k均值算法python

以下是使用Python实现k均值算法的示例代码：

from numpy import *
import matplotlib.pyplot as plt

# 计算两个向量之间的欧氏距离
def euclDistance(vector1, vector2):
    return sqrt(sum(power(vector2 - vector1, 2)))

# 初始化数据的质心，k表示簇的个数
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

# k均值聚类算法
def kMeans(dataSet, k):
    numSamples = dataSet.shape[0]
    # 第一列存储该样本属于哪个簇，第二列存储该样本距离所属簇的距离
    clusterAssment = mat(zeros((numSamples, 2)))
    clusterChanged = True

    # 初始化质心
    centroids = initCentroids(dataSet, k)

    while clusterChanged:
        clusterChanged = False
        # 遍历每个样本
        for i in range(numSamples):
            minDist = 100000.0
            minIndex = 0
            # 遍历每个质心
            for j in range(k):
                distance = euclDistance(centroids[j, :], dataSet[i, :])
                if distance < minDist:
                    minDist = distance
                    minIndex = j
            # 如果该样本所属的簇发生了变化
            if clusterAssment[i, 0] != minIndex:
                clusterChanged = True
                clusterAssment[i, :] = minIndex, minDist ** 2

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

    print('Cluster complete!')
    return centroids, clusterAssment

# 可视化聚类结果
def showCluster(dataSet, k, centroids, clusterAssment):
    numSamples, dim = dataSet.shape
    if dim != 2:
        print("Sorry! I can not draw because the dimension of your data is not 2!")
        return 1

    # 用不同颜色和标记绘制每个簇的点
    mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr', '<r', 'pr']
    for i in range(numSamples):
        markIndex = int(clusterAssment[i, 0])
        plt.plot(dataSet[i, 0], dataSet[i, 1], mark[markIndex])

    # 用不同颜色和标记绘制质心
    mark = ['*r', '*b', '*g', '*k', '^b', '+b', 'sb', 'db', '<b', 'pb']
    for i in range(k):
        plt.plot(centroids[i, 0], centroids[i, 1], mark[i], markersize=20)

    plt.show()

# 测试
if __name__ == '__main__':
    # 生成测试数据
    dataMat = mat(random.rand(100, 2))
    # 聚类个数为4
    k = 4
    # 运行k均值聚类算法
    centroids, clusterAssment = kMeans(dataMat, k)
    # 可视化聚类结果
    showCluster(dataMat, k, centroids, clusterAssment)