我是 Python 的新手，我正在尝试开发一个代码，该代码应该基于一个名为 Pycluster 的预定义包执行 K-Means 聚类。一开始我一直在使用固定数量的集群（n = 10 个集群）进行集群，并且代码运行良好。我尝试稍微扩展代码，以便不再只制作 10 个集群，而是尝试制作一个循环，将所需的集群数量从 2 个增加到 10 个（或更多）。问题开始了，因为正如我所说，我对 Python 完全陌生。我开发的代码可以追溯如下。我意识到错误开始于代码行 33 到 49。我非常感谢为使代码运行而提供的任何帮助。
# -*- coding: utf-8 -*-
"""
Created on Mon Oct 21 13:53:40 2013
@author: Engin
"""
from Pycluster import *
import numpy as np
#Open the text file containing the stored smart meter data
d=np.loadtxt("120-RES-195-Normalized.txt", delimiter="\t", skiprows=1, usecols=range(1,49))
handle=open("120-RES-195-Normalized.txt")
record = read(handle) #Store the smart meter data in an array called record.
cluster_results = np.ones((120, 11))
cluster_centroids=np.array([])
within_cluster_sum_of_squares=np.ones((1,11))
between_cluster_sum_of_squares=np.ones((1,11))
distance=[]
for n in range (1,11):
cluster_results[:,n-1], within_cluster_sum_of_squares[:,n-1], optimal_solution_repetition = record.kcluster(nclusters=n, npass=10, method='a', dist='e') #Performs the K-Means clustering using the defined parameters
centroids, cmask = record.clustercentroids(cluster_results[:,n-1], method='a', transpose=0) #Calculates the cluster centroids
cluster_centroids=np.append(cluster_centroids,centroids)
#The following routine stores the cluster numbers and the indices of the elements belonging to each
#cluster so that the Between Clusters Sum of Squares would be easily calculated. The results will also
#be easily visualised.
from collections import defaultdict
cluster_numbers_members = defaultdict(list)
for i,item in enumerate(cluster_results[:,n-1]):
cluster_numbers_members[item].append(i)
cluster_numbers_members = {k:v for k,v in cluster_numbers_members.items() if len(v)>=1}
cluster_members=cluster_numbers_members.values()
cluster_numbers=cluster_numbers_members.keys()
distance[:,n-1]=0
between_cluster_sum_of_squares[:,n-1]=0
for i in range(0,n):
for k in range(0,n):
distance[:,n-1] = record.clusterdistance(index1=cluster_members[i], index2=cluster_members[k], method='a', dist='e', transpose=0)
between_cluster_sum_of_squares[:,n-1]=between_cluster_sum_of_squares[:,n-1]+distance[:,n-1]
WCBCR = within_cluster_sum_of_squares/between_cluster_sum_of_squares
print cluster_results[:,n-1]
print within_cluster_sum_of_squares[:,n-1]
print cluster_centroids
#Arranging cluster centroids in (1X48) vector form
cluster_tuple=zip(*[iter(cluster_centroids)]*48)
cluster_array=numpy.array(list(cluster_tuple))