《集体智慧编程》—K均值聚类

源码：
注：
import clusters 来源于另外一篇博客
参考链接这里写链接内容
data数据集由generatefeedvector.py生成
参考链接这里写链接内容

# --coding:utf-8--
import random
import clusters

def kcluster(rows,distance =clusters.pearson,k=4):
    #q确定每个点的最大值和最小值
    ranges = [(min(row[i] for row in rows),max(row[i] for row in rows))for i in range(len(rows[0]))]
    #随机产生k个中心点
    kclusters = [[random.random() * (ranges[i][1] - ranges[i][0]) + ranges[i][0] for i in range(len(rows[0]))] for j in range(k)]

    lastmatches=None
    for t in range(100):
        print "Iteration %d" %t
        bestmatches=[[] for i in range(k)]

        #在每行中寻找距离最近的中心点
        for j in range(len(rows)):
            row=rows[j]
            bestmatch = 0
            for i in range(k):
                d = distance(kclusters[i],row)
                if d < distance(kclusters[bestmatch],row):
                    bestmatch = i
            bestmatches[bestmatch].append(j)
        #如果结果与上次相同，则结束迭代
        if bestmatches == lastmatches:
            break
        lastmatches = bestmatches

        #把中心点移到中心位置
        for i in range(k):
            avgs = [0.0] * len(rows[0])
            if len(bestmatches[i]) > 0:
                for rowid in bestmatches[i]:
                    for m in range(len(rows[rowid])):
                        avgs[m] += rows[rowid][m]
                for j in range(len(avgs)):
                    avgs[j] / len(bestmatches[i])
                kclusters[i] = avgs
    return bestmatches

blognames,words,data = clusters.readfile(r"D:\subject\PycharmProjects\blogdata")
k = kcluster(data)
print k
print len(k)
for row in k:
    for id in row:
        print blognames[id]
    print "**********"

数据集：

实验结果：
k=4时

k=8时

参数可以自己设定