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)
