Kajian kes menggunakan model LSTM dwiarah untuk pengelasan teks

import os  
import numpy as np  
from keras.preprocessing.text import Tokenizer  
from keras.preprocessing.sequence import pad_sequences  
from keras.models import Sequential  
from keras.layers import Dense, Embedding, Bidirectional, LSTM  
from sklearn.model_selection import train_test_split

def load_imdb_data(path):  
    assert os.path.exists(path)  
    trainset, devset, testset = [], [], []  
    with open(os.path.join(path, "train.txt"), "r") as fr:  
        for line in fr:  
            sentence_label, sentence = line.strip().lower().split("\t", maxsplit=1)  
            trainset.append((sentence, sentence_label))  
    with open(os.path.join(path, "dev.txt"), "r") as fr:  
        for line in fr:  
            sentence_label, sentence = line.strip().lower().split("\t", maxsplit=1)  
            devset.append((sentence, sentence_label))  
    with open(os.path.join(path, "test.txt"), "r") as fr:  
        for line in fr:  
            sentence_label, sentence = line.strip().lower().split("\t", maxsplit=1)  
            testset.append((sentence, sentence_label))  
    return trainset, devset, testset

max_features = 20000  
maxlen = 80  # cut texts after this number of words (among top max_features most common words)  
batch_size = 32  
  
print('Pad & split data into training set and dev set')  
x_train, y_train = [], []  
for sent, label in trainset:  
    x_train.append(sent)  
    y_train.append(label)  
x_train, y_train = pad_sequences(x_train, maxlen=maxlen), np.array(y_train)  
x_train, y_train = np.array(x_train), np.array(y_train)  
x_dev, y_dev = [], []  
for sent, label in devset:  
    x_dev.append(sent)  
    y_dev.append(label)  
x_dev, y_dev = pad_sequences(x_dev, maxlen=maxlen), np.array(y_dev)  
x_dev, y_dev = np.array(x_dev), np.array(y_dev)

print('Build model...')  
model = Sequential()  
model.add(Embedding(max_features, 128, input_length=maxlen))  
model.add(Bidirectional(LSTM(64)))  
model.add(LSTM(64))  
model.add(Dense(1, activation='sigmoid'))  
  
print('Compile model...')  
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

epochs = 10  
batch_size = 64  
  
history = model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_data=(x_dev, y_dev))

test_loss, test_acc = model.evaluate(x_test, y_test)  
print('Test accuracy:', test_acc)