K-means均值聚類算法尋找質心，Python

import numpy as np

# 歐氏距離計算
def distEclud(x,y):
    return np.sqrt(np.sum((x-y)**2))  # 計算歐氏距離

# 爲給定數據集構建一個包含K個隨機質心的集合
def randCent(dataSet,k):
    m,n = dataSet.shape
    centroids = np.zeros((k,n))
    for i in range(k):
        index = int(np.random.uniform(0,m)) 
        centroids[i,:] = dataSet[index,:]
    return centroids
 
# k均值聚類
def kmeans_open(dataSet,k):
    m = np.shape(dataSet)[0]  #行的數目
    # 第一列存樣本屬於哪一簇
    # 第二列存樣本的到簇的中心點的誤差
    clusterAssment = np.mat(np.zeros((m,2)))
    clusterChange = True
 
    # 第1步 初始化centroids
    centroids = randCent(dataSet,k)
    while clusterChange:
        clusterChange = False
 
        # 遍歷所有的樣本（行數）
        for i in range(m):
            minDist = 100000.0
            minIndex = -1
 
            # 遍歷所有的質心
            #第2步 找出最近的質心
            for j in range(k):
                # 計算該樣本到質心的歐式距離
                distance = distEclud(centroids[j,:],dataSet[i,:])
                if distance < minDist:
                    minDist = distance
                    minIndex = j
            # 第 3 步：更新每一行樣本所屬的簇
            if clusterAssment[i,0] != minIndex:
                clusterChange = True
                clusterAssment[i,:] = minIndex,minDist**2
        #第 4 步：更新質心
        for j in range(k):
            pointsInCluster = dataSet[np.nonzero(clusterAssment[:,0].A == j)[0]]  # 獲取簇類所有的點
            centroids[j,:] = np.mean(pointsInCluster,axis=0)   # 對矩陣的行求均值
 
    return clusterAssment.A[:,0], centroids