我已经训练并保存了一个模型。我试图在新数据上进一步训练该模型，但出现了错误。相关代码部分如下：
from tensorflow.keras.preprocessing.text import Tokenizer# 使用的最多单词数量（最常见）。MAX_NB_WORDS = 50000# 每条投诉中的最大单词数。MAX_SEQUENCE_LENGTH = 250# 这是固定的。EMBEDDING_DIM = 100tokenizer = Tokenizer(num_words=MAX_NB_WORDS, filters='!"#$%&()*+,-./:;<=>?@[\]^_`{|}~', lower=True)tokenizer.fit_on_texts(master_df['Observation'].values)word_index = tokenizer.word_indexfrom sklearn.feature_extraction.text import CountVectorizercv=CountVectorizer(max_df=1.0,min_df=1, stop_words=stop_words, max_features=10000, ngram_range=(1,3))X=cv.fit_transform(X)with open("../sgd.pickle", 'rb') as f: sgd = pickle.load(f)def output_sample(sentence): test=preprocess_text(sentence) test=test.lower() #print(test) test=[test] tokenizer.fit_on_sequences(test) new_words= tokenizer.word_index #print(word_index)`` test1=cv.transform(test) #print(test1) output=sgd.predict(test1) return output[0]def retrain(X,y): X=preprocess_text(X) X=X.lower() X=[X] tokenizer.fit_on_texts(X) new_words=tokenizer.word_index X=cv.fit_transform(X) sgd.fit(X,y) with open('sgd.pickle', 'wb') as f: pickle.dump(sgd, f) print("模型已在新数据上训练")sentence=input("\n\n输入您的观察结果：\n\n")output=output_sample(sentence)print("\n\n风险预测为",preprocess_text(output),"\n\n")print("上述预测正确吗？\n")corr=input("按'y'表示是，按'n'表示否。\n")if corr=='y': newy=np.array(output) retrain(sentence,newy)elif corr=='n': print("正确的风险是什么？\n1. 低\n2. 中\n") r=input("输入相应的数字： ") if r=='1': newy=np.array('Low') retrain(sentence,newy) elif r=='2': newy=np.array('Medium') retrain(sentence,newy) else: print("输入错误。请重新启动应用程序。")else: print("输入错误。请重新启动应用程序")运行程序时，错误发生在sgd.fit(X,y)处。错误信息如下：
---------------------------------------------------------------------------ValueError Traceback (most recent call last)~\AppData\Local\Temp/ipykernel_11300/3528077041.py in <module> 5 newy=[output] 6 print(newy)----> 7 retrain(sentence,newy) 8 9 elif corr=='n':~\AppData\Local\Temp/ipykernel_11300/2433836763.py in retrain(X, y) 7 X=cv.fit_transform(X) 8 #y = y.reshape((-1, 1))----> 9 sgd.fit(X,y) 10 with open('sgd.pickle', 'wb') as f: 11 pickle.dump(sgd, f)~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\pipeline.py in fit(self, X, y, **fit_params) 344 if self._final_estimator != 'passthrough': 345 fit_params_last_step = fit_params_steps[self.steps[-1][0]]--> 346 self._final_estimator.fit(Xt, y, **fit_params_last_step) 347 348 return self~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\linear_model\_stochastic_gradient.py in fit(self, X, y, coef_init, intercept_init, sample_weight) 727 Returns an instance of self. 728 """--> 729 return self._fit(X, y, alpha=self.alpha, C=1.0, 730 loss=self.loss, learning_rate=self.learning_rate, 731 coef_init=coef_init, intercept_init=intercept_init,~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\linear_model\_stochastic_gradient.py in _fit(self, X, y, alpha, C, loss, learning_rate, coef_init, intercept_init, sample_weight) 567 self.t_ = 1.0 568 --> 569 self._partial_fit(X, y, alpha, C, loss, learning_rate, self.max_iter, 570 classes, sample_weight, coef_init, intercept_init) 571 ~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\linear_model\_stochastic_gradient.py in _partial_fit(self, X, y, alpha, C, loss, learning_rate, max_iter, classes, sample_weight, coef_init, intercept_init) 529 max_iter=max_iter) 530 else:--> 531 raise ValueError( 532 "The number of classes has to be greater than one;" 533 " got %d class" % n_classes)ValueError: The number of classes has to be greater than one; got 1 class数据样本如下：
Observation Risk0 A separate road for light vehicle should be ma... Low2 All benches were not having sufficient berm. Low3 As light arrangement is not adequate. Low4 As light arrangement is not adequate. Low5 As contractor's equipment record is not availa... Low77 First aid Room is not established. Medium98 Heavy dust on haul road is found with in suffi... Medium79 First aid station is maintained in the Rest sh... Medium171 Presently explosive van is not available with ... Medium79 First aid station is maintained in the Rest sh... Medium理想情况下它应该接受输入，但我不知道为什么会出现这个错误。
回答：
我清理了代码并对retrain函数进行了多项更改，现在该函数将向训练集中添加新的字符串和标签，并再次拟合分类器。您的代码的其他部分在逻辑上保持不变！
实用函数：
def output_sample(sentence): test=preprocess_text(sentence) test=test.lower() test=[test] tokenizer.fit_on_sequences(test) new_words= tokenizer.word_index test1=cv.transform(test) output=sgd.predict(test1) return output[0]def preprocess_text(string): # 做任何你想做的事，但之后返回字符串 ;) return stringdef retrain(X,y): X=preprocess_text(X) X=X.lower() X=[X] X = cv.fit_transform(master_df['Observation']+X) new_words=tokenizer.word_index sgd.fit(X,master_df['Risk']+y) with open('sgd.pickle', 'wb') as f: pickle.dump(sgd, f) print("模型已在新数据上训练")实际流程：
import numpy as np import pickleimport nltkfrom sklearn.feature_extraction.text import CountVectorizerstopwords = nltk.corpus.stopwords.words('english')cv=CountVectorizer(max_df=1.0,min_df=1, stop_words=stopwords, max_features=10000, ngram_range=(1,3))master_df = pd.read_csv('classification.tsv')X=cv.fit_transform(master_df['Observation'])from sklearn.linear_model import SGDClassifiertry: f = open("./sgd.pickle", 'rb') sgd = pickle.load(f)except: sgd = SGDClassifier()sgd.fit(X, master_df['Risk'].to_list())sentence=input("\n\n输入您的观察结果：\n\n")output=output_sample(sentence)print("\n\n风险预测为",preprocess_text(output),"\n\n")print("上述预测正确吗？\n")corr=input("按'y'表示是，按'n'表示否。\n")if corr=='y': newy=np.array(output) retrain(sentence, newy)elif corr=='n': print("正确的风险是什么？\n1. 低\n2. 中\n") r=input("输入相应的数字： ") if r=='1': newy=np.array('Low') retrain(sentence,newy) elif r=='2': newy=np.array('Medium') retrain(sentence,newy) else: print("输入错误。请重新启动应用程序。")else: print("输入错误。请重新启动应用程序")