import numpy as np
#导入数据集
def loadDataSet(fileName):
dataMat=[]
fr=open(fileName)
for line in fr.readlines():
curLine = line.strip().split('\t')
fltLine = list(map(float,curLine))
dataMat.append(fltLine)
return dataMat
#欧氏距离
def distEclud(vecA,vecB):
return np.sqrt(np.sum(np.power(vecA-vecB,2)))
#随机生成中心点
def randCent(dataSet,k):
n=np.shape(dataSet)[1]
centroids=np.mat(np.zeros((k,n)))
for j in range(n):
minJ=np.min(dataSet[:,j])
maxJ=np.max(dataSet[:,j])
rangeJ=float(maxJ-minJ)
centroids[:,j]=minJ+rangeJ*np.random.rand(k,1)
return centroids
#聚类和中心点矩阵
def kMeans(dataSet,k,distMeas=distEclud,createCent=randCent):
m=np.shape(dataSet)[0]
clusterAssment=np.mat(np.zeros((m,2)))
centroids=createCent(dataSet,k)
clusterChanged=True
while clusterChanged:
clusterChanged=False
for i in range(m):
minDist=float('inf')
minIndex=-1
for j in range(k):
distJI=distMeas(centroids[j,:],dataSet[j,:])
if distJI<minDist:
minDist=distJI
minIndex=j
if clusterAssment[i,0]!=minIndex:
clusterChanged=True
clusterAssment[i,:]=minIndex,minDist**2
for cent in range(k):
ptsInClust=dataSet[np.nonzero(clusterAssment[:,0].A==cent)[0]]
centroids[cent,:]=np.mean(ptsInClust,axis=0)
return centroids,clusterAssment
datMat=loadDataSet('D:/python/files/新建文件夹/test.txt')
myCentroids,clustAssing=kMeans(datMat,4)
print(myCentroids)
print(clustAssing)
报错如下
runfile('D:/python/files/新建文件夹/未命名3.py')
Traceback (most recent call last):
File "D:\python\files\新建文件夹\未命名3.py", line 56, in
myCentroids,clustAssing=kMeans(datMat,4)
File "D:\python\files\新建文件夹\未命名3.py", line 36, in kMeans
centroids=createCent(dataSet,k)
File "D:\python\files\新建文件夹\未命名3.py", line 27, in randCent
minJ=np.min(dataSet[:,j])
TypeError: list indices must be integers or slices, not tuple