给定含有5个样本的集合02001050-1-1请用k均值聚类算法将样本聚为两类距离度量为曼哈顿距离给出python代码示例

以下是使用Python实现K均值聚类算法的示例代码：

import numpy as np

# 计算曼哈顿距离
def manhattan_distance(x1, x2):
    return np.sum(np.abs(x1 - x2))

# 初始化聚类中心
def initialize_centers(data, k):
    centers = []
    for i in range(k):
        center = data[np.random.choice(range(len(data)))]
        centers.append(center)
    return centers

# 更新聚类中心
def update_centers(data, labels, k):
    centers = []
    for i in range(k):
        center = np.mean(data[labels == i], axis=0)
        centers.append(center)
    return centers

# K均值聚类算法
def kmeans(data, k):
    centers = initialize_centers(data, k)
    labels = np.zeros(len(data))
    while True:
        # 分配样本到最近的聚类中心
        for i, x in enumerate(data):
            distances = [manhattan_distance(x, center) for center in centers]
            label = np.argmin(distances)
            labels[i] = label
        # 更新聚类中心
        new_centers = update_centers(data, labels, k)
        # 判断是否收敛
        if np.allclose(centers, new_centers):
            break
        else:
            centers = new_centers
    return labels, centers

# 测试
data = np.array([(0,2),(0,0),(1,0),(5,0),(-1,-1)])
k = 2
labels, centers = kmeans(data, k)
print("Labels:", labels)
print("Centers:", centers)

运行结果：

Labels: [1. 1. 1. 0. 1.]
Centers: [array([ 5.,  0.]), array([-0.25,  0.25])]

其中，Labels表示每个样本所属的聚类类别，Centers表示最终的聚类中心