kmeans代码分析

kmeans: 

缺点： 对初始值的选取敏感, 使用bikmean可以解决。

完整代码参考博客：http://blog.csdn.net/zouxy09/article/details/17590137

kmeans算法分析：

1、初始化聚类中心

def initCentroids(dataSet, k):
    numSamples, dim = dataSet.shape
    centroids = zeros((k, dim))
    for i in range(k):
        index = int(random.uniform(0, numSamples))
        centroids[i, :] = dataSet[index, :]
    return centroids

循环：

如果未迭代：即clusterChanged = True

1、计算各点到聚类中心的距离， 选择最近的距离， 更新clusterAssent：第一列存放该样本所在簇的类标，第二列存储该样本到对应簇中心的距离。判断是否迭代，更新 clusterChanged 。

while clusterChanged:
    clusterChanged = False
    ## for each sample
    for i in range(numSamples):
        minDist = 100000.0
        minIndex = 0
        ## for each centroid
        ## step 2: find the centroid who is closest
        for j in range(k):
            distance = euclDistance(centroids[j, :], dataSet[i, :])
            if distance < minDist:
                minDist = distance
                minIndex = j  #距离最小的聚类中心类标

                ## step 3: update its cluster
        if clusterAssment[i, 0] != minIndex:
            clusterChanged = True
            clusterAssment[i, :] = minIndex, minDist ** 2

2、更新聚类中心

for j in range(k):
    pointsInCluster = dataSet[nonzero(clusterAssment[:, 0].A == j)[0]]
    centroids[j, :] = mean(pointsInCluster, axis=0)