keras—多层感知器MLP—IMDb情感分析

 import urllib.request
 import os
 import tarfile
 from keras.datasets import imdb
 from keras.preprocessing import sequence
 from keras.preprocessing.text import Tokenizer
 import re
 def rm_tags(text):
     re_tag=re.compile(r'<[^>]+>')
     return re_tag.sub('',text)
 def read_files(filetype):
     path="C:/Users/admin/.keras/aclImdb/"
     file_list=[]
     positive_path=path+filetype+"/pos/"
     for f in os.listdir(positive_path):
         file_list+=[positive_path+f]
     negative_path=path+filetype+"/pos/"
     for f in os.listdir(negative_path):
         file_list+=[negative_path+f]
     print('read',filetype,'files:',len(file_list))
     all_labels=([]*+[]*)
     all_texts=[]
     for fi in file_list:
         with open(fi,encoding='utf8') as file_input:
             all_texts+=[rm_tags(" ".join(file_input.readlines()))]
     return all_labels,all_texts
 y_train,train_text=read_files("train")
 y_test,test_text=read_files("test")
 print(train_text[])
 print(y_train[])
 token=Tokenizer(num_words=)
 token.fit_on_texts(train_text)
 print(token.document_count)
 print(token.word_index)
 x_train_seq=token.texts_to_sequences(train_text)
 x_test_seq=token.texts_to_sequences(test_text)
 print(train_text[])
 print(x_train_seq[])
 x_train=sequence.pad_sequences(x_train_seq,maxlen=)
 x_test=sequence.pad_sequences(x_test_seq,maxlen=)
 print('before pad_sequences lenfth=',len(x_train_seq[]))
 print(x_train_seq[])
 print('after pad_sequences lenfth=',len(x_train[]))
 print(x_train[])
 from keras.models import Sequential
 from keras.layers import Dense,Dropout,Flatten,Activation
 from keras.layers.embeddings import Embedding
 model=Sequential()
 model.add(Embedding(output_dim=,
                  input_dim=,
                  input_length=))
 model.add(Dropout(0.2))
 #model.add(SimpleRNN(units=))
 model.add(Flatten())
 model.add(Dense(units=,
                 activation='relu'))
 model.add(Dropout(0.35))
 model.add(Dense(units=,
                 activation='sigmoid'))
 print(model.summary())
 model.compile(loss='binary_crossentropy',
               optimizer='adam',
               metrics=['accuracy'])
 train_history=model.fit(x=x_train,y=y_train,batch_size=,
                         epochs=,verbose=,
                         validation_split=0.2)
 scores=model.evaluate(x_test,y_test,verbose=)
 print('accuracy',scores[])
 predict=model.predict_classes(x_test)
 print("prediction[:10]",predict[:])
 predict_classes=predict.reshape(-)
 print(predict_classes[:])
 SentimentDict = {: '正面的', : '负面的'}
 def display_test_Sentiment(i):
     print(test_text[i])
     print('label真实值:', SentimentDict[y_test[i]],
           '预测结果:', SentimentDict[predict_classes[i]])
 display_test_Sentiment()
 input_text='''
 I saw this film with my -year-old a couple weeks ago. While there's plenty about which to gripe, here's one of
 my biggest problems: I can't stand this constant CGI-heavy everything-must-be-a-sequel-or- a- remake era of film
 making. It's making movie makers lazy.
 '''
 input_seq=token.texts_to_sequences([input_text])
 len(input_seq[])
 print(input_seq[])
 pad_input_seq=sequence.pad_sequences(input_seq,maxlen=)
 len(pad_input_seq[])
 print(pad_input_seq[])
 predict_result=model.predict_classes(pad_input_seq)
 print(predict_result)
 print(predict_result[][])
 print(SentimentDict[predict_result[][]])
 def predict_review(input_text):
     input_seq=token.texts_to_sequences([input_text])
     pad_input_seq=sequence.pad_sequences(input_seq,maxlen=)
     predict_result=model.predict_classes(pad_input_seq)
     print(SentimentDict[predict_result[][]])

 predict_review('''
 They poured on the whole "LeFou is gay" thing a bit thick for my taste. It was the only thing that added levity to the movie (despite how much fun it should have been already), but it seemed a bit cheap. I'm not going to apologize for wanting more for my LGBTQ characters than to be just the comic relief.
 ''')

验证的准确率为0问题待解决