#coding=utf-8
from numpy import *
def loadDataSet(fileName):
 dataMat = []
 fr = open(fileName)
 for line in fr.readlines():
 curLine = line.strip().split('\t')
 fltLine = map(float, curLine)
 dataMat.append(fltLine)
 return dataMat
#計(jì)算兩個(gè)向量的距離，用的是歐幾里得距離
def distEclud(vecA, vecB):
 return sqrt(sum(power(vecA - vecB, 2)))
#隨機(jī)生成初始的質(zhì)心（ng的課說的初始方式是隨機(jī)選K個(gè)點(diǎn)） 
def randCent(dataSet, k):
 n = shape(dataSet)[1]
 centroids = mat(zeros((k,n)))
 for j in range(n):
 minJ = min(dataSet[:,j])
 rangeJ = float(max(array(dataSet)[:,j]) - minJ)
 centroids[:,j] = minJ + rangeJ * random.rand(k,1)
 return centroids
def kMeans(dataSet, k, distMeas=distEclud, createCent=randCent):
 m = shape(dataSet)[0]
 clusterAssment = mat(zeros((m,2)))#create mat to assign data points 
     #to a centroid, also holds SE of each point
 centroids = createCent(dataSet, k)
 clusterChanged = True
 while clusterChanged:
 clusterChanged = False
 for i in range(m):#for each data point assign it to the closest centroid
  minDist = inf
  minIndex = -1
  for j in range(k):
  distJI = distMeas(centroids[j,:],dataSet[i,:])
  if distJI < minDist:
   minDist = distJI; minIndex = j
  if clusterAssment[i,0] != minIndex: 
  clusterChanged = True
  clusterAssment[i,:] = minIndex,minDist**2
 print centroids
 for cent in range(k):#recalculate centroids
  ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]#get all the point in this cluster
  centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean 
 return centroids, clusterAssment
def show(dataSet, k, centroids, clusterAssment):
 from matplotlib import pyplot as plt 
 numSamples, dim = dataSet.shape 
 mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr', '<r', 'pr'] 
 for i in xrange(numSamples): 
 markIndex = int(clusterAssment[i, 0]) 
 plt.plot(dataSet[i, 0], dataSet[i, 1], mark[markIndex]) 
 mark = ['Dr', 'Db', 'Dg', 'Dk', '^b', '+b', 'sb', 'db', '<b', 'pb'] 
 for i in range(k): 
 plt.plot(centroids[i, 0], centroids[i, 1], mark[i], markersize = 12) 
 plt.show()
def main():
 dataMat = mat(loadDataSet('testSet.txt'))
 myCentroids, clustAssing= kMeans(dataMat,4)
 print myCentroids
 show(dataMat, 4, myCentroids, clustAssing) 
 
if __name__ == '__main__':
 main()