java实现spark常用算子之coalesce

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.Function2;
import org.apache.spark.api.java.function.VoidFunction;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List;

/**
 * coalesce 算子： 将N个分区 合并为 N-M个分区
 * 分区合并(减少)，在filter后使用效果更佳，可以有效避免数据倾斜问题
 *
 */
public class CoalesceOperator {
    public static void main(String[] args){
        SparkConf conf = new SparkConf().setMaster("local").setAppName("coalesce");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<String> names = Arrays.asList("w1","w2","w3","w4","w5");

        JavaRDD<String> nameRdd = sc.parallelize(names,4);

        JavaRDD<String> namefristRdd = nameRdd.mapPartitionsWithIndex(new Function2<Integer, Iterator<String>, Iterator<String>>() {
            @Override
            public Iterator<String> call(Integer index, Iterator<String> iterator) throws Exception {
                List<String> list = new ArrayList<>();
                while (iterator.hasNext()){
                    list.add("1["+index+"]:"+iterator.next());
                }
                return list.iterator();
            }
        },true);

        // 将 4 个partition减少为2个partition
        JavaRDD<String> tempRdd = namefristRdd.coalesce(2);

        JavaRDD<String> result = tempRdd.mapPartitionsWithIndex(new Function2<Integer, Iterator<String>, Iterator<String>>() {
            @Override
            public Iterator<String> call(Integer index, Iterator<String> iterator) throws Exception {
                List<String> list = new ArrayList<>();
                while (iterator.hasNext()){
                    list.add("2["+index+"]:"+iterator.next());
                }
                return list.iterator();
            }
        },false);

        result.foreach(new VoidFunction<String>() {
            @Override
            public void call(String s) throws Exception {
                System.err.println(s);
            }
        });


    }
}

微信扫描下图二维码加入博主知识星球,获取更多大数据、人工智能、算法等免费学习资料哦！