spark action之countbykey

java

public class CountByKeyDemo {
    private static SparkConf conf = new SparkConf().setMaster("local").setAppName("countbykeydemo");
    private static JavaSparkContext jsc = new JavaSparkContext(conf);
    public static void main(String[] args) {
        List<Tuple2<String,Integer>> list = Arrays.asList(
                                            new Tuple2<String,Integer>("tele",100),
                                            new Tuple2<String,Integer>("tele",200),
                                            new Tuple2<String,Integer>("tele",300),
                                            new Tuple2<String,Integer>("yeye",50),
                                            new Tuple2<String,Integer>("yeye",10),
                                            new Tuple2<String,Integer>("yeye",70),
                                            new Tuple2<String,Integer>("wyc",10000)
                                             );
        
        JavaPairRDD<String, Integer> rdd = jsc.parallelizePairs(list);
        
        Map<String, Long> map = rdd.countByKey();
        map.entrySet().forEach(i-> System.out.println(i.getKey() + ":" + i.getValue()));
        
        jsc.close();
    }
}

scala

object CountByKeyDemo {
    def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local").setAppName("countdemo");
    val sc = new SparkContext(conf);
    
    val arr = Array(("class1","tele"),("class1","yeye"),("class2","wyc"));
    val rdd = sc.parallelize(arr,1);
    
    val result = rdd.countByKey();
    for((k,v) <- result) {
      println(k + ":" + v);
    }
  }
}