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.FlatMapFunction;
import org.apache.spark.api.java.function.VoidFunction;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List; /**
* flatmap 算子:
* 一对多 处理数据
*/
public class FlatMapOperator { public static void main(String[] args){
SparkConf conf = new SparkConf().setMaster("local").setAppName("flatmap");
JavaSparkContext sc = new JavaSparkContext(conf);
List<String> list = Arrays.asList("w1 1","w2 2","w3 3","w4 4"); JavaRDD<String> listRdd = sc.parallelize(list); JavaRDD<String> result = listRdd.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterator<String> call(String s) throws Exception {
return Arrays.asList(s.split(" ")).iterator();
}
}); result.foreach(new VoidFunction<String>() {
@Override
public void call(String s) throws Exception {
System.err.println(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!

java实现spark常用算子之flatmap的更多相关文章

  1. java实现spark常用算子之Union

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

  2. java实现spark常用算子之TakeSample

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

  3. java实现spark常用算子之SaveAsTextFile

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

  4. java实现spark常用算子之Repartitions

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

  5. java实现spark常用算子之mapPartitionsWithIndex

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

  6. 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.a ...

  7. java实现spark常用算子之intersection

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

  8. java实现spark常用算子之frist

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

  9. java实现spark常用算子之filter

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

随机推荐

  1. SQLSTATE[HY000] [2002] Connection refused

    //域名绑定到模块 '__domain__' => [ 'admin' => 'admin', 'post' => 'api', 'user' => 'index', 'www ...

  2. Maven私服搭建及使用-Windows版

    了解有限,目前只针对基础功能介绍,持续更新 一.下载对应的版本(本例版本:nexus-3.7.1-02) https://www.sonatype.com/download-oss-sonatype ...

  3. mysql 创建相同的表结构

    前言: 项目中用到分表存储,需要创建100张表,每个表的结构相同,原始操作,一个个复制粘贴,修改名字.今天DBA给了意见 create table a like b 将b的表结构和索引都复制  cre ...

  4. leetcode-hard-array- 227. Basic Calculator II

    mycode  29.58% class Solution(object): def calculate(self, s): """ :type s: str :rtyp ...

  5. js获取当前时间,并格式化为"yyyy-MM-dd HH:mm:ss"

    /** * Created by Administrator on 2019/11/15. *指尖敲打着世界 ----一个阳光而又不失帅气的少年!!!. */ // js获取当前时间,并格式化为&qu ...

  6. 小D课堂 - 新版本微服务springcloud+Docker教程_2_03常见的微服务框架

    笔记 3.常见的微服务框架     简介:讲解常用的微服务框架 consumer: 调用方         provider: 被调用方         一个接口一般都会充当两个角色(不是同时充当) ...

  7. SQL Server批量备份数据库

    --批量备份数据库201911 --开启文件夹权限 GO SP_CONFIGURE RECONFIGURE GO SP_CONFIGURE RECONFIGURE GO DECLARE ), ), ) ...

  8. 五十三:WTForms表单验证之常用验证器

    Email:验证数据是否为邮箱EqualTo:验证此字段的数据是否和另一个字段的值相等,常用与校验密码和确认密码InputRequired:检验数据必传Length:校验数据长度NumberRange ...

  9. 抓包工具chlers的使用

    1,下载chlers破解版:https://zhubangbang.com/charles-crack-version-free-download-and-install-tutorial.html ...

  10. Codeforces Round #594 (Div. 2)(A/B/C)

    A. Integer PointsDescription DLS and JLS are bored with a Math lesson. In order to entertain themsel ...