• Demo1


    package com.bjsxt.spark.others;

    import java.util.Arrays;
    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.FlatMapFunction;
    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;
    /**
    * 动态统计出现次数最多的单词个数,过滤掉。
    * @author root
    *
    */
    public class Demo1 {
    public static void main(String[] args) {
    SparkConf conf = new SparkConf();
    conf.setMaster("local").setAppName("demo1");
    JavaSparkContext jsc = new JavaSparkContext(conf);
    JavaRDD<String> lines = jsc.textFile("./records.txt");
    JavaRDD<String> flatMap = lines.flatMap(new FlatMapFunction<String, String>() {

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

    @Override
    public Iterable<String> call(String t) throws Exception {
    return Arrays.asList(t.split(" "));
    }
    });
    JavaPairRDD<String, Integer> mapToPair = flatMap.mapToPair(new PairFunction<String,String, Integer>() {

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

    @Override
    public Tuple2<String, Integer> call(String t) throws Exception {
    return new Tuple2<String, Integer>(t, 1);
    }
    });

    JavaPairRDD<String, Integer> sample = mapToPair.sample(true, 0.5);

    final List<Tuple2<String, Integer>> take = sample.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);
    }
    }).take(1);

    System.out.println("take--------"+take);

    JavaPairRDD<String, Integer> result = mapToPair.filter(new Function<Tuple2<String,Integer>, Boolean>() {

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

    @Override
    public Boolean call(Tuple2<String, Integer> v1) throws Exception {
    return !v1._1.equals(take.get(0)._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>, 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);
    }
    });

    result.foreach(new VoidFunction<Tuple2<String,Integer>>() {

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

    @Override
    public void call(Tuple2<String, Integer> t) throws Exception {
    System.out.println(t);
    }
    });

    jsc.stop();

    }
    }

  • 相关阅读:
    fatal error C1189: #error : Building MFC application with /MD[d] (CRT dll version) requires MFC
    error LNK2019: 无法解析的外部符号 _Direct3DCreate9@4,该符号在函数 "long __cdecl InitD3D(struct HWND__ *)" (?InitD3D
    无法将参数 1 从“WCHAR [256]”转换为“const char *”
    WPE 过滤器 高级滤镜
    WPE 过滤器 滤镜 用法
    Easy2game使用
    JMeter Concurrency Thread Group阶梯式加压
    Selenium页面工厂+数据驱动测试框架
    讨伐Cucumber行为驱动
    Selenium LoadableComponent加载组件
  • 原文地址:https://www.cnblogs.com/huiandong/p/9194609.html
Copyright © 2020-2023  润新知