def testRNN(vocabulary_file, training_dir):
print("Reading vocabulary " + vocabulary_file + "...")
words, dictionary = read_vocabulary(vocabulary_file, MAX_VOCAB_SIZE)
print("Reading sentences and training RNN...")
start = timer()
rnn = RNNExtended(len(words), HIDDEN_LAYER_SIZE)
num_words = 0
for i in range(NUM_ITER):
sentences = tokenize_files(dictionary, training_dir)
for sentence in itertools.islice(sentences, MAX_SENTENCES):
# Todo, create context window for each sentence?
rnn.train(sentence)
num_words += len(sentence)
print("Iteration " + str(i + 1) + "/" + str(NUM_ITER) + " finished (" + str(num_words) + " words)")
num_words = 0
print("- Took %.2f sec" % (timer() - start))
def testSkipGram(vocabulary_file, training_dir):
last_sentence = None
print("Reading vocabulary " + vocabulary_file + "...")
words, dictionary = read_vocabulary(vocabulary_file, MAX_VOCAB_SIZE)
print("Reading sentences and training SkipGram...")
start = timer()
skip_gram = SkipGram(len(words), WINDOW_SIZE, HIDDEN_LAYER_SIZE)
num_words = 0
for i in range(NUM_ITER):
sentences = tokenize_files(dictionary, training_dir)
for sentence in itertools.islice(sentences, MAX_SENTENCES):
last_sentence = sentence
skip_gram.train(sentence)
num_words += len(sentence)
ll = skip_gram.train(last_sentence, compute_ll=True)
print("Iteration " + str(i + 1) + "/" + str(NUM_ITER) + " finished (" + str(num_words) + " words)")
print("Log-likelihood: " + str(ll))
num_words = 0
print("- Took %.2f sec" % (timer() - start))
