引言
K-均值算法试图将一系列样本分割成K个不同的类簇(其中K是模型的输入参数),其形式化的目标函数称为类簇内的方差和(within cluster sum of squared errors,WCSS)。K-均值聚类的目的是最小化所有类簇中的方差之和。标准的K-均值算法初始化K个类中心(为每个类簇中所有样本的平均向量)
原理
k-均值聚类算法
创建
K
K
个点作为起始质点(经常是随机选择)
进行迭代
将每个数据点分配到离他距离最近的质点的簇。
全部分配后,用各个簇中的数据点的位置均值来更新质点的位置
直到达到迭代次数,或者所有的数据点所在的簇不发生改变
这意味着需要某种距离运算。数据集上k-均值算法的性能会受到所选距离计算方法的影响。我们可列出k-均值聚类支持函数:
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
第一个函数的功能是进行数据导入,第二个函数的功能是计算两个向量的欧氏距离,最后一个函数是为给定数据集构建一个包含个随机之心的集合。
然后便是k-均值聚类算法:
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
实例分析
可以对它进行一些测试,测试集采用如下测试集
一个书中自带的测试集
输入如下命令:
datMat=mat(loadDataSet('testSet.txt'))
myCentroids,clustAssing=kMeans(datMat,4)
得到如下结果,进行了四次迭代后算法收敛
二分k-均值算法
将所有点看成一个簇
当簇数目小于k时
对于每一个簇:
计算总误差
在给定的簇上面进行K-均值聚类
(k=2)
(
k
=
2
)
计算将该簇一分为二后的总误差
选择使得误差最小的那个簇进行划分操作
代码如下
def biKmeans(dataSet, k, distMeas=distEclud):
m = shape(dataSet)[0]
clusterAssment = mat(zeros((m,2)))
centroid0 = mean(dataSet, axis=0).tolist()[0]
centList =[centroid0] #create a list with one centroid
for j in range(m):#calc initial Error
clusterAssment[j,1] = distMeas(mat(centroid0), dataSet[j,:])**2
while (len(centList) < k):
lowestSSE = inf
for i in range(len(centList)):
ptsInCurrCluster = dataSet[nonzero(clusterAssment[:,0].A==i)[0],:]#get the data points currently in cluster i
centroidMat, splitClustAss = kMeans(ptsInCurrCluster, 2, distMeas)
sseSplit = sum(splitClustAss[:,1])#compare the SSE to the currrent minimum
sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:,0].A!=i)[0],1])
print ("sseSplit, and notSplit: ",sseSplit,sseNotSplit)
if (sseSplit + sseNotSplit) < lowestSSE:
bestCentToSplit = i
bestNewCents = centroidMat
bestClustAss = splitClustAss.copy()
lowestSSE = sseSplit + sseNotSplit
bestClustAss[nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList) #change 1 to 3,4, or whatever
bestClustAss[nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit
print ('the bestCentToSplit is: ',bestCentToSplit)
print ('the len of bestClustAss is: ', len(bestClustAss))
centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]#replace a centroid with two best centroids
centList.append(bestNewCents[1,:].tolist()[0])
clusterAssment[nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:]= bestClustAss#reassign new clusters, and SSE
return mat(centList), clusterAssment
实例分析
在上述测试集中进行测试
输入
datMat=mat(loadDataSet('testSet.txt'))
CentList,MyNewAssments=biKmeans(datMat,4)
print(CentList)
得到聚类结果
也可用一个较难的数据集
一个书中自带的测试集
输入
datMat=mat(loadDataSet('testSet2.txt'))
CentList,MyNewAssments=biKmeans(datMat,3)
print(CentList)
得到聚类结果
实例
运用经典的iris数据集进行分类
使用经典的k-均值算法进行分类
datMat=mat(loadDataSet('iris.txt'))
CentList,MyNewAssments=kMeans(datMat,3)
可得到迭代结果
经过10次迭代,算法收敛最后的聚类中心
以及最后的聚类集
部分聚类集
代码
from numpy import *
import matplotlib.pyplot as plt
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 = list(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):#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 biKmeans(dataSet, k, distMeas=distEclud):
m = shape(dataSet)[0]
clusterAssment = mat(zeros((m,2)))
centroid0 = mean(dataSet, axis=0).tolist()[0]
centList =[centroid0] #create a list with one centroid
for j in range(m):#calc initial Error
clusterAssment[j,1] = distMeas(mat(centroid0), dataSet[j,:])**2
while (len(centList) < k):
lowestSSE = inf
for i in range(len(centList)):
ptsInCurrCluster = dataSet[nonzero(clusterAssment[:,0].A==i)[0],:]#get the data points currently in cluster i
centroidMat, splitClustAss = kMeans(ptsInCurrCluster, 2, distMeas)
sseSplit = sum(splitClustAss[:,1])#compare the SSE to the currrent minimum
sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:,0].A!=i)[0],1])
print ("sseSplit, and notSplit: ",sseSplit,sseNotSplit)
if (sseSplit + sseNotSplit) < lowestSSE:
bestCentToSplit = i
bestNewCents = centroidMat
bestClustAss = splitClustAss.copy()
lowestSSE = sseSplit + sseNotSplit
bestClustAss[nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList) #change 1 to 3,4, or whatever
bestClustAss[nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit
print ('the bestCentToSplit is: ',bestCentToSplit)
print ('the len of bestClustAss is: ', len(bestClustAss))
centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]#replace a centroid with two best centroids
centList.append(bestNewCents[1,:].tolist()[0])
clusterAssment[nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:]= bestClustAss#reassign new clusters, and SSE
return mat(centList), clusterAssment
参考文献
《机器学习实战》