我正在嘗試尋找 DBSCAN 的最佳 eps 值。我設置min_samples為 24，因為我有 2 * 12 個特征傳入x_set，但出現(xiàn)以下錯誤：ValueError: Number of labels is 1. Valid values are 2 to n_samples - 1 (inclusive)我知道需要silhouette_score超過 1 個集群標簽?；陬愃频腻e誤，這可能會導致此錯誤。我該如何解決這個問題？x_set包含以下數(shù)據(jù)：x_set = [6.67933536e+00 1.65097236e+00 1.24573705e+00 1.01693195e+00 9.28128921e-01 7.82497904e-01 5.98319768e-01 1.13439548e-01 9.05382510e-04 5.42710767e-04 2.87522799e-04 1.90924073e-04]def best_eps(x_set):        X = x_set    range_eps = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]    for i in range_eps:        print("eps value is: "+str(i))        db = DBSCAN(eps=i, min_samples=24, metric='euclidean').fit(X)        core_samples_mask = np.zeros_like(db.labels_, dtype=bool)        core_samples_mask[db.core_sample_indices_] = True        labels = db.labels_        print(set(labels))        silhouette_avg = silhouette_score(X, labels)        print("For eps value ="+str(i), labels, "The average silhouette_score is :", silhouette_avg)    return