java实现spark常用算子之Take

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

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

/**
 * take(n)
 * 将RDD中的前多少数据返回过来，返回结果为数据形式
 *
 */
public class TakeOperator {
    public static void main(String[] args){
        SparkConf conf = new SparkConf().setMaster("local").setAppName("take");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<String> list  = Arrays.asList("w1","w2","w3","w4","w5","w6");
        JavaRDD<String> listRdd = sc.parallelize(list);
        List<String> result = listRdd.take(3);
        System.err.println(result.toString());
    }
}

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！