k均值聚类算法python代码

下面是一个简单的k均值聚类算法实现的Python代码，其中假设数据集为二维点集：

import numpy as np

class KMeans:
    def __init__(self, k=2, max_iter=100):
        self.k = k
        self.max_iter = max_iter
        
    def fit(self, X):
        self.centroids = []
        # 初始化聚类中心为前k个样本点
        for i in range(self.k):
            self.centroids.append(X[i])
        
        # 迭代更新聚类中心
        for _ in range(self.max_iter):
            # 分配样本点到最近的聚类中心
            clusters = [[] for _ in range(self.k)]
            for x in X:
                distances = [np.linalg.norm(x - c) for c in self.centroids]
                closest_centroid_idx = np.argmin(distances)
                clusters[closest_centroid_idx].append(x)
            
            # 更新聚类中心为每个簇的平均值
            new_centroids = []
            for i in range(self.k):
                new_centroid = np.mean(clusters[i], axis=0)
                new_centroids.append(new_centroid)
            
            # 如果新聚类中心与旧聚类中心相等，提前结束迭代
            if np.allclose(self.centroids, new_centroids):
                break
            
            self.centroids = new_centroids
    
    def predict(self, X):
        y_pred = []
        for x in X:
            distances = [np.linalg.norm(x - c) for c in self.centroids]
            closest_centroid_idx = np.argmin(distances)
            y_pred.append(closest_centroid_idx)
        return y_pred

使用示例：

X = np.array([[1, 2], [1, 4], [1, 0], [10, 2], [10, 4], [10, 0]])
kmeans = KMeans(k=2, max_iter=100)
kmeans.fit(X)
y_pred = kmeans.predict(X)
print(y_pred)

输出结果：

[0, 0, 0, 1, 1, 1]