中文文本分析，在分好词、转换为tifdf矩阵，进行kmeans聚类的时候，无法得到聚类结果文件
import joblib
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
import pandas as pd
from sklearn.cluster import KMeans
stpwrdpath = "D:\数据挖掘\project\data\stop_word.txt"
stpwrd_dic = open(stpwrdpath, 'rb')
stpwrd_content = stpwrd_dic.read()
stpwrdlst = stpwrd_content.splitlines()
stpwrd_dic.close()
with open('D:\数据挖掘\project\data\test1.txt',"r",encoding="utf8") as f3:
res1 = f3.readlines()
print(res1)
with open('D:\数据挖掘\project\data\test3.txt',"r",encoding="utf8") as f4:
res2 = f4.readlines()
print(res2)
corpus=[]
corpus = res1 + res2
vector = TfidfVectorizer()
tfidf = vector.fit_transform(corpus)
tfidf.toarray()
print(tfidf.shape)
clf = KMeans(n_clusters=4, random_state=4) # 选择4个中心点# random_state：相当于随机种子。在开始运行时，k 均值聚类需要从众多数据中随机挑选 k 个点作为簇中心，random_state 就是为挑选 k 个簇中心而准备的随机种
clf.fit(tfidf)
print('4个中心点为:' + str(clf.cluster_centers_))
joblib.dump(clf, 'km.pkl')
train_res = pd.Series(clf.labels_).value_counts()
s = 0
for i in range(len(train_res)):
s += abs(train_res[i] - 400)
acc_train = (len(train_res) * 400 - s) / (len(train_res) * 400)
print('\n训练集准确率为：' + str(acc_train))
print('\n每个样本所属的簇为', i + 1, ' ', clf.labels_[i])
for i in range(len(clf.labels_)):
print(i + 1, ' ', clf.labels_[i])
kinds = pd.Series([clf.classify(i) for i in tfidf])
fw = open('data/ClusterText.txt', 'a+', encoding='utf-8')
for i, v in kinds.items():
fw.write(str(i) + '\t' + str(v) + '\n')
fw.close()
AttributeError: 'KMeans' object has no attribute 'classify'