Pv

package com.bjsxt.spark.others.pvuv;

import java.util.List;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;

import scala.Tuple2;

public class Pv {
public static void main(String[] args) {
SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("PV");
JavaSparkContext sc = new JavaSparkContext(conf);

JavaRDD<String> lines = sc.textFile("./pvuvdata");
JavaPairRDD<String, Integer> ipWeb = lines.mapToPair(new PairFunction<String, String, Integer>() {

/**
*
*/
private static final long serialVersionUID = 1L;

@Override
public Tuple2<String, Integer> call(String line) throws Exception {

return new Tuple2<String, Integer>(line.split("\t")[5],1);
}
});
JavaPairRDD<String, Integer> mapToPair = ipWeb.reduceByKey(new Function2<Integer, Integer, Integer>() {

/**
*
*/
private static final long serialVersionUID = 1L;

@Override
public Integer call(Integer v1, Integer v2) throws Exception {
return v1+v2;
}
}).mapToPair(new PairFunction<Tuple2<String,Integer>, Integer, String>() {

/**
*
*/
private static final long serialVersionUID = 1L;

@Override
public Tuple2<Integer, String> call(Tuple2<String, Integer> t)
throws Exception {
return new Tuple2<Integer, String>(t._2,t._1);
}
}).sortByKey(false).mapToPair(new PairFunction<Tuple2<Integer,String>, String,Integer>() {

/**
*
*/
private static final long serialVersionUID = 1L;

@Override
public Tuple2<String, Integer> call(Tuple2<Integer, String> t)
throws Exception {

return new Tuple2<String, Integer>(t._2,t._1) ;
}
});
List<Tuple2<String, Integer>> take = mapToPair.take(5);
for(Tuple2<String, Integer> t:take){
System.out.println(t);
}
sc.stop();
}
}

转载于:https://www.cnblogs.com/huiandong/p/9194634.html

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
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