kmeans python

前面写的JAVA版的KMEANS比较恶心，现在补上一个简单的python版本。

#kmeans

import math

def doKmeansCluster(data, cnum, itnum):

    c = data[:cnum]

    for time in range(itnum):

        groups = [[] for i in range(len(c))]

        for d in data:

            min = distance(d,c[0])

            index = 0

            for i in range(len(c)):

                dis = distance(d,c[i])

                index = [index,i][dis<min]

                min = [min,dis][dis<min]

            groups[index].append(d)

            

        c = []

        for g in groups:

            print g

            #transport the matrix, make all measure of the same demision in one same list

            trans = [[r[col] for r in g] for col in range(len(g[0]))]

            #get new center by sum and divide

            avg = [float(sum(trans[i]))/float(len(trans[0])) for i in range(len(trans))] 

            c.append(avg)









def distance(a, b):

    return math.sqrt(sum([math.pow(a[i]-b[i],2) for i in range(len(a))]))

只简单的测试了一下，没有考虑太多的约束，如果有心的话可以自己改写。