わかりました、これは少し複雑なアルゴリズムでの私の非常に最適化されていない方法です。これは、最初にブール値の近接行列を作成し、そこから最終的に平均座標を取得するために使用されるクラスターのリストを作成します。
# -*- coding: utf-8 -*-
"""
Created on Wed Oct 16 08:42:50 2013
@author: Tobias Kienzler
"""
def squared_distance(p1, p2):
# TODO optimization: use numpy.ndarrays, simply return (p1-p2)**2
sd = 0
for x, y in zip(p1, p2):
sd += (x-y)**2
return sd
def get_proximity_matrix(points, threshold):
n = len(points)
t2 = threshold**2
# TODO optimization: use sparse boolean matrix
prox = [[False]*n for k in xrange(n)]
for i in xrange(0, n):
for j in xrange(i+1, n):
prox[i][j] = (squared_distance(points[i], points[j]) < t2)
prox[j][i] = prox[i][j] # symmetric matrix
return prox
def find_clusters(points, threshold):
n = len(points)
prox = get_proximity_matrix(points, threshold)
point_in_list = [None]*n
clusters = []
for i in xrange(0, n):
for j in xrange(i+1, n):
if prox[i][j]:
list1 = point_in_list[i]
list2 = point_in_list[j]
if list1 is not None:
if list2 is None:
list1.append(j)
point_in_list[j] = list1
elif list2 is not list1:
# merge the two lists if not identical
list1 += list2
point_in_list[j] = list1
del clusters[clusters.index(list2)]
else:
pass # both points are already in the same cluster
elif list2 is not None:
list2.append(i)
point_in_list[i] = list2
else:
list_new = [i, j]
for index in [i, j]:
point_in_list[index] = list_new
clusters.append(list_new)
if point_in_list[i] is None:
list_new = [i] # point is isolated so far
point_in_list[i] = list_new
clusters.append(list_new)
return clusters
def average_clusters(points, threshold=1.0, clusters=None):
if clusters is None:
clusters = find_clusters(points, threshold)
newpoints = []
for cluster in clusters:
n = len(cluster)
point = [0]*len(points[0]) # TODO numpy
for index in cluster:
part = points[index] # in numpy: just point += part / n
for j in xrange(0, len(part)):
point[j] += part[j] / n # TODO optimization: point/n later
newpoints.append(point)
return newpoints
points = [(-57.213878612138828, 17.916958304169601),
(76.392039480378514, 0.060882542482108504),
(0.12417670682730897, 1.0417670682730924),
(-64.840321976787706, 21.374279296143762),
(-48.966302937359913, 81.336323778066188),
(11.122014925372399, 85.001119402984656),
(8.6383049769438465, 84.874829066623917),
(-57.349835526315836, 16.683634868421084),
(83.051530302006697, 97.450469562867383),
(8.5405200433369473, 83.566955579631625),
(81.620435769843965, 48.106831247886376),
(78.713027357450656, 19.547209139192304),
(82.926153287322933, 81.026080639302577)]
threshold = 20.0
clusters = find_clusters(points, threshold)
clustered = average_clusters(points, clusters=clusters)
print "clusters:", clusters
print clustered
import matplotlib.pyplot as plt
ax = plt.figure().add_subplot(1, 1, 1)
for cluster in clustered:
ax.add_patch(plt.Circle(cluster, radius=threshold/2, color='g'))
for point in points:
ax.add_patch(plt.Circle(point, radius=threshold/2, edgecolor='k', facecolor='none'))
plt.plot(*zip(*points), marker='o', color='r', ls='')
plt.plot(*zip(*clustered), marker='.', color='g', ls='')
plt.axis('equal')
plt.show()
(より良い視覚化のために、円の半径はしきい値の半分です。つまり、円が互いに交差/接触するだけの場合、点は同じクラスター内にあります。)