sentiment_classification_using_rnn.py

import tensorflow_datasets as tfds
import tensorflow as tf

import matplotlib.pyplot as plt

def plot_graphs(history, metric):
  plt.plot(history.history[metric])
  plt.plot(history.history['val_'+metric], '')
  plt.xlabel("Epochs")
  plt.ylabel(metric)
  plt.legend([metric, 'val_'+metric])
  plt.show()

def main():
  dataset, info = tfds.load('imdb_reviews/subwords8k', with_info=True,
                            as_supervised=True)
  train_dataset, test_dataset = dataset['train'], dataset['test']

  encoder = info.features['text'].encoder
  print('Vocabulary size: {}'.format(encoder.vocab_size))

  sample_string = 'Hello TensorFlow.'

  encoded_string = encoder.encode(sample_string)
  print('Encoded string is {}'.format(encoded_string))

  original_string = encoder.decode(encoded_string)
  print('The original string: "{}"'.format(original_string))

  assert original_string == sample_string

  for index in encoded_string:
    print('{} ----> {}'.format(index, encoder.decode([index])))

  BUFFER_SIZE = 10000
  BATCH_SIZE = 64

  train_dataset = train_dataset.shuffle(BUFFER_SIZE)
  train_dataset = train_dataset.padded_batch(BATCH_SIZE)
  test_dataset = test_dataset.padded_batch(BATCH_SIZE)

  model = tf.keras.Sequential([
      tf.keras.layers.Embedding(encoder.vocab_size, 64),
      tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
      tf.keras.layers.Dense(64, activation='relu'),
      tf.keras.layers.Dense(1)
  ])

  model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
                optimizer=tf.keras.optimizers.Adam(1e-4),
                metrics=['accuracy'])

  history = model.fit(train_dataset, epochs=10,
                      validation_data=test_dataset,
                      validation_steps=30)

  test_loss, test_acc = model.evaluate(test_dataset)

  print('Test Loss: {}'.format(test_loss))
  print('Test Accuracy: {}'.format(test_acc))

  def pad_to_size(vec, size):
    zeros = [0] * (size - len(vec))
    vec.extend(zeros)
    return vec

  def sample_predict(sample_pred_text, pad):
    encoded_sample_pred_text = encoder.encode(sample_pred_text)

    if pad:
      encoded_sample_pred_text = pad_to_size(encoded_sample_pred_text, 64)
    encoded_sample_pred_text = tf.cast(encoded_sample_pred_text, tf.float32)
    predictions = model.predict(tf.expand_dims(encoded_sample_pred_text, 0))

    return (predictions)

  # predict on a sample text without padding.
  sample_pred_text = ('The movie was cool. The animation and the graphics '
                      'were out of this world. I would recommend this movie.')
  predictions = sample_predict(sample_pred_text, pad=False)
  print(predictions)

  # predict on a sample text with padding
  sample_pred_text = ('The movie was cool. The animation and the graphics '
                      'were out of this world. I would recommend this movie.')
  predictions = sample_predict(sample_pred_text, pad=True)
  print(predictions)

  plot_graphs(history, 'accuracy')
  plot_graphs(history, 'loss')

  # Stack two or more LSTM layers
  model = tf.keras.Sequential([
      tf.keras.layers.Embedding(encoder.vocab_size, 64),
      tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64,  return_sequences=True)),
      tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),
      tf.keras.layers.Dense(64, activation='relu'),
      tf.keras.layers.Dropout(0.5),
      tf.keras.layers.Dense(1)
  ])

  model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
                optimizer=tf.keras.optimizers.Adam(1e-4),
                metrics=['accuracy'])

  history = model.fit(train_dataset, epochs=10,
                      validation_data=test_dataset,
                      validation_steps=30)

  test_loss, test_acc = model.evaluate(test_dataset)

  print('Test Loss: {}'.format(test_loss))
  print('Test Accuracy: {}'.format(test_acc))

  # predict on a sample text without padding.
  sample_pred_text = ('The movie was not good. The animation and the graphics '
                      'were terrible. I would not recommend this movie.')
  predictions = sample_predict(sample_pred_text, pad=False)
  print(predictions)

  # predict on a sample text with padding
  sample_pred_text = ('The movie was not good. The animation and the graphics '
                      'were terrible. I would not recommend this movie.')
  predictions = sample_predict(sample_pred_text, pad=True)
  print(predictions)

  plot_graphs(history, 'accuracy')
  plot_graphs(history, 'loss')

if __name__ == '__main__':
  main()