Exemple #1
0
    def _dijkstra(self, start, targets):
        """A helper method that implements the Dijkstra algorithm.
        Return the shortest-path tree represented as a dict came_from.
        """
        came_from = {start: None}
        targets = set(targets)

        # initialize the cost of every node to be infinity, except the start
        frontier = HeapQueue((node, INF) for node in self.nodes)
        frontier.push(start, 0)

        while frontier:
            # node popped from the queue already has its shortest path found,
            # can be safely discarded
            cur_node, cur_cost = frontier.pop()
            targets.discard(cur_node)

            # if all targets are found, stop
            if not targets:
                break

            for nxt_node, weight in self.neighbors(cur_node):
                # only relax the nodes to which shortest paths are not yet found
                if nxt_node in frontier:
                    nxt_cost = cur_cost + weight

                    # if new cost less than the current cost, update it
                    if nxt_cost < frontier[nxt_node]:
                        frontier.push(nxt_node, nxt_cost)
                        came_from[nxt_node] = cur_node

        return came_from
Exemple #2
0
def balanced_partition(promoted_data1, promoted_data2, data_objects, distance_function):
	partition1 = set()
	partition2 = set()
	
	queue1 = HeapQueue(data_objects, key=lambda data:distance_function(data, promoted_data1))
	queue2 = HeapQueue(data_objects, key=lambda data:distance_function(data, promoted_data2))
	
	while queue1 or queue2:
		while queue1:
			data = queue1.pop()
			if data not in partition2:
				partition1.add(data)
				break
		
		while queue2:
			data = queue2.pop()
			if data not in partition1:
				partition2.add(data)
				break
	
	return partition1, partition2
Exemple #3
0
	def get_nearest(self, query_data, range=_INFINITY, limit=_INFINITY):
		"""
		Returns an iterator on the indexed data nearest to the query_data. The
		returned items are tuples containing the data and its distance to the
		query_data, in increasing distance order. The results can be limited by
		the range (maximum distance from the query_data) and limit arguments.
		"""
		if self.root is None:
			# No indexed data!
			return
		
		distance = self.distance_function(query_data, self.root.data)
		min_distance = max(distance - self.root.radius, 0)
		
		pending_queue = HeapQueue(
				content=[_ItemWithDistances(item=self.root, distance=distance, min_distance=min_distance)],
				key=lambda iwd: iwd.min_distance,
			)
		
		nearest_queue = HeapQueue(key=lambda iwd: iwd.distance)
		
		yielded_count = 0
		
		while pending_queue:
			pending = pending_queue.pop()
			
			node = pending.item
			assert isinstance(node, _Node)
			
			for child in node.children.itervalues():
				if abs(pending.distance - child.distance_to_parent) - child.radius <= range:
					child_distance = self.distance_function(query_data, child.data)
					child_min_distance = max(child_distance - child.radius, 0)
					if child_min_distance <= range:
						iwd = _ItemWithDistances(item=child, distance=child_distance, min_distance=child_min_distance)
						if isinstance(child, _Entry):
							nearest_queue.push(iwd)
						else:
							pending_queue.push(iwd)
			
			# Tries to yield known results so far
			if pending_queue:
				next_pending = pending_queue.head()
				next_pending_min_distance = next_pending.min_distance
			else:
				next_pending_min_distance = _INFINITY
			
			while nearest_queue:
				next_nearest = nearest_queue.head()
				assert isinstance(next_nearest, _ItemWithDistances)
				if next_nearest.distance <= next_pending_min_distance:
					_ = nearest_queue.pop()
					assert _ is next_nearest
					
					yield self.ResultItem(data=next_nearest.item.data, distance=next_nearest.distance)
					yielded_count += 1
					if yielded_count >= limit:
						# Limit reached
						return
				else:
					break