在Python中省略区域的四叉树搜索

Question

我在Python中编写的四叉树类有一个问题。我使用四叉树有效地交叉关联大型（100,000多个条目）数据目录，并且我从四叉树中得到的匹配记录省略了目录的大区域。这是整个四叉树代码。与匹配源相关的函数是nearersource（）和nearestsource（），

import math

import geom_utils as gu

MAX = 60
class Quadtree(object):
    """
    Quadtree base class. Only functions that are agnostic to
    the type of coordinate system or source object used. Must
    use a subclass.
    """
    def __init__(self, xmin, ymin, xmax, ymax):
        self.top = Node(xmin, ymin, xmax, ymax)


    def inserttonode(self, node, source):
        if len(node.contents) == MAX:
            self.subdivide(node)
        if node.q1:
            self.inserttoquad(node, source)
        else:
            # If no subquads exist add source to the list in CONTENTS element
            node.contents.append(source)

    def inserttoquad(self, node, source):
        if source.x >= node.xmid:
            if source.y >= node.ymid:
                quadrant = node.q1
            else:
                quadrant = node.q4
        else:
            if source.y >= node.ymid:
                quadrant = node.q2
            else:
                quadrant = node.q3
        self.inserttonode(quadrant, source)

    def subdivide(self, node):
        node.q1 = Node(node.xmid, node.ymid, node.xmax, node.ymax)
        node.q2 = Node(node.xmin, node.ymid, node.xmid, node.ymax)
        node.q3 = Node(node.xmin, node.ymin, node.xmid, node.ymid)
        node.q4 = Node(node.xmid, node.ymin, node.xmax, node.ymid)
        # Pop the list and insert the sources as they come off
        while node.contents:
            self.inserttoquad(node, node.contents.pop())

    def match(self, x, y):
        return self.nearestsource(self, x, y)

    def nearestsource(self, tree, x, y):
        nearest = {'source':None, 'dist':0}
        nearest['dist'] = self.initial_dist(tree.top.xmax, tree.top.xmin,
                                       tree.top.ymax, tree.top.ymin)
        interest = {'xmin':x-nearest['dist'], 'ymin':y-nearest['dist'],
                    'xmax':x+nearest['dist'], 'ymax':y+nearest['dist']}
        interest = gu.clip_box(interest['xmin'], interest['ymin'],
                               interest['xmax'], interest['ymax'],
                               tree.top.xmin, tree.top.ymin,
                               tree.top.xmax, tree.top.ymax)
        nearest['dist'] = nearest['dist']*nearest['dist']

        self.nearersource(tree, tree.top, x, y, nearest, interest)
        return nearest['source']

    def nearersource(self, tree, node, x, y, nearest, interest):
        self.num_nearersources+=1
        if gu.intersecting((node.xmin), (node.xmax),
                           (node.ymin), (node.ymax),
                           (interest['xmin']), (interest['xmax']),
                           (interest['ymin']), (interest['ymax'])):
            if node.q1 == None:
               for s in node.contents:
                    s_dist = self.norm2(s.x, s.y, x, y)
                    if s_dist < nearest['dist']:
                        nearest['source'] = s.source
                        nearest['dist'] = s_dist
                        dist = math.sqrt(s_dist)
                        interest['xmin'] = x - dist
                        interest['ymin'] = y - dist
                        interest['xmax'] = x + dist
                        interest['ymax'] = y + dist
                        interest = gu.clip_box(interest['xmin'], interest['ymin'],
                                           interest['xmax'], interest['ymax'],
                                           tree.top.xmin, tree.top.ymin,
                                           tree.top.xmax, tree.top.ymax)
            else:
                self.nearersource(tree, node.q1, x, y, nearest, interest)
                self.nearersource(tree, node.q2, x, y, nearest, interest)
                self.nearersource(tree, node.q3, x, y, nearest, interest)
                self.nearersource(tree, node.q4, x, y, nearest, interest)

class Node(object):
    def __init__(self, xmin, ymin, xmax, ymax):
        self.xmin = float(xmin)
        self.ymin = float(ymin)
        self.xmax = float(xmax)
        self.ymax = float(ymax)
        self.xmid = float((self.xmin + self.xmax)/2.0)
        self.ymid = float((self.ymin + self.ymax)/2.0)
        self.q1 = self.q2 = self.q3 = self.q4 = None
        self.contents = []

class Point(object):
    """
    The point of Point (heh.) is to have a uniform object that
    can be passed around the Quadtree. This makes for
    easy switching between equatorial and pixel coordinate
    systems or different objects.
    """
    def __init__(self, source, x, y):
        self.source = source
        self.x = float(x)
        self.y = float(y)

class ScamPixelQuadtree(Quadtree):
    def __init__(self, xmin, ymin, xmax, ymax):
        super(ScamPixelQuadtree, self).__init__(xmin, ymin, xmax, ymax)

    def insert(self, source):
        self.inserttonode(self.top, Point(source, source.ximg, source.yimg))

    def norm2(self, x1, y1, x2, y2):
        return gu.pixnorm2(x1, y1, x2, y2)

    def initial_dist(self, x2, x1, y2, y1):
        return  min(x2 - x1, y2 - y1)/1000.0

class ScamEquatorialQuadtree(Quadtree):
    def __init__(self, xmin, ymin, xmax, ymax):
        super(ScamEquatorialQuadtree, self).__init__(xmin, ymin, xmax, ymax)

    def insert(self, source):
        self.inserttonode(self.top, Point(source, source.ra, source.dec))

    def norm2(self, x1, y1, x2, y2):
        return gu.equnorm2(x1, y1, x2, y2)

    def initial_dist(self, x2, x1, y2, y1):
        return  min(x2 - x1, y2 - y1)/100.0

我尝试使MAX值非常大，实际上将树变成了一个花哨的数组，匹配工作正常（虽然很慢）。所以我认为问题可能出在nearersource（）函数中，这个函数控制我们是否会进入一个区域进行实际比较，但我无法弄清楚是什么。

我在C中编写了相同的代码，完全相同的算法，并且它工作正常。没有地区遗漏。因此，我一直在试图考虑语言特定的原因，为什么算法在C语言中起作用而在Python中起作用。我想到的第一件事就是精度，所以我尝试使用BigFloat包来代码中控制代码是否进入某个区域的部分，但它没有帮助。 C或Python中是否存在可能导致Python出现此问题的其他差异？