Is there a simple and efficient solution to determine the top n elements of a Scala Iterable? I mean something like
iter.toList.sortBy(_.myAttr).take(2)
An optimised solution using PriorityQueue with Time Complexity of O(nlogk). In the approach given in the update, you are sorting the sofar list every time which is not needed and below it is optimised by using PriorityQueue.
import scala.language.implicitConversions
import scala.language.reflectiveCalls
import collection.mutable.PriorityQueue
implicit def iterExt[A](iter: Iterable[A]) = new {
def top[B](n: Int, f: A => B)(implicit ord: Ordering[B]) : List[A] = {
def updateSofar (sofar: PriorityQueue[A], el: A): PriorityQueue[A] = {
if (ord.compare(f(el), f(sofar.head)) < 0){
sofar.dequeue
sofar.enqueue(el)
}
sofar
}
val (sofar, rest) = iter.splitAt(n)
(PriorityQueue(sofar.toSeq:_*)( Ordering.by( (x :A) => f(x) ) ) /: rest) (updateSofar (_, _)).dequeueAll.toList.reverse
}
}
case class A(s: String, i: Int)
val li = List (4, 3, 6, 7, 1, 2, 9, 5).map(i => A(i.toString(), i))
println(li.top(3, -_.i))