstProject\\data\\topn.txt")
    val words = textFile.flatMap(line => line.split(" "))
    val wordPairs = words.map(word => (word, 1))
    val wordCounts = wordPairs.reduceByKey((a,b) => a + b)
 // val groupRDD = textFile.map(line => (line.split(" ")(0),line.split(" ")(1).toInt)).groupByKey()
  //  val top2 = groupRDD.map(pair => (pair._1, pair._2.toList.sortWith(_>_).take(2)))
   val top2 = wordCounts.sortBy(_._2, false).take(4)

    println("wordCounts: ")
    top2.foreach(println)
  }
}

关注公众号“大模型全栈程序员”回复“小程序”获取1000个小程序打包源码。更多免费资源在http://www.gitweixin.com/?p=2627