Python-kmeans算法实践

import numpy as np

#调用一些下面写的子函数模拟实现kmeans的功能
def kmeans(x, k, maxIt):
        numPoints, numDim = x.shape

        dataSet = np.zeros((numPoints, numDim + 1))
        dataSet[:, :-1] = x

        #centroids = dataSet[np.random.randint(numPoints, size = k), :]
        #对于中心点的选择应是以随机的方式，这里选择和上篇例子中同样的中心点为了验证结果。
        centroids = dataSet[0:2, :]

        centroids[:, -1] = range(1, k+1)

        iterations = 0
        oldCentroids = None

        while not shouldStop(oldCentroids, centroids, iterations, maxIt):
            print "iteration； \n", iterations
            print "dataSet: \n", dataSet
            print "centroids: \n", centroids

            oldCentroids = np.copy(centroids)
            iterations += 1

            updataLabels(dataSet, centroids)

            centroids = getCentroids(dataSet, k)

        return dataSet

#对迭代停止时间的判断函数       
def shouldStop(oldCentroids, centroids, iterations, maxIt):
    if iterations > maxIt:
        return True
    return np.array_equal(oldCentroids, centroids)

 #根据中心点修改类别标签   
def updataLabels(dataSet, centroids):
    numPoints, numDim = dataSet.shape
    for i in range(0, numPoints):
        dataSet[i,1] = getLabelFromClosestCentroid(dataSet[i,:1], centroids)

#计算得出最近的中心点将标签返回的函数       
def getLabelFromClosestCentroid(dataSetRow, centroids):
    label = centroids[0, -1];
    minDist = np.linalg.norm(dataSetRow - centroids[0, :-1])
    for i in range(1, centroids.shape[0]):
        dist = np.linalg.norm(dataSetRow - centroids[i, :-1])
        if dist < minDist:
            minDist = dist
            label = centroids[i, -1]
    print "minDist： ", minDist
    return label

 #根据均值更新中心点   
def getCentroids(dataSet, k):
    result = np.zeros((k, dataSet.shape[1]))
    for i in range(1, k+1):
        oneCluster = dataSet[dataSet[:, -1] == i, :-1]
        result[i-1, :-1] = np.mean(oneCluster, axis = 0)
        result[i-1, -1] = i
    return result

#下面是一个例子        
x1 = np.array([1,1])
x2 = np.array([2,1])
x3 = np.array([4,3])
x4 = np.array([5,4])
testX = np.vstack((x1,x2,x3,x4))

result = kmeans(testX, 2, 10)
print "final result:"
print result

最后的例子和上篇的例子一样，计算结果也相同，是正确的结果。