K-means bug fix

[wheniseeyou]

#@wheniseeyou K-means
from numpy import *



#step1 load DATASET
def loadDataSet(filename):
	'''

	输出的时候要转为mat
	:param filename:
	:return:
	'''
	dataMat =[]#数据矩阵
	fr = open(filename)
	for line in fr.readlines():
		#拆分
		curLine = line.strip().split('\t')
		fltLine = list(map(float,curLine))
		dataMat.append(fltLine)
	return dataMat

'''
[[1.658985, 4.285136], [-3.453687, 3.424321], [4.838138, -1.151539], [-5.37971
'''
#======test====
#x=loadDataSet('/Users/admin/Desktop/testSet_K.txt')
#step2 calc distance
def distEclud(vecA,vecB):
	return sqrt(sum(power(vecA-vecB,2)))

#初始化K点

def randCent(dataSet,k):
	'''
	这里假设dataSet是list 那么 下面的取最值就要改为下面的方法
	回顾下面的算法 发现：
	其随机zhixing的第二个特诊即y是从已知数据最小到最大的rand值 随机游走
	:param dataSet:
	:param k:
	:return:
	'''
	#取数据集的列
	n = shape(dataSet)[1]
	#创建矩阵块 以k为行数 n为列
	centroids = mat(zeros((k,n)))
	'''
	[[ 0.  0.  0.]
    [ 0.  0.  0.]
    [ 0.  0.  0.]
    [ 0.  0.  0.]]
	'''
	#创造随机质心
	for j in range(n):#对列遍历
		#找到最小的数据集的列的数
		#minJ = min(dataSet[:,j])
		minJ = min(array(dataSet)[:,j])
		rangeJ = float(max(array(dataSet)[:,j])-minJ)
		#rangeJ = float(max(dataSet[:,j])-minJ)#这里是找到每一列的特征的最大值 去减一个ZUIXIAO
		#生成随机质点
		'''
		np.random.rand(3,1)
		#=>
		[[ 0.70504333]
         [ 0.88452734]
         [ 0.31081878]]
		'''
		centroids[:,j] = mat(minJ + rangeJ*random.rand(k,1))#random.rand可以保证出现k个不一样的值
	return centroids

'''
K-均值聚类算法接收4个参数，
两个必要参数为数据集和k的值，
另外两个为距离计算函数和初始化函数（可修改）。
算法采用计算质心-分配-重新计算质心反复迭代的方式，
直到所有点的分配结果不再改变。
设置flag为clusterChange=True。
'''
#K-均值算法:
def KMeans(dataSet,k,distMeas = distEclud,createCent = randCent):
	'''

	:param dataSet: 数据集
	:param k: 你懂的
	:param distMeas:距离计算方式
	:param createCent: k点生成方式
	:return:
	'''
	#取数据集的行数
	m = shape(dataSet)[0]
	#簇群的0矩阵
	clusterAssment = mat(zeros((m,2)))
	'''
	[[ 0.  0.]
    [ 0.  0.]
    [ 0.  0.]
    [ 0.  0.]]
	'''
	#生成随机zhixing
	centroids = createCent(dataSet,k)
	#为了让最后的簇群保持不表
	clusterChanged = True
	while clusterChanged:
		clusterChanged = False
		#对于数据集的每一个点
		for i in range(m):
			minDist =inf#无穷
			minIndex = -1#初始化 类别
			for j in range(k):#对于每一个知心
				distJI = distMeas(centroids[j,:],dataSet[i,:])
				if distJI <minDist:#迭代距离
					minDist = distJI
					#更新最小距离是属于哪个类别的（类别与zhixn一模一样））
					minIndex = j
			#当数据集的簇群点的第一个数字 即类别 不属于j类 则继续迭代
			if clusterAssment[i,0] != minIndex:
				clusterChanged = True
			clusterAssment[i,:] = minIndex,minDist**2
		print(centroids)
		#更新k点
		for cent in range(k):
			'''
			nonzeros(a)返回数组a中值不为零的元素的下标，
			它的返回值是一个长度为a.ndim(数组a的轴数)的元组，
			元组的每个元素都是一个整数数组，其值为非零元素的下标在对应轴上的值。
			dataSet =[
			[1, 1],
			[1, 1],
			[1, 0],
			[0, 1],
			[0, 1]
			]
			print(np.nonzero(dataSet))
			#=>
			(array([0, 0, 1, 1, 2, 3, 4]), array([0, 1, 0, 1, 0, 1, 1]))
			上面是左右对应的 坐标的左边 与右边
			'''
			#找到dataset里面的 属于k类的全体点
			ptsInClust = dataSet[nonzero(clusterAssment[:,0].A == cent)[0]]
			#更新zhixin
			centroids[cent,:] = mean(ptsInClust,axis =0)
	return centroids,clusterAssment


dataMat = loadDataSet('/Users/admin/Desktop/testSet_K.txt')
print(mat(dataMat))

print(KMeans(mat(dataMat),2))

IN PY3.6 if use ur org-code it will run error! TO FIX IT the input must be change th type to MATRIX!!

[[ 1.658985  4.285136]
 [-3.453687  3.424321]
 [ 4.838138 -1.151539]
 [-5.379713 -3.362104]
 [ 0.972564  2.924086]
 [-3.567919  1.531611]
 [ 0.450614 -3.302219]
 [-3.487105 -1.724432]
 [ 2.668759  1.594842]
 [-3.156485  3.191137]
 [ 3.165506 -3.999838]
 [-2.786837 -3.099354]
 [ 4.208187  2.984927]
 [-2.123337  2.943366]
 [ 0.704199 -0.479481]
 [-0.39237  -3.963704]
 [ 2.831667  1.574018]
 [-0.790153  3.343144]
 [ 2.943496 -3.357075]
 [-3.195883 -2.283926]
 [ 2.336445  2.875106]
 [-1.786345  2.554248]
 [ 2.190101 -1.90602 ]
 [-3.403367 -2.778288]
 [ 1.778124  3.880832]
 [-1.688346  2.230267]
 [ 2.592976 -2.054368]
 [-4.007257 -3.207066]
 [ 2.257734  3.387564]
 [-2.679011  0.785119]
 [ 0.939512 -4.023563]
 [-3.674424 -2.261084]
 [ 2.046259  2.735279]
 [-3.18947   1.780269]
 [ 4.372646 -0.822248]
 [-2.579316 -3.497576]
 [ 1.889034  5.1904  ]
 [-0.798747  2.185588]
 [ 2.83652  -2.658556]
 [-3.837877 -3.253815]
 [ 2.096701  3.886007]
 [-2.709034  2.923887]
 [ 3.367037 -3.184789]
 [-2.121479 -4.232586]
 [ 2.329546  3.179764]
 [-3.284816  3.273099]
 [ 3.091414 -3.815232]
 [-3.762093 -2.432191]
 [ 3.542056  2.778832]
 [-1.736822  4.241041]
 [ 2.127073 -2.98368 ]
 [-4.323818 -3.938116]
 [ 3.792121  5.135768]
 [-4.786473  3.358547]
 [ 2.624081 -3.260715]
 [-4.009299 -2.978115]
 [ 2.493525  1.96371 ]
 [-2.513661  2.642162]
 [ 1.864375 -3.176309]
 [-3.171184 -3.572452]
 [ 2.89422   2.489128]
 [-2.562539  2.884438]
 [ 3.491078 -3.947487]
 [-2.565729 -2.012114]
 [ 3.332948  3.983102]
 [-1.616805  3.573188]
 [ 2.280615 -2.559444]
 [-2.651229 -3.103198]
 [ 2.321395  3.154987]
 [-1.685703  2.939697]
 [ 3.031012 -3.620252]
 [-4.599622 -2.185829]
 [ 4.196223  1.126677]
 [-2.133863  3.093686]
 [ 4.668892 -2.562705]
 [-2.793241 -2.149706]
 [ 2.884105  3.043438]
 [-2.967647  2.848696]
 [ 4.479332 -1.764772]
 [-4.905566 -2.91107 ]]
[[ 0.83986288 -1.83976116]
 [-4.0469936  -1.40467133]]
[[ 2.47925453  0.21182184]
 [-3.10532438 -0.12876332]]
[[ 2.71473038  0.18858278]
 [-2.9219568  -0.07998038]]
(matrix([[ 2.71473038,  0.18858278],
        [-2.9219568 , -0.07998038]]), matrix([[  0.        ,  17.89634662],
        [  1.        ,  12.56286513],
        [  0.        ,   6.30478631],
        [  1.        ,  16.81290103],
        [  0.        ,  10.51812157],
        [  1.        ,   3.01449392],
        [  0.        ,  17.31191999],
        [  1.        ,   3.02361363],
        [  0.        ,   1.97967838],
        [  1.        ,  10.75521236],
        [  0.        ,  17.74606725],
        [  1.        ,   9.13487445],
        [  0.        ,  10.04995372],
        [  1.        ,   9.77841689],
        [  0.        ,   4.48854562],
        [  1.        ,  21.48211857],
        [  0.        ,   1.93310494],
        [  1.        ,  16.26236793],
        [  0.        ,  12.62402277],
        [  1.        ,   4.93241188],
        [  0.        ,   7.36050686],
        [  1.        ,   8.22877329],
        [  0.        ,   4.66259677],
        [  1.        ,   7.51261982],
        [  0.        ,  14.50993584],
        [  1.        ,   6.85903854],
        [  0.        ,   5.04565231],
        [  1.        ,  10.95654103],
        [  0.        ,  10.44232656],
        [  1.        ,   0.80741959],
        [  0.        ,  20.89357231],
        [  1.        ,   5.32341991],
        [  0.        ,   6.93251564],
        [  1.        ,   3.53209105],
        [  0.        ,   3.77046308],
        [  1.        ,  11.79736257],
        [  0.        ,  25.69995006],
        [  1.        ,   9.64081992],
        [  0.        ,   8.12103192],
        [  1.        ,  10.91213604],
        [  0.        ,  14.05290621],
        [  1.        ,   9.06855533],
        [  0.        ,  11.80514107],
        [  1.        ,  17.88489819],
        [  0.        ,   9.09553212],
        [  1.        ,  11.37480809],
        [  0.        ,  16.17242331],
        [  1.        ,   6.23872366],
        [  0.        ,   7.39385874],
        [  1.        ,  20.07577022],
        [  0.        ,  10.4085923 ],
        [  1.        ,  16.85042532],
        [  0.        ,  25.63541221],
        [  1.        ,  15.29989117],
        [  0.        ,  11.90587245],
        [  1.        ,   9.58149736],
        [  0.        ,   3.20000848],
        [  1.        ,   7.57676457],
        [  0.        ,  12.04560092],
        [  1.        ,  12.25947225],
        [  0.        ,   5.32472486],
        [  1.        ,   8.91695746],
        [  0.        ,  17.70978882],
        [  1.        ,   3.86003859],
        [  0.        ,  14.78056918],
        [  1.        ,  15.0490604 ],
        [  0.        ,   7.74010731],
        [  1.        ,   9.21313835],
        [  0.        ,   8.95426674],
        [  1.        ,  10.64677491],
        [  0.        ,  14.60725641],
        [  1.        ,   7.24915895],
        [  0.        ,   3.07484117],
        [  1.        ,  10.6932501 ],
        [  0.        ,  11.38833208],
        [  1.        ,   4.30033192],
        [  0.        ,   8.17888612],
        [  1.        ,   8.5792329 ],
        [  0.        ,   6.92941377],
        [  1.        ,  11.94977392]]))

Process finished with exit code 0