值错误:标签数为1。使用剪影分数时,有效值为2到n_个样本-1(包括1个样本)

我正在计算 silhouette score 当我找到要创建的最佳集群数时,会得到一个错误,它说:

ValueError: Number of labels is 1. Valid values are 2 to n_samples - 1 (inclusive)

我不明白为什么会这样。这是我用来聚类和计算的代码 轮廓分数 .

我读取包含要群集和运行的文本的csv K-Means 上 n 群集值。为什么我会出现这个错误?

  #Create cluster using K-Means
#Only creates graph
import matplotlib
#matplotlib.use('Agg')
import re
import os
import nltk, math, codecs
import csv
from nltk.corpus import stopwords
from gensim.models import Doc2Vec
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.metrics import silhouette_score

model_name = checkpoint_save_path
loaded_model = Doc2Vec.load(model_name)

#Load the test csv file
data = pd.read_csv(test_filename)
overview = data['overview'].astype('str').tolist()
overview = filter(bool, overview)
vectors = []

def split_words(text):
  return ''.join([x if x.isalnum() or x.isspace() else " " for x in text ]).split()

def preprocess_document(text):
  sp_words = split_words(text)
  return sp_words

for i, t in enumerate(overview):
  vectors.append(loaded_model.infer_vector(preprocess_document(t)))

sse = {}
silhouette = {}


for k in range(1,15):
  km = KMeans(n_clusters=k, max_iter=1000, verbose = 0).fit(vectors)
  sse[k] = km.inertia_
  #FOLLOWING LINE CAUSES ERROR
  silhouette[k] = silhouette_score(vectors, km.labels_, metric='euclidean')

best_cluster_size = 1
min_error = float("inf")

for cluster_size in sse:
    if sse[cluster_size] < min_error:
        min_error = sse[cluster_size]
        best_cluster_size = cluster_size

print(sse)
print("====")
print(silhouette)