java实现spark常用算子之map

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

/**
 *  map算子
 *  通过函数将RDD中的每一个元素转换为另一个新的RDD
 */
public class MapOperator {

    public static void main(String[] args){
        SparkConf conf = new SparkConf().setMaster("local").setAppName("mapOperator");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<Integer> numbers = Arrays.asList(1,2,3,4,5);
        JavaRDD<Integer> numberRdd = sc.parallelize(numbers);
        JavaRDD<String> result = numberRdd.map(new Function<Integer, String>() {
            @Override
            public String call(Integer inte) throws Exception{
                return "number:"+inte;
            }
        });

        result.foreach(new VoidFunction<String>() {
            @Override
            public void call(String s) throws Exception {
                System.err.println("使用map算子:"+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！