[tf] 11. RNN

!pip install -q -U tensorflow
!pip install -q tensorflow_datasets

import numpy as np

import tensorflow_datasets as tfds
import tensorflow as tf

tfds.disable_progress_bar()

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])

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

for example, label in train_dataset.take(1):
  print('text: ', example.numpy() )
  print('label: ', label.numpy())

BUFFER_SIZE = 10000
BATCH_SIZE = 64

train_dataset = train_dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)
test_dataset = test_dataset.batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)

for example, label in train_dataset.take(1):
  print('texts: ', example.numpy()[:3])
  print()
  print('labels:', label.numpy()[:3])

VOCAB_SIZE=1000
encoder = tf.keras.layers.experimental.preprocessing.TextVectorization(
    max_tokens=VOCAB_SIZE)
encoder.adapt(train_dataset.map(lambda text, label: text))

vocab = np.array(encoder.get_vocabulary())
vocab[:20]

encoded_example = encoder(example)[:3].numpy()
encoded_example

tf.keras.layers.LSTM(units, activation='tanh', recurrent_activation='sigmoid', 
                     use_bias=True, kernel_initializer='glorot_uniform', 
                     recurrent_initializer='orthogonal',
                     bias_initializer='zeros', unit_forget_bias=True,
                     kernel_regularizer=None, recurrent_regularizer=None, bias_regularizer=None,
                     activity_regularizer=None, kernel_constraint=None, recurrent_constraint=None,
                     bias_constraint=None, dropout=0.0, recurrent_dropout=0.0, return_sequences=False,
                     return_state=False, go_backwards=False, stateful=False,
                     time_major=False, unroll=False, **kwargs)

model = tf.keras.Sequential([
    encoder,
    tf.keras.layers.Embedding(
        input_dim=len(encoder.get_vocabulary()),
        output_dim=64,
        mask_zero=True),
        #tf.keras.layers.LSTM(64),
        tf.keras.layers.Bidirectional(tf.keras.layers.RNN(tf.keras.layers.LSTMCell(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)

plt.figure(figsize=(16,8))
plt.subplot(1,2,1)
plot_graphs(history, 'accuracy')
plt.ylim(None,1)
plt.subplot(1,2,2)
plot_graphs(history, 'loss')
plt.ylim(0,None)