Spark Action算子-＞top(num)、takeOrdered(num)

takeOrdered : 针对RDD 获取RDD中最小的前num个值，返回一个集合，放在Driver端。
top(num) :针对RDD 获取RDD中最大的前num个值，返回一个集合，放在Driver端。

1. scala

package spark

import org.apache.spark.{SparkConf, SparkContext}

/**
 * @Author yqq
 * @Date 2021/12/10 12:22
 * @Version 1.0
 */
object TopAndOrderedTest1 {
  def main(args: Array[String]): Unit = {
    val context = new SparkContext(
      new SparkConf()
        .setMaster("local")
        .setAppName("TopAndOrderedTest1")
    )
    context.setLogLevel("Error")
    context.parallelize(Array[Int](1,2,3,4,5,6,7,8,9))
      .takeOrdered(5).foreach(println)
//      .top(5).foreach(println)
  }
}

2. java

package action;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;

import java.util.Arrays;

/**
 * @Author yqq
 * @Date 2021/12/10 12:16
 * @Version 1.0
 */
public class TopAndOrderedTest {
    public static void main(String[] args) {
        JavaSparkContext context = new JavaSparkContext(
                new SparkConf()
                        .setMaster("local")
                        .setAppName("TopAndOrderedTest")
        );
        context.setLogLevel("Error");
        context.parallelize(Arrays.asList(1,2,3,4,5,6,7,8,9))
                .takeOrdered(3).forEach(e-> System.out.println(e));//获取最小前三个
//                .top(3).forEach(e-> System.out.println(e));//获取最大前三个
    }
}