不调包实现kmeans聚类，并画出聚类结果图 python

K-Means是一种经典的聚类算法，可以将数据集划分为预定数量的簇。下面是不调用Python库实现K-Means聚类的代码（假设数据集为X，聚类数为k）：

import numpy as np

# 计算两个向量之间的欧式距离
def dist(x1, x2):
    return np.sqrt(np.sum((x1-x2)**2))

# 初始化聚类中心
def init_centers(X, k):
    centers = X[np.random.choice(range(len(X)), k, replace=False)]
    return centers

# 进行K-Means聚类
def kmeans(X, k):
    centers = init_centers(X, k)
    while True:
        # 计算每个样本距离最近的聚类中心，并将样本归入对应簇
        clusters = [[] for _ in range(k)]
        for i, x in enumerate(X):
            distances = [dist(x, center) for center in centers]
            cluster_index = np.argmin(distances)
            clusters[cluster_index].append(i)
        
        # 计算新的聚类中心
        new_centers = np.zeros_like(centers)
        for i, cluster in enumerate(clusters):
            cluster_mean = np.mean(X[cluster], axis=0)
            new_centers[i] = cluster_mean
        
        # 如果聚类中心不再改变，则停止迭代
        if np.allclose(new_centers, centers):
            break
        else:
            centers = new_centers
    
    return clusters

# 生成数据集
X = np.concatenate([np.random.randn(100, 2) + [-5, -5], 
                    np.random.randn(100, 2) + [5, 5], 
                    np.random.randn(100, 2) + [-5, 5], 
                    np.random.randn(100, 2) + [5, -5]])

# 进行K-Means聚类
clusters = kmeans(X, k=4)

# 绘制聚类结果图
import matplotlib.pyplot as plt
colors = ['r', 'g', 'b', 'y']
for i, cluster in enumerate(clusters):
    for j in cluster:
        plt.scatter(X[j, 0], X[j, 1], c=colors[i])
plt.show()