spark入門cogroup簡單例子（JAVA）

maven依賴：

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.10</artifactId>
    <version>1.6.0</version>
</dependency>

public class CoGroup {
    public static void main(String[] args) {
        /**
         * 創建spark配置對象SparkConf，設置spark運行時配置信息，
         * 例如通過setMaster來設置程序要連接的集羣的Master的URL，如果設置爲local，
         * spark爲本地運行
         */
        SparkConf conf = new SparkConf().setAppName("My first spark").setMaster("local");
        /**
         * 創建JavaSparkContext對象
         * SparkContext是spark所有功能的唯一入口，
         * SparkContext核心作用，初始化spark運行所需要的核心組件，同時還會負責spark程序在master的註冊。
         *
         */
        JavaSparkContext sc = new JavaSparkContext(conf);
        /**
         * 初始化學生集合
         */
        List<Tuple2<Integer,String>> nameList = Arrays.asList(new Tuple2<Integer,String>(1,"xiaoming"),
                new Tuple2<Integer,String>(2,"feifei"),
                new Tuple2<Integer,String>(3,"katong"));
        /**
         * 初始化分數集合
         */
        List<Tuple2<Integer,Integer>> scoreList = Arrays.asList(
                new Tuple2<Integer,Integer>(1,90),
                new Tuple2<Integer,Integer>(2,80),
                new Tuple2<Integer,Integer>(1,70),
                new Tuple2<Integer,Integer>(3,60),
                new Tuple2<Integer,Integer>(2,80),
                new Tuple2<Integer,Integer>(1,70));
        //轉成rdd
        JavaPairRDD<Integer, String> names = sc.parallelizePairs(nameList);
        JavaPairRDD<Integer, Integer> scores = sc.parallelizePairs(scoreList);
        //聚合分組
        JavaPairRDD<Integer, Tuple2<Iterable<String>, Iterable<Integer>>> cogroup = names.cogroup(scores);
        //打印
        cogroup.foreach(new VoidFunction<Tuple2<Integer, Tuple2<Iterable<String>, Iterable<Integer>>>>() {
            public void call(Tuple2<Integer, Tuple2<Iterable<String>, Iterable<Integer>>> integerTuple2Tuple2) throws Exception {
                System.out.println(integerTuple2Tuple2._1+"  "+integerTuple2Tuple2._2._1+"  "+integerTuple2Tuple2._2._2);
            }
        });
        //關閉
        sc.close();
    }

}