使用python实现可以返回SSE的wkmeans

好的，以下是一个基于Python实现的可以返回SSE的wkmeans代码：

import numpy as np

def euclidean_distance(x1, x2):
    return np.sqrt(np.sum((x1 - x2) ** 2))

class WKMeans:
    def __init__(self, k=2, max_iters=100, plot_steps=False):
        self.k = k
        self.max_iters = max_iters
        self.plot_steps = plot_steps
        
        # list of sample indices for each cluster
        self.clusters = [[] for _ in range(self.k)]
        
        # mean feature vector for each cluster
        self.centroids = []
        
        # SSE (sum of squared errors) for each iteration
        self.sse = []
        
    def predict(self, X):
        self.X = X
        self.n_samples, self.n_features = X.shape
        
        # initialize centroids
        random_sample_idxs = np.random.choice(self.n_samples, self.k, replace=False)
        self.centroids = [self.X[idx] for idx in random_sample_idxs]
        
        # optimization loop
        for i in range(self.max_iters):
            # update clusters
            self.clusters = self._create_clusters(self.centroids)
            
            if self.plot_steps:
                self.plot()
                
            # update centroids
            centroids_old = self.centroids
            self.centroids = self._get_centroids(self.clusters)
            
            # check if converged
            if self._is_converged(centroids_old, self.centroids):
                break
                
        # calculate SSE
        self.sse.append(self._get_sse())
        
        return self._get_cluster_labels(self.clusters)
    
    def _get_cluster_labels(self, clusters):
        labels = np.empty(self.n_samples)
        for cluster_idx, cluster in enumerate(clusters):
            for sample_idx in cluster:
                labels[sample_idx] = cluster_idx
        return labels
    
    def _create_clusters(self, centroids):
        clusters = [[] for _ in range(self.k)]
        for idx, sample in enumerate(self.X):
            centroid_idx = self._closest_centroid(sample, centroids)
            clusters[centroid_idx].append(idx)
        return clusters
    
    def _closest_centroid(self, sample, centroids):
        distances = [euclidean_distance(sample, point) for point in centroids]
        closest_idx = np.argmin(distances)
        return closest_idx
    
    def _get_centroids(self, clusters):
        centroids = np.zeros((self.k, self.n_features))
        for cluster_idx, cluster in enumerate(clusters):
            cluster_mean = np.mean(self.X[cluster], axis=0)
            centroids[cluster_idx] = cluster_mean
        return centroids
    
    def _is_converged(self, centroids_old, centroids):
        distances = [euclidean_distance(centroids_old[i], centroids[i]) for i in range(self.k)]
        return sum(distances) == 0
    
    def _get_sse(self):
        sse = 0
        for cluster_idx, cluster in enumerate(self.clusters):
            for sample_idx in cluster:
                sse += euclidean_distance(self.X[sample_idx], self.centroids[cluster_idx])
        return sse

该代码使用numpy进行向量运算和计算欧几里得距离。初始化KMeans对象时可以指定聚类数目k、最大迭代次数max_iters和是否绘制迭代过程中每个簇的样本点分布（plot_steps），在调用predict方法时将数据集X传入进行聚类并返回每个样本点所属簇的标签。最后可以通过KMeans对象的sse属性获取每次迭代后的SSE值。