python ML 笔记：Kmeans

kmeans算法的python实现：

参考与样本来源《Machine Learning in Action》

#-*-coding:UTF-8-*-
'''
Created on 2015年8月19日
@author: Ayumi Phoenix
'''
import numpy as np

def distL2(a,b):
    """ 计算两个向量之间的L2距离 """
    return np.sqrt(np.sum((a-b)**2))

class Kmeans():
    def __init__(self, dataset,k):
        self.dataset = dataset
        self.k = k
        self.m, self.n = dataset.shape
        
    def randcent(self):
        """ 根据输入数据集获得随机生成一组簇质心 """
        maxn = np.max(self.dataset, 0)  # 获取每一维的最大值
        minn = np.min(self.dataset, 0)  # 获取每一维的最小值
        centoroid = np.random.rand(self.k,self.n) * (maxn - minn) + minn    # k x n
        return centoroid

    def train(self, dist, iter = 1):
        """
        # 1. 计算每个样本与所有簇心的最近匹配距离数组 m x 1：
            # 计算某样本与所有簇心的距离,
            # 找到最小距离所属的下标序号 0...k-1
        # 2. 根据当前类标的分配，重新计算平均聚类中心
            # 按照当前分配索引样本数据
            # 迭代次数减一
        # 3. 返回最终的质心与分配的序号
        """
        centoroid = self.randcent()
        while iter:
            labels = np.zeros((self.m,), int)               
            for i in range(self.m):
                d = [dist(self.dataset[i,:],centoroid[j])   
                     for j in range(self.k)]   
                labels[i] = np.argmin(d)                    
            for i in range(self.k):                         
                x = self.dataset[labels==i]                 
                centoroid[i] = np.mean(x, 0)
            iter -= 1                                       
        return centoroid, labels    

读取数据与测试函数：

ef loadDataSet(filename):
    dataMat = []
    with open(filename) as f:
        for line in f.readlines():
            curline = line.strip().split('	')
            fltline = map(np.float, curline)
            dataMat.append(fltline)
    return dataMat


if __name__=="__main__":
    pass
    datMat = np.array(loadDataSet('testSet.txt'))
    km = Kmeans(datMat,4)
    centoroid, labels = km.train(distL2, iter=20)
    
    # 根据当前质心显示样本分布
    import matplotlib.pylab as pl
    pl.figure()
    c = ['ro','go','bo','yo','co','ko','wo','mo']
    for i in range(datMat.shape[0]):
        pl.plot(datMat[i][0],datMat[i][1],c[labels[i]])
    for cen in centoroid:
        pl.plot(cen[0],cen[1],'mo')
    pl.show()

结果：