k-modes算法mysql_第十一章 K-Means(K均值)算法模型实现（中）

python2 代码实现：

from numpy import *

import numpy

def loadDataSet(fileName): #general function to parse tab -delimited floats

dataMat = [] #assume last column is target value

fr = open(fileName)

for line in fr.readlines():

curLine = line.strip().split('\t')

fltLine = map(float,curLine) #map all elements to float()

dataMat.append(fltLine)

return dataMat

def distEclud(vecA, vecB):

return sqrt(sum(power(vecA - vecB, 2))) #la.norm(vecA-vecB)

def randCent(dataSet, k):

n = shape(dataSet)[1]

centroids = mat(zeros((k,n)))#create centroid mat

for j in range(n):#create random cluster centers, within bounds of each dimension

minJ = min(dataSet[:,j])

rangeJ = float(max(dataSet[:,j]) - minJ)

centroids[:,j] = mat(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):#recalcula