java實現spark常用算子之flatmap

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：
 * 一對多 處理數據
 */
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);
            }
        });
    }
}

微信掃描下圖二維碼加入博主知識星球,獲取更多大數據、人工智能、算法等免費學習資料哦！