import org.apache.spark.{SparkConf, SparkContext}
/**
* Created by liupeng on 2017/6/16.
*/
object A_reduce {
System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("reduce_test").setMaster("local")
val sc = new SparkContext(conf)
//准备一下数据,有一个集合,通过reduce来进行累加
val list = List(1, 2, 3, 4, 5)
val rdd = sc.parallelize(list)
//reduce它需要两个参数并返回一个,来聚合数据集的元素。
val sum = rdd.reduce((x,y) => x + y)
println(sum)
}
}
运行结果:
15