def test_train_rnn_model(): data_dir = './data/' data = load_data.load_rotten_tomatoes_sentiment_analysis_dataset(data_dir) acc, loss = train_rnn_model.train_rnn_model(data) assert acc == pytest.approx(0.68, 0.02) assert loss == pytest.approx(0.82, 0.02)
def test_train_sequence_model(self): data = load_data.load_rotten_tomatoes_sentiment_analysis_dataset( data_dir) acc, loss = train_sequence_model.train_sequence_model(data) self.assertTrue(0.66 < acc < 0.70) self.assertTrue(0.80 < loss < 0.84)
history = model.fit( x_train, train_labels, epochs=epochs, callbacks=callbacks, validation_data=(x_val, val_labels), verbose=2, # Logs once per epoch. batch_size=batch_size) # Print results. history = history.history print('Validation accuracy: {acc}, loss: {loss}'.format( acc=history['val_acc'][-1], loss=history['val_loss'][-1])) # Save model. model.save('rotten_tomatoes_sepcnn_model.h5') return history['val_acc'][-1], history['val_loss'][-1] if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument('--data_dir', type=str, default='./data', help='input data directory') FLAGS, unparsed = parser.parse_known_args() # Using the Rotten tomatoes movie reviews dataset to demonstrate # training sequence model. data = load_data.load_rotten_tomatoes_sentiment_analysis_dataset( FLAGS.data_dir) train_sequence_model(data)
@author: nikhil """ import numpy as np import load_data import explore_data # ((train_texts, train_labels), (validation_texts, validation_labels)) = load_data.load_imdb_sentiment_analysis_dataset("./data/") # explore_data.get_num_classes(train_labels) # explore_data.get_num_words_per_sample(train_texts) # explore_data.plot_frequency_distribution_of_ngrams(train_texts) # explore_data.plot_sample_length_distribution(train_texts) # explore_data.plot_class_distribution(train_labels) ((train_texts, train_labels), (validation_texts, validation_labels)) = load_data.load_rotten_tomatoes_sentiment_analysis_dataset("./data/") count = 0 for i in train_labels: if i == 1: count+=1 c2=0 c3=0 train_labels_final = [] train_texts_final = [] for i in range(len(train_labels)): if train_labels[i]==0 or train_labels[i]==4: continue elif train_labels[i]==1: train_labels_final.append(1)