Spark 就是那么回事（1）—— wordCount

package com.test

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

object WordCount {
  def main(args: Array[String]): Unit = {
    val path = "C:\Users\Administrator\Desktop\test.txt"
    // 构建SparkContext对象
    val sparkConf = new SparkConf().setAppName("WordCount").setMaster("local")
    val sc = new SparkContext(sparkConf)

    // 读取文件
    val rdd = sc.textFile(path)
    val flapMap = rdd.flatMap(_.split(" "))
    val map = flapMap.map((_, 1))
    val reduce = map.reduceByKey(_ + _)
    val sort = reduce.map(x => (x._2, x._1)).sortByKey(false).map(x => (x._2, x._1))

    sort.foreach(x => println("word:" + x._1 + ",time:" + x._2))
  }
}

简简单单，不过需要以下条件

scala环境idea编译器java环境 附上pom文件

    4.0.0

    org.example
    SparkProject
    1.0-SNAPSHOT

    
        8
        8
    

    
        
            org.apache.spark
            spark-core_2.11
            2.4.8