kMeans.py
from numpy import *
def loadDataSet(fileName):
dataSet = []
fr = open(fileName)
for line in fr.readlines():
curLine = line.strip().split('\t')
fltLine = list(map(float, curLine))
dataSet.append(fltLine)
return dataSet
def distEclud(vecA, vecB):
return sqrt(sum(power(vecA - vecB, 2)))
def randCent(dataMat, k):
n = shape(dataMat)[1]
centroids = mat(zeros((k, n)))
for j in range(n):
minJ = min(dataMat[:, j])
rangeJ = float(max(dataMat[:, j]) - minJ)
centroids[:, j] = mat(minJ + rangeJ * random.rand(k, 1))
return centroids
def kMeans(dataMat, k, distMeas=distEclud, createCent=randCent):
m = shape(dataMat)[0]
clusterAssment = mat(zeros(
(m, 2)))
centroids = createCent(dataMat, k)
clusterChanged = True
while clusterChanged:
clusterChanged = False
for i in range(m):
minDist = inf
minIndex = -1
for j in range(k):
distJI = distMeas(centroids[j, :],
dataMat[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):
ptsInClust = dataMat[nonzero(
clusterAssment[:, 0].A == cent)[0]]
centroids[cent, :] = mean(
ptsInClust, axis=0)
return centroids, clusterAssment
def biKMeans(dataMat, k, distMeas=distEclud):
m = shape(dataMat)[0]
clusterAssment = mat(zeros((m, 2)))
centroid0 = mean(dataMat, axis=0).tolist()[0]
centList = [centroid0]
for j in range(m):
clusterAssment[j, 1] = distMeas(mat(centroid0), dataMat[j, :])**2
while len(centList) < k:
lowestSSE = inf
for i in range(len(centList)):
ptsInCurrCluster = dataMat[nonzero(
clusterAssment[:, 0].A == i)[0], :]
centroidMat, splitClustAss = kMeans(
ptsInCurrCluster, 2, distMeas)
sseSplit = sum(splitClustAss[:, 1])
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)
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]
centList.append(
bestNewCents[1, :].tolist()[0])
clusterAssment[nonzero(clusterAssment[:, 0].A == bestCentToSplit)[
0], :] = bestClustAss
return mat(centList), clusterAssment
def testBasicFunc():
dataMat = mat(loadDataSet('data/testSet.txt'))
print('min(dataMat[:, 0])=', min(dataMat[:, 0]))
print('min(dataMat[:, 1])=', min(dataMat[:, 1]))
print('max(dataMat[:, 1])=', max(dataMat[:, 1]))
print('max(dataMat[:, 0])=', max(dataMat[:, 0]))
print('randCent(dataMat, 2)=', randCent(dataMat, 2))
print(' distEclud(dataMat[0], dataMat[1])=', distEclud(dataMat[0], dataMat[1]))
def testKMeans():
dataMat = mat(loadDataSet('data/testSet.txt'))
myCentroids, clustAssing = kMeans(dataMat, 4)
print('centroids=', myCentroids)
def testBiKMeans():
dataMat = mat(loadDataSet('data/testSet2.txt'))
centList, myNewAssments = biKMeans(dataMat, 3)
print('centList=', centList)
if __name__ == "__main__":
testBiKMeans()