Spark入门实战WordCount

创建scala项目

但是引入spark解压出来的jar包

在这里我就用Win10的WSL了

jars目录里的全部引入

 

新建一个scala的类

 

WordCount.scala

import org.apache.spark.SparkContext

object WordCount {
  def main(args: Array[String]): Unit = {
     var sc = new SparkContext("local","wordcount")//spark上下文环境
     var file = sc.textFile("C:/Users/admin/AppData/Local/Packages/CanonicalGroupLimited.Ubuntu18.04onWindows_79rhkp1fndgsc/LocalState/rootfs/home/ubuntu/spark-2.3.0/licenses")
     var result = file.flatMap(_.split(" ")).map((_,1)).reduceByKey((a,b) => a+b).sortBy(_._2)
     result.foreach(println)
  }

}