python实现kMeans算法的详解

聚类是一种无监督的学习，将相似的对象放到同一簇中，有点像是全自动分类，簇内的对象越相似，簇间的对象差别越大，则聚类效果越好。本文主要为大家详细介绍了python实现kMeans算法，具有一定的参考价值，感兴趣的小伙伴们可以参考一下，希望能帮助到大家。

import numpy as np
import matplotlib.pyplot as plt

def loadDataSet(fileName): 
 dataMat = [] 
 with open(fileName) as f:
  for line in f.readlines():
   line = line.strip().split('\t')
   dataMat.append(line)
 dataMat = np.array(dataMat).astype(np.float32)
 return dataMat


def distEclud(vecA,vecB):
 return np.sqrt(np.sum(np.power((vecA-vecB),2)))
def randCent(dataSet,k):
 m = np.shape(dataSet)[1]
 center = np.mat(np.ones((k,m)))
 for i in range(m):
  centmin = min(dataSet[:,i])
  centmax = max(dataSet[:,i])
  center[:,i] = centmin + (centmax - centmin) * np.random.rand(k,1)
 return center
def kMeans(dataSet,k,distMeans = 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 = np.inf
   minIndex = -1
   for j in range(k):
    distJI = distMeans(dataSet[i,:],centroids[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



data = loadDataSet('testSet.txt')
muCentroids, clusterAssing = kMeans(data,4)
fig = plt.figure(0)
ax = fig.add_subplot(111)
ax.scatter(data[:,0],data[:,1],c = clusterAssing[:,0].A)
plt.show()

print(clusterAssing)

import numpy as np
import matplotlib.pyplot as plt

def loadDataSet(fileName): 
 dataMat = [] 
 with open(fileName) as f:
  for line in f.readlines():
   line = line.strip().split('\t')
   dataMat.append(line)
 dataMat = np.array(dataMat).astype(np.float32)
 return dataMat


def distEclud(vecA,vecB):
 return np.sqrt(np.sum(np.power((vecA-vecB),2)))
def randCent(dataSet,k):
 m = np.shape(dataSet)[1]
 center = np.mat(np.ones((k,m)))
 for i in range(m):
  centmin = min(dataSet[:,i])
  centmax = max(dataSet[:,i])
  center[:,i] = centmin + (centmax - centmin) * np.random.rand(k,1)
 return center
def kMeans(dataSet,k,distMeans = 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 = np.inf
   minIndex = -1
   for j in range(k):
    distJI = distMeans(dataSet[i,:],centroids[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

def biKmeans(dataSet,k,distMeans = distEclud):
 m = np.shape(dataSet)[0]
 clusterAssment = np.mat(np.zeros((m,2)))
 centroid0 = np.mean(dataSet,axis=0).tolist()
 centList = [centroid0]
 for j in range(m):
  clusterAssment[j,1] = distMeans(dataSet[j,:],np.mat(centroid0))**2
 while (len(centList)<k):
  lowestSSE = np.inf
  for i in range(len(centList)):
   ptsInCurrCluster = dataSet[np.nonzero(clusterAssment[:,0].A == i)[0],:]
   centroidMat,splitClustAss = kMeans(ptsInCurrCluster,2,distMeans)
   sseSplit = np.sum(splitClustAss[:,1])
   sseNotSplit = np.sum(clusterAssment[np.nonzero(clusterAssment[:,0].A != i)[0],1])
   if (sseSplit + sseNotSplit) < lowestSSE:
    bestCentToSplit = i
    bestNewCents = centroidMat.copy()
    bestClustAss = splitClustAss.copy()
    lowestSSE = sseSplit + sseNotSplit
  print('the best cent to split is ',bestCentToSplit)
#  print('the len of the bestClust')
  bestClustAss[np.nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList)
  bestClustAss[np.nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit

  clusterAssment[np.nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:] = bestClustAss.copy()
  centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]
  centList.append(bestNewCents[1,:].tolist()[0])
 return np.mat(centList),clusterAssment

data = loadDataSet('testSet2.txt')
muCentroids, clusterAssing = biKmeans(data,3)
fig = plt.figure(0)
ax = fig.add_subplot(111)
ax.scatter(data[:,0],data[:,1],c = clusterAssing[:,0].A,cmap=plt.cm.Paired)
ax.scatter(muCentroids[:,0],muCentroids[:,1])
plt.show()

print(clusterAssing)
print(muCentroids)

代码及数据集下载：K-means