kmeans代码实现聚类

以下是K-Means算法的Python代码实现：

import numpy as np

class KMeans:
    def __init__(self, n_clusters=8, max_iter=300):
        self.n_clusters = n_clusters
        self.max_iter = max_iter

    def fit(self, X):
        self.centroids = X[np.random.choice(range(len(X)), self.n_clusters, replace=False)]
        for i in range(self.max_iter):
            clusters = [[] for _ in range(self.n_clusters)]
            for x in X:
                distances = [np.linalg.norm(x-c) for c in self.centroids]
                cluster_idx = np.argmin(distances)
                clusters[cluster_idx].append(x)
            prev_centroids = self.centroids.copy()
            for j, cluster in enumerate(clusters):
                if len(cluster) == 0:
                    continue
                self.centroids[j] = np.mean(cluster, axis=0)
            if np.allclose(prev_centroids, self.centroids):
                break

    def predict(self, X):
        distances = [[np.linalg.norm(x-c) for c in self.centroids] for x in X]
        cluster_indices = np.argmin(distances, axis=1)
        return cluster_indices

使用方法如下：

from sklearn.datasets import make_blobs
from sklearn.metrics import silhouette_score

X, y = make_blobs(n_samples=1000, centers=8, n_features=2, random_state=42)

kmeans = KMeans(n_clusters=8)
kmeans.fit(X)

labels = kmeans.predict(X)

print("Silhouette Score: ", silhouette_score(X, labels))

这里使用make_blobs函数生成了一个聚类数据集，并计算了Silhouette Score来评估聚类效果。