轮廓系数做聚类，枚举

from sklearn.cluster import KMeans

from sklearn.metrics import silhouette_score

import numpy as np

X = your_embedding_or_pca_array # shape = (N, D)

best_k = None

best_score = -1

scores = \[\]

for k in range(2, 15):

kmeans = KMeans(n_clusters=k, random_state=42)

labels = kmeans.fit_predict(X)

score = silhouette_score(X, labels)

scores.append(score)

if score > best_score:

best_score = score

best_k = k

print(f"最佳 k = {best_k}, 得分 = {best_score:.4f}")

可视化轮廓系数随 k 的变化

import matplotlib.pyplot as plt

plt.plot(range(2, 15), scores, marker='o')

plt.title("Silhouette Score vs K")

plt.xlabel("K")

plt.ylabel("Silhouette Score")

plt.grid(True)

plt.show()