python实现k-means算法简单案例

好的，下面是一个简单的Python实现k-means算法的案例：

import numpy as np
import matplotlib.pyplot as plt

def kMeans(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, :]
    clusterChanged = True
    while clusterChanged:
        clusterChanged = False
        clusterAssment = np.zeros((m, 2))
        for i in range(m):
            minDist = np.inf
            minIndex = -1
            for j in range(k):
                dist = np.sqrt(np.sum(np.power(dataSet[i, :] - centroids[j, :], 2)))
                if dist < minDist:
                    minDist = dist
                    minIndex = j
            if clusterAssment[i, 0] != minIndex:
                clusterChanged = True
                clusterAssment[i, :] = minIndex, minDist ** 2
        for j in range(k):
            pointsInCluster = dataSet[np.nonzero(clusterAssment[:, 0] == j)]
            centroids[j, :] = np.mean(pointsInCluster, axis=0)
    return centroids, clusterAssment

def show(dataSet, k, centroids, clusterAssment):
    m, n = dataSet.shape
    if n != 2:
        print("Dimension of dataSet should be 2!")
        return
    colors = ['b', 'g', 'r', 'c', 'm', 'y', 'k', 'w']
    for i in range(k):
        pointsInCluster = dataSet[np.nonzero(clusterAssment[:, 0] == i)]
        plt.scatter(pointsInCluster[:, 0], pointsInCluster[:, 1], marker='o', c=colors[i % len(colors)], alpha=0.5)
    plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='k', s=100, linewidths=3)
    plt.title('k-means')
    plt.xlabel('X')
    plt.ylabel('Y')
    plt.show()

if __name__ == '__main__':
    data = np.random.rand(200, 2)
    k = 3
    centroids, clusterAssment = kMeans(data, k)
    show(data, k, centroids, clusterAssment)

该案例中，我们首先随机生成一组数据，然后输入数据和k值，即可得到聚类结果。其中，函数`kMeans()`实现了k-means算法，函数`show()`用于绘制聚类结果的图表。