zoukankan      html  css  js  c++  java
  • 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(" ")[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();
    }
    }

  • 相关阅读:
    GridView固定表头
    图片自动适应大小
    GridView实现用"..."代替超长字符串
    使用纯 CSS 设计3D按钮
    Net下二进制形式的文件(图片)的存储与读取
    repeater创建复杂的表头
    GridView加入自动求和求平均值小计
    CSS+DIV(盒子)
    DIV 在 IE 与 FF 下的设置
    gridView分页
  • 原文地址:https://www.cnblogs.com/huiandong/p/9194634.html
Copyright © 2011-2022 走看看