scala版wordcount

来源:互联网 发布:宁波淘宝托管公司排名 编辑:程序博客网 时间:2024/06/02 06:52

需求

用scala实现计算wordcount


完整实现

package coreimport org.apache.spark.{SparkConf, SparkContext}/**  *   */object BasicWordCountApp {  def main(args: Array[String]): Unit = {    //获得SparkConf    var conf = new SparkConf().setAppName("BasicWordCountApp").setMaster("local")    //获得SparkContext    val sc = new SparkContext(conf);    //加载本地文件,准备lineRDD    val lines = sc.textFile("D:/WordCount.txt")    //将每行数据根据空格分割,得到wordRDD    val wordsRDD = lines.flatMap(_.split(" "))    //转换为pairRDD    val pairRDD = wordsRDD.map((_,1))    //聚合    val wcRDD = pairRDD.reduceByKey(_+_)    //action操作,打印    wcRDD.foreach(t => println(t))  }}


0 0