def load_ratnet(data_dir, model_dir):
logging.info("Loading data from cache...")
with open(data_dir / 'beer_core-train.pkl', 'rb') as fp:
reviews, beers = pickle.load(fp)
random.seed(1337)
random.shuffle(reviews)
logging.info("Loading text sequences...")
text_sequences = [
CharacterSequence.from_string(review.text) for review in reviews
]
text_encoding = OneHotEncoding(include_start_token=True,
include_stop_token=True)
text_encoding.build_encoding(text_sequences)
identity_encoding = IdentityEncoding(1)
logging.info("Loading model...")
ratnet = CharacterRNN('ratnet',
len(text_encoding) + len(identity_encoding),
len(text_encoding),
n_layers=2,
n_hidden=1024)
ratnet.load_parameters(model_dir / 'ratnet1_2-1024.pkl')
ratnet.compile_method('generate_with_concat')
ratnet.compile_method('log_probability')
return ratnet, text_encoding
with open('data/beer/beer_top-train.pkl', 'rb') as fp:
reviews, beers = pickle.load(fp)
text_sequences = [CharacterSequence.from_string(review.text) for review in reviews]
beer_cats = [SingletonSequence(review.beer.style) for review in reviews]
review_num_seqs = [c.encode(text_encoding) for c in text_sequences]
num_seq = NumberSequence(np.concatenate([c.seq for c in review_num_seqs]))
beer_seq = NumberSequence(np.concatenate([c.encode(cat_encoding).replicate(len(r)).seq for c, r in
zip(beer_cats, review_num_seqs)]))
batcher = WindowedBatcher([num_seq, beer_seq], [text_encoding, cat_encoding],
sequence_length=200, batch_size=256)
catnet = CharacterRNN('2pac', len(text_encoding) + len(cat_encoding),
len(text_encoding), n_layers=2, n_hidden=1024)
catnet.compile_method("generate_with_concat")
def load_charnet():
catnet.load_parameters('models/charnet-top_2-1024-2.pkl')
layer = catnet.lstm.input_layer
weights = {
'W_ix': layer.get_parameter_value("W_ix"),
'W_ox': layer.get_parameter_value("W_ox"),
'W_fx': layer.get_parameter_value("W_fx"),
'W_gx': layer.get_parameter_value("W_gx"),
}
for w, value in weights.items():
layer.set_parameter_value(w, np.vstack([value,
c.replicate(len(r)).seq for c, r in zip(beer_ratings, review_num_seqs)
]))
# batcher = WindowedBatcher(num_seq, [text_encoding, style_encoding], sequence_length=200, batch_size=500)
batcher = WindowedBatcher([num_seq, beer_seq],
[text_encoding, identity_encoding],
sequence_length=200,
batch_size=500)
# batcher = WindowedBatcher(num_seq, [text_encoding], sequence_length=200, batch_size=500)
D = text_encoding.index
# charrnn = CharacterRNN('2pac', len(text_encoding) + len(style_encoding), len(text_encoding), n_layers=2, n_hidden=512)
# charrnn = CharacterRNN('2pac', len(text_encoding), len(text_encoding), n_layers=2, n_hidden=1024)
charrnn = CharacterRNN('2pac',
len(text_encoding) + len(identity_encoding),
len(text_encoding),
n_layers=2,
n_hidden=512)
# charrnn.compile_method('generate')
# sgd = SGD(charrnn)
# rmsprop = RMSProp(charrnn)
# mom = Momentum(charrnn)
def train(optimizer, n_iterations, *args):
state = None
for i in xrange(n_iterations):
X, y = batcher.next_batch()
if state is None:
state = np.zeros((X.shape[1], charrnn.n_layers, charrnn.n_hidden))
