Here we implement an LSTM model on all a data set of Shakespeare works.
We will stack multiple LSTM models for a more accurate representation
of Shakespearean language. We will also use characters instead of words.
# -*- coding: utf-8 -*-
#
# Stacking LSTM Layers
#---------------------
# Here we implement an LSTM model on all a data set of Shakespeare works.
# We will stack multiple LSTM models for a more accurate representation
# of Shakespearean language. We will also use characters instead of words.
#
import os
import re
import string
import requests
import numpy as np
import collections
import random
import pickle
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
ops.reset_default_graph()
# Start a session
sess = tf.Session()
# Set RNN Parameters
num_layers = 3 # Number of RNN layers stacked
min_word_freq = 5 # Trim the less frequent words off
rnn_size = 128 # RNN Model size, has to equal embedding size
epochs = 10 # Number of epochs to cycle through data
batch_size = 100 # Train on this many examples at once
learning_rate = 0.0005 # Learning rate
training_seq_len = 50 # how long of a word group to consider
save_every = 500 # How often to save model checkpoints
eval_every = 50 # How often to evaluate the test sentences
prime_texts = ['thou art more', 'to be or not to', 'wherefore art thou']
# Download/store Shakespeare data
data_dir = 'temp'
data_file = 'shakespeare.txt'
model_path = 'shakespeare_model'
full_model_dir = os.path.join(data_dir, model_path)
# Declare punctuation to remove, everything except hyphens and apostrophes
punctuation = string.punctuation
punctuation = ''.join([x for x in punctuation if x not in ['-', "'"]])
# Make Model Directory
if not os.path.exists(full_model_dir):
os.makedirs(full_model_dir)
# Make data directory
if not os.path.exists(data_dir):
os.makedirs(data_dir)
print('Loading Shakespeare Data')
# Check if file is downloaded.
if not os.path.isfile(os.path.join(data_dir, data_file)):
print('Not found, downloading Shakespeare texts from www.gutenberg.org')
shakespeare_url = 'http://www.gutenberg.org/cache/epub/100/pg100.txt'
# Get Shakespeare text
response = requests.get(shakespeare_url)
shakespeare_file = response.content
# Decode binary into string
s_text = shakespeare_file.decode('utf-8')
# Drop first few descriptive paragraphs.
s_text = s_text[7675:]
# Remove newlines
s_text = s_text.replace('\r\n', '')
s_text = s_text.replace('\n', '')
# Write to file
with open(os.path.join(data_dir, data_file), 'w') as out_conn:
out_conn.write(s_text)
else:
# If file has been saved, load from that file
with open(os.path.join(data_dir, data_file), 'r') as file_conn:
s_text = file_conn.read().replace('\n', '')
# Clean text
print('Cleaning Text')
s_text = re.sub(r'[{}]'.format(punctuation), ' ', s_text)
s_text = re.sub('\s+', ' ', s_text).strip().lower()
# Split up by characters
char_list = list(s_text)
# Build word vocabulary function
def build_vocab(characters):
character_counts = collections.Counter(characters)
# Create vocab --> index mapping
chars = character_counts.keys()
vocab_to_ix_dict = {key: (inx + 1) for inx, key in enumerate(chars)}
# Add unknown key --> 0 index
vocab_to_ix_dict['unknown'] = 0
# Create index --> vocab mapping
ix_to_vocab_dict = {val: key for key, val in vocab_to_ix_dict.items()}
return ix_to_vocab_dict, vocab_to_ix_dict
# Build Shakespeare vocabulary
print('Building Shakespeare Vocab by Characters')
ix2vocab, vocab2ix = build_vocab(char_list)
vocab_size = len(ix2vocab)
print('Vocabulary Length = {}'.format(vocab_size))
# Sanity Check
assert(len(ix2vocab) == len(vocab2ix))
# Convert text to word vectors
s_text_ix = []
for x in char_list:
try:
s_text_ix.append(vocab2ix[x])
except KeyError:
s_text_ix.append(0)
s_text_ix = np.array(s_text_ix)
# Define LSTM RNN Model
class LSTM_Model():
def __init__(self, rnn_size, num_layers, batch_size, learning_rate,
training_seq_len, vocab_size, infer_sample=False):
self.rnn_size = rnn_size
self.num_layers = num_layers
self.vocab_size = vocab_size
self.infer_sample = infer_sample
self.learning_rate = learning_rate
if infer_sample:
self.batch_size = 1
self.training_seq_len = 1
else:
self.batch_size = batch_size
self.training_seq_len = training_seq_len
self.lstm_cell = tf.contrib.rnn.BasicLSTMCell(rnn_size)
self.lstm_cell = tf.contrib.rnn.MultiRNNCell([self.lstm_cell for _ in range(self.num_layers)])
self.initial_state = self.lstm_cell.zero_state(self.batch_size, tf.float32)
self.x_data = tf.placeholder(tf.int32, [self.batch_size, self.training_seq_len])
self.y_output = tf.placeholder(tf.int32, [self.batch_size, self.training_seq_len])
with tf.variable_scope('lstm_vars'):
# Softmax Output Weights
W = tf.get_variable('W', [self.rnn_size, self.vocab_size], tf.float32, tf.random_normal_initializer())
b = tf.get_variable('b', [self.vocab_size], tf.float32, tf.constant_initializer(0.0))
# Define Embedding
embedding_mat = tf.get_variable('embedding_mat', [self.vocab_size, self.rnn_size],
tf.float32, tf.random_normal_initializer())
embedding_output = tf.nn.embedding_lookup(embedding_mat, self.x_data)
rnn_inputs = tf.split(axis=1, num_or_size_splits=self.training_seq_len, value=embedding_output)
rnn_inputs_trimmed = [tf.squeeze(x, [1]) for x in rnn_inputs]
decoder = tf.contrib.legacy_seq2seq.rnn_decoder
outputs, last_state = decoder(rnn_inputs_trimmed,
self.initial_state,
self.lstm_cell)
# RNN outputs
output = tf.reshape(tf.concat(axis=1, values=outputs), [-1, rnn_size])
# Logits and output
self.logit_output = tf.matmul(output, W) + b
self.model_output = tf.nn.softmax(self.logit_output)
loss_fun = tf.contrib.legacy_seq2seq.sequence_loss_by_example
loss = loss_fun([self.logit_output],[tf.reshape(self.y_output, [-1])],
[tf.ones([self.batch_size * self.training_seq_len])],
self.vocab_size)
self.cost = tf.reduce_sum(loss) / (self.batch_size * self.training_seq_len)
self.final_state = last_state
gradients, _ = tf.clip_by_global_norm(tf.gradients(self.cost, tf.trainable_variables()), 4.5)
optimizer = tf.train.AdamOptimizer(self.learning_rate)
self.train_op = optimizer.apply_gradients(zip(gradients, tf.trainable_variables()))
def sample(self, sess, words=ix2vocab, vocab=vocab2ix, num=20, prime_text='thou art'):
state = sess.run(self.lstm_cell.zero_state(1, tf.float32))
char_list = list(prime_text)
for char in char_list[:-1]:
x = np.zeros((1, 1))
x[0, 0] = vocab[char]
feed_dict = {self.x_data: x, self.initial_state:state}
[state] = sess.run([self.final_state], feed_dict=feed_dict)
out_sentence = prime_text
char = char_list[-1]
for n in range(num):
x = np.zeros((1, 1))
x[0, 0] = vocab[char]
feed_dict = {self.x_data: x, self.initial_state:state}
[model_output, state] = sess.run([self.model_output, self.final_state], feed_dict=feed_dict)
sample = np.argmax(model_output[0])
if sample == 0:
break
char = words[sample]
out_sentence = out_sentence + char
return out_sentence
# Define LSTM Model
lstm_model = LSTM_Model(rnn_size,
num_layers,
batch_size,
learning_rate,
training_seq_len,
vocab_size)
# Tell TensorFlow we are reusing the scope for the testing
with tf.variable_scope(tf.get_variable_scope(), reuse=True):
test_lstm_model = LSTM_Model(rnn_size,
num_layers,
batch_size,
learning_rate,
training_seq_len,
vocab_size,
infer_sample=True)
# Create model saver
saver = tf.train.Saver(tf.global_variables())
# Create batches for each epoch
num_batches = int(len(s_text_ix)/(batch_size * training_seq_len)) + 1
# Split up text indices into subarrays, of equal size
batches = np.array_split(s_text_ix, num_batches)
# Reshape each split into [batch_size, training_seq_len]
batches = [np.resize(x, [batch_size, training_seq_len]) for x in batches]
# Initialize all variables
init = tf.global_variables_initializer()
sess.run(init)
# Train model
train_loss = []
iteration_count = 1
for epoch in range(epochs):
# Shuffle word indices
random.shuffle(batches)
# Create targets from shuffled batches
targets = [np.roll(x, -1, axis=1) for x in batches]
# Run a through one epoch
print('Starting Epoch #{} of {}.'.format(epoch+1, epochs))
# Reset initial LSTM state every epoch
state = sess.run(lstm_model.initial_state)
for ix, batch in enumerate(batches):
training_dict = {lstm_model.x_data: batch, lstm_model.y_output: targets[ix]}
# We need to update initial state for each RNN cell:
for i, (c, h) in enumerate(lstm_model.initial_state):
training_dict[c] = state[i].c
training_dict[h] = state[i].h
temp_loss, state, _ = sess.run([lstm_model.cost, lstm_model.final_state, lstm_model.train_op],
feed_dict=training_dict)
train_loss.append(temp_loss)
# Print status every 10 gens
if iteration_count % 10 == 0:
summary_nums = (iteration_count, epoch+1, ix+1, num_batches+1, temp_loss)
print('Iteration: {}, Epoch: {}, Batch: {} out of {}, Loss: {:.2f}'.format(*summary_nums))
# Save the model and the vocab
if iteration_count % save_every == 0:
# Save model
model_file_name = os.path.join(full_model_dir, 'model')
saver.save(sess, model_file_name, global_step=iteration_count)
print('Model Saved To: {}'.format(model_file_name))
# Save vocabulary
dictionary_file = os.path.join(full_model_dir, 'vocab.pkl')
with open(dictionary_file, 'wb') as dict_file_conn:
pickle.dump([vocab2ix, ix2vocab], dict_file_conn)
if iteration_count % eval_every == 0:
for sample in prime_texts:
print(test_lstm_model.sample(sess, ix2vocab, vocab2ix, num=10, prime_text=sample))
iteration_count += 1
# Plot loss over time
plt.plot(train_loss, 'k-')
plt.title('Sequence to Sequence Loss')
plt.xlabel('Generation')
plt.ylabel('Loss')
plt.show()