d = sqr_distance_2D(cc, point)
if min_dist > d:
min_dist = d
min_index = i
return (min_index, min_dist)
'''
points是数据点，nclusters是给定的簇类数目
cluster_centers包含初始化的nclusters个中心点，开始都是对象->(0,0,0)
'''
def kpp(points, cluster_centers):
cluster_centers[0] = copy(choice(points)) #随机选取第一个中心点
d = [0.0 for _ in xrange(len(points))] #列表，长度为len(points)，保存每个点离最近的中心点的距离
for i in xrange(1, len(cluster_centers)): # i=1...len(c_c)-1
sum = 0
for j, p in enumerate(points):
d[j] = nearest_cluster_center(p, cluster_centers[:i])[1] #第j个数据点p与各个中心点距离的最小值
sum += d[j]
sum *= random()
for j, di in enumerate(d):
sum -= di
if sum > 0:
continue
cluster_centers[i] = copy(points[j])
break
for p in points:
p.group = nearest_cluster_center(p, cluster_centers)[0]
'''
points是数据点，nclusters是给定的簇类数目
'''
def lloyd(points, nclusters):
cluster_centers = [Point() for _ in xrange(nclusters)] #根据指定的中心点个数，初始化中心点，均为(0,0,0)
# call k++ init
kpp(points, cluster_centers) #选择初始种子点
# 下面是kmeans
lenpts10 = len(points) >> 10
changed = 0
while True:
# group element for centroids are used as counters
for cc in cluster_centers:
cc.x = 0
cc.y = 0
cc.group = 0
for p in points:
