Keras学习（九）-IMDB情感分析（LSTM形式）

• LSTM，是专门设计来解决RNN长期依赖的问题
  
  

1.数据准备

from keras.datasets import imdb
from keras.preprocessing import sequence
from keras.preprocessing.text import Tokenizer
import numpy as np
np.random.seed(10)

import re
re_tag = re.compile(r'<[^>]+>')

def rm_tags(text):
    return re_tag.sub('', text)

import os
def read_files(filetype):
    path = "data/aclImdb/"
    file_list=[]

    positive_path=path + filetype+"/pos/"
    for f in os.listdir(positive_path):
        file_list+=[positive_path+f]
    
    negative_path=path + filetype+"/neg/"
    for f in os.listdir(negative_path):
        file_list+=[negative_path+f]
        
    print('read',filetype, 'files:',len(file_list))
       
    all_labels = ([1] * 12500 + [0] * 12500) 
    
    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

token = Tokenizer(num_words=3800)
token.fit_on_texts(train_text)

x_train_seq = token.texts_to_sequences(train_text)
x_test_seq  = token.texts_to_sequences(test_text)

x_train = sequence.pad_sequences(x_train_seq, maxlen=380)
x_test  = sequence.pad_sequences(x_test_seq,  maxlen=380)

2.建立模型

from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation,Flatten
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM

model = Sequential()

model.add(Embedding(output_dim=32,
                    input_dim=3800, 
                    input_length=380))
model.add(Dropout(0.2))

model.add(LSTM(32))

model.add(Dense(units=256,
                activation='relu' ))
model.add(Dropout(0.2))

model.add(Dense(units=1,
                activation='sigmoid' ))

model.summary()

3.训练模型

model.compile(loss='binary_crossentropy', 
              #optimizer='rmsprop', 
              optimizer='adam', 
              metrics=['accuracy'])

train_history =model.fit(x_train, y_train,batch_size=100, 
                         epochs=10,verbose=1,
                         validation_split=0.2)

%pylab inline
import matplotlib.pyplot as plt
def show_train_history(train_history,train,validation):
    plt.plot(train_history.history[train])
    plt.plot(train_history.history[validation])
    plt.title('Train History')
    plt.ylabel(train)
    plt.xlabel('Epoch')
    plt.legend(['train', 'validation'], loc='upper left')
    plt.show()

show_train_history(train_history,'acc','val_acc')
show_train_history(train_history,'loss','val_loss')

4.模型准确率

scores = model.evaluate(x_test, y_test, verbose=1)
scores[1]

5.结果预测

• 概率预测

probility=model.predict(x_test)

• 预测结果

predict=model.predict_classes(x_test)

• 查看预测结果

SentimentDict={1:'正面的',0:'负面的'}
def display_test_Sentiment(i):
    print(test_text[i])
    print('标签label:',SentimentDict[y_test[i]],'预测结果:',SentimentDict[predict_classes[i]])

display_test_Sentiment(2)

6.模型保存

model_json = model.to_json()
with open("SaveModel/Imdb_LSTM_model.json", "w") as json_file:
    json_file.write(model_json)

model.save_weights("SaveModel/Imdb_LSTM_model.h5")
print("Saved model to disk")