java实现spark常用算子之SortByKey

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;

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

/**
 * sortbykey([ascending],[numTasks]) 算子：
 * 根据key进行排序操作
 * 第一个参数为true,则为升序，反之为降序
 * 第二个参数决定执行的task数目
 *
 */
public class SortByKeyOperator {
    public static void main(String[] args){
        SparkConf conf = new SparkConf().setMaster("local").setAppName("sortByKey");
        JavaSparkContext sc = new JavaSparkContext(conf);

        List<Tuple2<String,Integer>> list = Arrays.asList(
                new Tuple2<String,Integer>("w1",1),
                new Tuple2<String,Integer>("w2",2),
                new Tuple2<String,Integer>("w3",3),
                new Tuple2<String,Integer>("w2",22),
                new Tuple2<String,Integer>("w1",11)
        );

        JavaPairRDD<String,Integer> pairRdd = sc.parallelizePairs(list);

        JavaPairRDD<String,Integer> result = pairRdd.sortByKey(true,2);

        result.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                System.err.println(stringIntegerTuple2._1+":"+stringIntegerTuple2._2);
            }
        });

    }
}

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！