<spark>pairRDD

来源:互联网 发布:平面设计和淘宝美工 编辑:程序博客网 时间:2024/06/08 17:06
import org.apache.spark.api.java.JavaPairRDD;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.PairFunction;import scala.Tuple2;import java.util.Arrays;/** * Created by hadoop on 17-2-23. */public class JavaMyPairRDD {    public static void main(String[] args) throws Exception{        SparkConf conf = new SparkConf().setAppName("PairRDD");        JavaSparkContext sc = new JavaSparkContext(conf);        JavaRDD<String> lines = sc.parallelize(Arrays.asList("1 a","2 b"));        PairFunction<String,String,String> keyData = new PairFunction<String, String, String>() {            @Override            public Tuple2<String, String> call(String s) throws Exception {                return new Tuple2(s.split(" ")[0],s);            }        };        JavaPairRDD<String,String> pairs = lines.mapToPair(keyData);        System.out.println(pairs.collect());    }}
0 0
原创粉丝点击