计算图书平均每天销售量
package com.fengrui
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
/**
* 给定一组键值对("spark",2),("hadoop",6),("javaee",3),("spark",4),("hadoop",8),("javaee",5)
* 键值对的key表示图书名称,value表示某天图书销量,计算每种图书平均每天销量
*/
object SellingBooks {
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf().setAppName("SellingBooks").setMaster("local[*]")
val sc = new SparkContext(conf)
val books: RDD[(String, Int)] = sc.parallelize(Array(("spark",2),("hadoop",6),("javaee",3),("spark",4),("hadoop",8),("javaee",5)))
//将RDD中每个元素变为("spark",(2,1)),("spark",(4,1)),("hadoop",(6,1))...,mapValues就是操作元素中的value
val A: RDD[(String, (Int, Int))] = books.mapValues(x => (x,1))
//根据reducebykey,把key相同的value(value-list)进行聚合,比如spark这本书,("spark",(6,2))
val B: RDD[(String, (Int, Int))] = A.reduceByKey((x,y) => (x._1+y._1,x._2+y._2))
//用value值中(value-list)x._1(图书销售总数)/x._2(天数)得出平均每天销售数量
val avg: RDD[(String, Int)] = B.mapValues(x => (x._1 / x._2))
//用foreach(action)将结果遍历打印出来
avg.foreach(println)
}
}