def kmeans(d,points=3,axis=0,iter=20):
def init_centroids(dok_vecs):
centroids = []
# 1a. choose an initial center c_1 uniformly at random X
centroids.append(dok_vecs.values()[0])
# 1b. choose the next ceter c_i selecting c_i = x' in X w/probablity D(x')^2/\sum_{x in X} D(x)
# 1c. repeat step 1b until i == k
items = []
for i in range(1,points):
for w,v in dok_vecs.items():
temp = [ dok.squaredistance(v,c) for c in centroids ]
temp = [ x for x in temp if temp > 0 ]
items += [(w,min(temp))]
centroids.append(dok_vecs[dok.weighted_choice_bisect_compile(items)()])
return centroids
dok_vecs = d.tovecs(axis)
centroids = init_centroids(dok_vecs)
#centroidsを更新する。
for i in range(iter):
clusters = []
for i in range(points):
clusters += [[]]
for v in dok_vecs.values():
temp = [ (dok.squaredistance(v,centroids[i]),i) for i in range(points) ]
clusters[min(temp)[1]] += [v]
for i in range(points):
if len(clusters[i]) > 1:
centroids[i] = dok.mean(clusters[i])
else:
centroids[i] = centroids[i]
return centroids,clusters
def init_centroids(dok_vecs):
centroids = []
# 1a. choose an initial center c_1 uniformly at random X
centroids.append(dok_vecs.values()[0])
# 1b. choose the next ceter c_i selecting c_i = x' in X w/probablity D(x')^2/\sum_{x in X} D(x)
# 1c. repeat step 1b until i == k
items = []
for i in range(1,points):
for w,v in dok_vecs.items():
temp = [ dok.squaredistance(v,c) for c in centroids ]
temp = [ x for x in temp if temp > 0 ]
items += [(w,min(temp))]
centroids.append(dok_vecs[dok.weighted_choice_bisect_compile(items)()])
return centroids
