scala wordcount

来源:互联网 发布:java的三层架构是什么 编辑:程序博客网 时间:2024/06/04 23:34
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD.rddToOrderedRDDFunctions
import org.apache.spark.rdd.RDD.rddToPairRDDFunctions


object WordCount {
  
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("WordCount").setMaster("local")
    val sc = new SparkContext(conf)
    
    val lines = sc.textFile("D:\\BigData\\mockData\\mockData.txt")
    val words = lines.flatMap { _.split(" ") }
    val pairs = words.map { (_, 1) }
    val results = pairs.reduceByKey(_+_)
//    val sorted = results.sortBy(pair=>pair._2, true)
    val sorted = results.sortByKey(false)
    sorted.foreach(println(_))
  }
}
0 0
原创粉丝点击