用sklearn结合bert对中文句子聚类

from sklearn.cluster import KMeans
from bert_serving.client import BertClient
import csv

# 先命令行启动服务
# bert-serving-start -model_dir C:\Users\jason\PycharmProjects\code\chinese_L-12_H-768_A-12 -num_worker=1
'''kmeans聚类所有跟合作有关的句子成3类'''

filename = "sentence_rela_hezuo.csv"

with open(filename, "r", newline='', encoding='utf-8-sig') as f:
    with open("cluster3_hezuo_0.txt", "a", newline='', encoding='utf-8') as f0:
        with open("cluster3_hezuo_1.txt", "a", newline='', encoding='utf-8') as f1:
            with open("cluster3_hezuo_2.txt", "a", newline='', encoding='utf-8') as f2:
                with open("cluster3_hezuo_center.txt", "a", newline='', encoding='utf-8') as fc:
                    f_reader = csv.reader(f)
                    sentence_list = [row[0] for row in f_reader]  # 1273个字符串 句子

                    bc = BertClient(check_length=False)
                    vecs = bc.encode(sentence_list)  # （1273,768） np.ndarray数组