机器学习之k-均值算法的python的实现

# -*-coding:utf-8-*-
#将进行数据加载
from numpy import *
from scipy.cluster.vq import kmeans


def loadDataSet(fileName):
    fr=open(fileName)
    dataWord=[]
    for line in fr.readlines():
        curLine=line.strip().split("\t")
        fitLine=map(float,curLine)#转化为小数
        dataWord.append(fitLine)#添加到list中
    # print dataWord
    return dataWord #他是一个集合中的map[[,],[,],[,]............]

# 计算欧几里得距离
def distEclud(vecA, vecB):
    return sqrt(sum(power(vecA - vecB, 2)))

#构建类簇的中心，随机取4个作为随机质心
def randCent(dataSet ,k):
    n=shape(dataSet)[1]#q取矩阵行数
    centroids=mat(zeros(k.n))#创建一个k行n列的矩阵。k个质心，每个质心n个坐标值

    #随机构建n个质心坐标
    for j in range(n):
        minJ=min(dataSet[:,j])#计算第j列的最小值
        maxJ=max(dataSet[:,j])#计算第j列的最大值
        rangeJ=float(maxJ-minJ)
        centroids[:, j] = minJ + rangeJ * random.rand(k, 1)#将第j列的值赋值为它
        return centroids

#k-means 聚类算法
def KMeans(dataSet,k,distMeans=distEclud,createCent=randCent):
    m = shape(dataSet)[0]#读取这个矩阵共有多少行
    clusterAssment = mat(zeros((m, 2)))  # 用于存放该样本属于哪类及质心距离
    centroids = createCent(dataSet, k)
    clusterChanged = True
    while clusterChanged:
        clusterChanged = False;
        for i in range(m):
            minDist = inf;
            minIndex = -1;
            for j in range(k):
                distJI = distMeans(centroids[j, :], dataSet[i, :])#计算质点到数据集点的距离
                if distJI < minDist:
                    minDist = distJI;#将这个值限定为一个区域的划分值
                    minIndex = j#作为一个分类的标志，这是第j类
            if clusterAssment[i, 0] != minIndex: clusterChanged = True;#如果当前的质点不位于这个分类的话，将前面设置的标志位true
            clusterAssment[i, :] = minIndex, minDist ** 2#暂时将它归为上一个数据的类，将离质点的距离设为上一个距离的平方，然后不断的迭代计算
        print centroids
        for cent in range(k):
            ptsInClust = dataSet[nonzero(clusterAssment[:, 0].A == cent)[0]]  # 去第一列等于cent的所有列
            centroids[cent, :] = mean(ptsInClust, axis=0)
    return centroids, clusterAssment

print "step 1: load data..."
dataSet = []
dataSet = loadDataSet('D:/testSet.txt')



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

print "step 3: show the result..."
KMeans(dataSet, 4, centroids, clusterAssment)

python的机器学习的资源