按Key进行分组,使用给定的func函数聚合value值,
val arr = List(("A",3),("A",2),("B",1),("B",3))
val rdd = sc.parallelize(arr)
val reduceByKeyRDD = rdd.reduceByKey(_ +_)
reduceByKeyRDD.foreach(println)
sc.stop
# (A,5)
# (A,4)
按Key进行分组,使用给定的func函数聚合value值,
val arr = List(("A",3),("A",2),("B",1),("B",3))
val rdd = sc.parallelize(arr)
val reduceByKeyRDD = rdd.reduceByKey(_ +_)
reduceByKeyRDD.foreach(println)
sc.stop
# (A,5)
# (A,4)
转载于:https://www.cnblogs.com/pocahontas/p/11334578.html