<spark>RDD初识

来源：互联网发布：mac arp 嗅探工具dmg 编辑：程序博客网时间：2024/05/01 17:57

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 java.util.Arrays;/** * Created by hadoop on 17-2-23. */public class JavaPow {    public static void main(String[] args) throws Exception{    //创建java版的sparkcontext 用于返回JavaRDD        SparkConf conf = new SparkConf().setAppName("Pow");        JavaSparkContext sc = new JavaSparkContext(conf);        //RDD 弹性分布式数据集（可简单理解为spark所处理的数据所储存的地方，但是有区别        JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1,2,3,4,5,6));    //返回RDD中储存的平方        JavaRDD<Integer> result = rdd.map(new Function<Integer,Integer>(){            public Integer call(Integer x)            {                return x*x;            }        });    //输出RDD中所有数据        //System.out.println(StringUtils.join(result.collect(),","));        System.out.println(result.collect());    }}

0 0