package com.oracle.scala
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
/**
* WordCount示例
*/
object WordCount {
def main(args: Array[String]): Unit = {
//创建SparkConf Spark运行时配置
val sparkConf = new SparkConf().setAppName("WordCount")
.setMaster("local")
//通过传入的SparkConf配置对象实例化一个SparkContext
val sc = new SparkContext(sparkConf)
//从本地文件加载数据产生RDD
val linesRdd = sc.textFile("C:\Users\Desktop\csd\wordcount.txt")
//将每一行的记录通过指定分隔符分隔
val wordsRdd = linesRdd.flatMap { _.split(" ") }
//将每一个单词设置为1 形成key-value
val pairRdd =wordsRdd.map((_ , 1))
//相同的key的value进行聚合
val resultRdd = pairRdd.reduceByKey(_+_)
//触发Job
val results = resultRdd.collect()
for(result <- results){
println(result)
}
sc.stop()
}
}