Operator_AggregateByKey

package com.bjsxt.spark.transformations;


import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;


import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.VoidFunction;


import scala.Tuple2;




public class Operator_AggregateByKey {


public static void main(String[] args) {
SparkConf sparkConf = new SparkConf().setAppName("AggregateOperator").setMaster("local");
JavaSparkContext sc = new JavaSparkContext(sparkConf);
List<Tuple2<Integer,Integer>> dataList =  new ArrayList<Tuple2<Integer,Integer>>();
dataList.add(new Tuple2<Integer, Integer>(1,99));
dataList.add(new Tuple2<Integer, Integer>(2,78));
dataList.add(new Tuple2<Integer, Integer>(1,89));
dataList.add(new Tuple2<Integer, Integer>(2,3));
dataList.add(new Tuple2<Integer, Integer>(3,3));
dataList.add(new Tuple2<Integer, Integer>(3,30));

JavaPairRDD<Integer, Integer> dataRdd = sc.parallelizePairs(dataList,2);
dataRdd.mapPartitionsWithIndex(new Function2<Integer, Iterator<Tuple2<Integer,Integer>>, Iterator<Tuple2<Integer,Integer>>>() {


/**

*/
private static final long serialVersionUID = 1L;


@Override
public Iterator<Tuple2<Integer, Integer>> call(Integer index,
Iterator<Tuple2<Integer, Integer>> iter) throws Exception {
List<Tuple2<Integer, Integer>> list = new ArrayList<Tuple2<Integer, Integer>>();
while(iter.hasNext()){
/**
* partitions --0,value ---(1,99)
partitions --0,value ---(2,78)
partitions --0,value ---(1,89)
*  partitions --1,value ---(2,3)
partitions --1,value ---(3,3)
partitions --1,value ---(3,30)
*(1,99)
  (2,78)
  (1,89)
*(2,3)
  (3,3)
  (3,30)
*/
System.out.println("partitions --"+index+",value ---"+iter.next());
}
return list.iterator();
}
}, true).collect();
System.out.println("*****************");
JavaPairRDD<Integer, Integer> aggregateByKey = dataRdd.aggregateByKey(80,
new Function2<Integer, Integer, Integer>() {
/**

*   (1,99)
  (2,78)
  (1,89)
*(2,3)
  (3,3)
  (3,30)
* seq: 80 99
seq: 80 78
seq: 99 89

seq: 80 3
seq: 80 3
seq: 80 30
*/
private static final long serialVersionUID = 1L;


@Override
public Integer call(Integer t1, Integer t2) throws Exception {
System.out.println("seq: " + t1 + "\t " + t2);
return Math.max(t1, t2);
}
},new Function2<Integer, Integer, Integer>() {


/**
* comb: 80 80
*/
private static final long serialVersionUID = 1L;


@Override
public Integer call(Integer t1, Integer t2) throws Exception {
System.out.println("comb: " + t1 + "\t " + t2);
return t1+t2;
}

});
List<Tuple2<Integer,Integer>> resultRdd = aggregateByKey.collect();
for (Tuple2<Integer, Integer> tuple2 : resultRdd) {
System.out.println(tuple2._1+"\t"+tuple2._2);
}
/*
  * 2 160
1 99
3 80
  */
}
}
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值