K-mean聚类的一个代码的详细注释

#
#  coding:utf-8
from numpy import *
import time
import matplotlib.pyplot as plt

# calculate Euclidean distance
def euclDistance(vector1, vector2):
    return sqrt(sum(power(vector1 - vector2, 2)))
    # 0ρ = sqrt( (x1-x2)^2+(y1-y2)^2 )　|x| = √( x2 + y2 )
    # power 对列表计算2次方  求和后开方

# init centroids with random samples 初始化质心随机样本
def initCentroids(dataSet, k):
    numSamples, dim = dataSet.shape
    #numSamples为dataSet的行数 dim为dataSet的列数
    centroids = zeros((k, dim))
    #centroids为k行dim列的零矩阵
    for i in range(k):
        index = int(random.uniform(0, numSamples))
        # uniform(x,y) 方法将随机生成下一个实数，它在[x,y]范围内。
        centroids[i, :] = dataSet[index, :]
    return centroids

# k-means cluser
def kmeans(dataSet, l):
    numSamples = dataSet.shape[0]
    # first colum stores which cluster this sample belongs to,
    # second colum stores the error between this sample and its centroid
    clusterAssment = mat(zeros((numSamples, 2)))
    '''
    zeros((numSamples, 2))生成数组
    mat(zeros((numSamples, 2)))将生成的数组转换为矩阵
    '''
    clusterChanged = True

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

    while clusterChanged:
        clusterChanged = False
        ## for each sample
        for i in xrange(numSamples):
            #range()直接生成一个list对象，
            #xrange()生成一个生成器，由于每次调用只返回一个值
            #xrang()的执行效率要高于range()
            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]]
            #numpy.nonzero(a)[source]
            #Return the indices of the elements that are non-zero.
            #官网文档：http://docs.scipy.org/doc/numpy/reference/generated/numpy.nonzero.html
            centroids[j, :] = mean(pointsInCluster, axis = 0)

    print 'Congratulatons, 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', ', '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', ', 'pb']
    # draw the centroids
    for i in range(k):
        plt.plot(centroids[i, 0], centroids[i, 1], mark[i], markersize = 12)
        plt.show()
    #plt.savefig('foo1.png')

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

## step 1: load data
print "step 1: load data..."
dataSet = []
fileIn = open('/home/amos/machine_learning')
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)

#"setp 2:"可以通过直接调用官方库sklearn.cluster中的KMeans实现聚类
print "step 2: clustering..."
dataSet = mat(dataSet)
k = 4

############################################################
#by importing KMeans from sklearn.cluster
#call KMeans and get the same result as kmeans.py
kmeans = KMeans(n_clusters=k, random_state=0).fit(dataSet)
centroids = kmeans.cluster_centers_
clusterAssment = kmeans.labels_
############################################################

#"step 3:"中需要将showCluster(dataSet, k, centroids, clusterAssment)中的
# draw all samples部分的markIndex = int(clusterAssment[i, 0])
#改为markIndex = int(clusterAssment[i])