码迷,mamicode.com
首页 > 其他好文 > 详细

AreaTopN

时间:2018-06-18 11:50:11      阅读:119      评论:0      收藏:0      [点我收藏+]

标签:key   rdd   contex   long   fun   except   lin   website   IV   

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 org.apache.spark.api.java.function.VoidFunction;

import scala.Tuple2;

public class AreaTopN {
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<WebSiteInfo, String> mapToPair = 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")[1]+"_"+line.split("\t")[5],1);
}
}).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>, WebSiteInfo, String>() {

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

@Override
public Tuple2<WebSiteInfo, String> call(Tuple2<String,Integer> t) throws Exception {
WebSiteInfo webSiteInfo = new WebSiteInfo(t._1.split("_")[1],t._1.split("_")[0],t._2);
String s = t._1.split("_")[1]+","+t._1.split("_")[0]+"="+t._2;
return new Tuple2<WebSiteInfo, String>(webSiteInfo,s);
}
});
mapToPair.sortByKey().foreach(new VoidFunction<Tuple2<WebSiteInfo,String>>() {

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

@Override
public void call(Tuple2<WebSiteInfo, String> t)
throws Exception {
System.out.println(t);
}
});
// List<Tuple2<String, Integer>> take = mapToPair.take(5);
// for(Tuple2<String, Integer> t:take){
// System.out.println(t);
// }
sc.stop();
}
}

AreaTopN

标签:key   rdd   contex   long   fun   except   lin   website   IV   

原文地址:https://www.cnblogs.com/huiandong/p/9194632.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!