Spark共享变量---Java

最新推荐文章于 2023-09-13 07:58:21 发布

Star-Technology

最新推荐文章于 2023-09-13 07:58:21 发布

阅读量816

点赞数

分类专栏： Big Data 文章标签： spark 共享变量 BroadCast Accumulate

本文链接：https://blog.csdn.net/ymf827311945/article/details/76549177

版权

Big Data 专栏收录该内容

140 篇文章 0 订阅

订阅专栏

Point 1：AccumulatorValue

package com.spark.sharevariables.java;

import java.util.Arrays;
import java.util.List;

import org.apache.spark.Accumulator;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.VoidFunction;

public class AccumulatorValue {

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

        final Accumulator<Integer> sum = sc.accumulator(0, "Our Accumulator");

        List<Integer> list = Arrays.asList(1,2,3,4,5);
        JavaRDD<Integer> listRDD = sc.parallelize(list);

        listRDD.foreach(new VoidFunction<Integer>() {

            private static final long serialVersionUID = 1L;

            @Override
            public void call(Integer num) throws Exception {
                sum.add(num);
//              System.out.println(sum.value());
            }
        });

        System.out.println(sum.value());
        sc.close();
    }
}

Point 2：BroadCastValue

package com.spark.sharevariables.java;

import java.util.Arrays;
import java.util.List;

import org.apache.spark.SparkConf;
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.VoidFunction;
import org.apache.spark.broadcast.Broadcast;

public class BroadCastValue {

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

        final int f = 3;
        final Broadcast<Integer> broadCastFactor = sc.broadcast(f);
        List<Integer> list = Arrays.asList(1,2,3,4,5);
        JavaRDD<Integer> listRDD = sc.parallelize(list);
        JavaRDD<Integer> results = listRDD.map(new Function<Integer, Integer>() {

            private static final long serialVersionUID = 1L;

            @Override
            public Integer call(Integer num) throws Exception {
//              return num * f;
                // 只读的
                return num * broadCastFactor.value();
            }
        });

        results.foreach(new VoidFunction<Integer>() {

            private static final long serialVersionUID = 1L;

            @Override
            public void call(Integer num) throws Exception {
                System.out.println(num);
            }
        });

        sc.close();
    }
}