Assume two versions for ReduceByKey   def reduceByKey(f, kvs, acc):    s = shuffle(kvs)    return map(lambda p: (p[0], reduce(f,p[1],acc)), s)   which works as:    reduceByKey(lambda x,y:x+y, [("k1",1),("k2",1), ("k1",2), ("k2",3)],0)  yields [('k1', 3), ('k2', 4)]     and  def reduceByKey2(agg, kvs):    return map(agg, shuffle(kvs))   with  reduceByKey2(lam   bda kvs:(kvs[0], sum(kvs[1])), [("k1",1),("k2",1), ("k1",2), ("k2",3)]) which yields [('k1', 3), ('k2', 4)]     and shuffle:    def merge(kvls1, kvls2):    if len(kvls1) == 0: return kvls2    elif len(kvls2) == 0: return kvls1    else:       ((k1,vl1), tl1) = (kvls1[0], kvls1[1:])       ((k2,vl2), tl2) = (kvls2[0], kvls2[1:])       if k1 == k2: return [(k1,vl1+vl2)]+merge(tl1,tl2)       elif k1 < k2: return [(k1,vl1)]+merge(tl1,kvls2)       else: return [(k2,vl2)]+merge(kvls1, tl2) def shuffle(kvs):    kvls = map(lambda kv: [(kv[0], [kv[1]])], kvs)    return reduce(merge, kvls, [])     I am wondering about the key limitations with reduceByKey2?    Also, what would be an operation that can be defined with reduceByKey2, but not by reduceByKey? I can only think of aggregations methods like median, but I think there are more.    ... View more