Kmeans多维数据代码实现聚类

以下是Kmeans多维数据的Python实现，假设有一个数据集X，其中每个数据点都有n个维度：

import numpy as np

class Kmeans:
    def __init__(self, n_clusters=8, max_iter=300, tol=1e-4, random_state=1):
        self.n_clusters = n_clusters
        self.max_iter = max_iter
        self.tol = tol
        self.random_state = random_state
        self.labels_ = None
        self.centers_ = None

    def fit(self, X):
        n_samples, n_features = X.shape
        np.random.seed(self.random_state)
        center_ids = np.random.choice(n_samples, self.n_clusters, replace=False)
        centers = X[center_ids]
        for i in range(self.max_iter):
            distances = np.linalg.norm(X[:, np.newaxis, :] - centers, axis=-1)
            labels = np.argmin(distances, axis=-1)
            new_centers = np.array([X[labels == j].mean(axis=0) for j in range(self.n_clusters)])
            if np.allclose(centers, new_centers, rtol=self.tol):
                break
            centers = new_centers
        self.labels_ = labels
        self.centers_ = centers

其中，n_clusters为聚类的簇数，max_iter为最大迭代次数，tol为收敛阈值，random_state为随机数种子。fit方法进行Kmeans聚类，输入数据集X，输出标签labels和聚类中心centers。