Kmeans算法

#################################################
# kmeans: k-means cluster
# Author : zouxy
# Date   : 2013-12-25
# HomePage : http://blog.csdn.net/zouxy09
# Email  : zouxy09@qq.com
#################################################

from numpy import *
import time
import matplotlib.pyplot as plt


# calculate Euclidean distance
def euclDistance(vector1, vector2):
    return sqrt(sum(power(vector2 - vector1, 2)))

# init centroids with random samples
def initCentroids(dataSet, k):
    numSamples, dim = dataSet.shape
    centroids = zeros((k, dim))
    for i in range(k):
        index = int(random.uniform(0, numSamples))
        centroids[i, :] = dataSet[index, :]
    return centroids

# k-means cluster
def kmeans(dataSet, k):
    numSamples = dataSet.shape[0]
    # first column stores which cluster this sample belongs to,
    # second column stores the error between this sample and its centroid
    clusterAssment = mat(zeros((numSamples, 2)))
    clusterChanged = True

    ## step 1: init centroids
    centroids = initCentroids(dataSet, k)

    while clusterChanged:
        clusterChanged = False
        ## for each sample
        for i in xrange(numSamples):
            minDist  = 100000.0
            minIndex = 0
            ## for each centroid
            ## step 2: find the centroid who is closest
            for j in range(k):
                distance = euclDistance(centroids[j, :], dataSet[i, :])
                if distance < minDist:
                    minDist  = distance
                    minIndex = j
            
            ## step 3: update its cluster
            if clusterAssment[i, 0] != minIndex:
                clusterChanged = True
                clusterAssment[i, :] = minIndex, minDist**2

        ## step 4: update centroids
        for j in range(k):
            pointsInCluster = dataSet[nonzero(clusterAssment[:, 0].A == j)[0]]
            centroids[j, :] = mean(pointsInCluster, axis = 0)

    print 'Congratulations, cluster complete!'
    return centroids, clusterAssment

# show your cluster only available with 2-D data
def showCluster(dataSet, k, centroids, clusterAssment):
    numSamples, dim = dataSet.shape
    if dim != 2:
        print "Sorry! I can not draw because the dimension of your data is not 2!"
        return 1

    mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr', '<r', 'pr']
    if k > len(mark):
        print "Sorry! Your k is too large! please contact Zouxy"
        return 1

    # draw all samples
    for i in xrange(numSamples):
        markIndex = int(clusterAssment[i, 0])
        plt.plot(dataSet[i, 0], dataSet[i, 1], mark[markIndex])

    mark = ['Dr', 'Db', 'Dg', 'Dk', '^b', '+b', 'sb', 'db', '<b', 'pb']
    # draw the centroids
    for i in range(k):
        plt.plot(centroids[i, 0], centroids[i, 1], mark[i], markersize = 12)

    plt.show()

数据集

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
-0.392370   -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    -1.906020
-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
-3.189470   1.780269
4.372646    -0.822248
-2.579316   -3.497576
1.889034    5.190400
-0.798747   2.185588
2.836520    -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    -2.983680
-4.323818   -3.938116
3.792121    5.135768
-4.786473   3.358547
2.624081    -3.260715
-4.009299   -2.978115
2.493525    1.963710
-2.513661   2.642162
1.864375    -3.176309
-3.171184   -3.572452
2.894220    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   -2.911070

测试

#################################################
# kmeans: k-means cluster
# Author : zouxy
# Date   : 2013-12-25
# HomePage : http://blog.csdn.net/zouxy09
# Email  : zouxy09@qq.com
#################################################

from numpy import *
import time
import matplotlib.pyplot as plt

## step 1: load data
print "step 1: load data..."
dataSet = []
fileIn = open('E:/Python/Machine Learning in Action/testSet.txt')
for line in fileIn.readlines():
    lineArr = line.strip().split('\t')
    dataSet.append([float(lineArr[0]), float(lineArr[1])])

## step 2: clustering...
print "step 2: clustering..."
dataSet = mat(dataSet)
k = 4
centroids, clusterAssment = kmeans(dataSet, k)

## step 3: show the result
print "step 3: show the result..."
showCluster(dataSet, k, centroids, clusterAssment)