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:
    彻底禁用resource manager
    NYOJ_94 cigarettes 递归VS迭代
    itunes connect上传截图提示无法加载文件问题
    hdu 1165 Eddy&#39;s research II(数学题,递推)
    USACO holstein 超时代码
    金蝶KIS标准版与金蝶K3的差别
    OC第三天(内存管理)
    HDU 1059 Dividing(多重背包)
    说说參数传递(泛型托付)
    Json数组操作小记 及 JSON对象和字符串之间的相互转换
  • 原文地址:https://www.cnblogs.com/huiandong/p/9194634.html
Copyright © 2011-2022 走看看