等同于GROUP BY的JavaRDD

List<Tuple2<String, Integer>> data = Arrays.asList(
    new Tuple2<>("Alice", 30),
    new Tuple2<>("Bob", 25),
    new Tuple2<>("Alice", 35),
    new Tuple2<>("Bob", 20),
    new Tuple2<>("Charlie", 40)
);

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.SparkConf;
import scala.Tuple2;

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

public class GroupByExample {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("GroupByExample").setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(conf);

        List<Tuple2<String, Integer>> data = Arrays.asList(
            new Tuple2<>("Alice", 30),
            new Tuple2<>("Bob", 25),
            new Tuple2<>("Alice", 35),
            new Tuple2<>("Bob", 20),
            new Tuple2<>("Charlie", 40)
        );

        JavaRDD<Tuple2<String, Integer>> rdd = sc.parallelize(data);

        // 进行 groupBy 操作
        JavaPairRDD<String, Iterable<Tuple2<String, Integer>>> groupedRDD = rdd.groupBy(tuple -> tuple._1());

        // 打印结果
        groupedRDD.collect().forEach(System.out::println);

        sc.close();
    }
}

(Alice,[Tuple2(Alice,30), Tuple2(Alice,35)])
(Bob,[Tuple2(Bob,25), Tuple2(Bob,20)])
(Charlie,[Tuple2(Charlie,40)])