reduce(lambda x, y: list(x) + list(y),
train_lex + valid_lex + test_lex)))
num_classes = len(
set(reduce(lambda x, y: list(x) + list(y),
train_y + valid_y + test_y)))
num_sentences = len(train_lex)
# instantiate the model
numpy.random.seed(s['seed'])
random.seed(s['seed'])
if rnn_type == "elman":
rnn = elman.model(nh=s['nhidden'],
nc=num_classes,
ne=voc_size,
de=s['emb_dimension'],
cs=s['win'],
em=dataset["embeddings"],
init=initialize,
featdim=14)
elif rnn_type == "jordan":
rnn = jordan.model(nh=s['nhidden'],
nc=num_classes,
ne=voc_size,
de=s['emb_dimension'],
cs=s['win'],
em=dataset["embeddings"],
init=initialize)
elif rnn_type == "elman_M1":
rnn = elman_M1.model(nh=s['nhidden'],
assert len(test_feat) == len(test_lex) == len(test_y)
assert len(valid_feat) == len(valid_lex) == len(valid_y)
voc_size = len(set(reduce(lambda x, y: list(x) + list(y), train_lex + valid_lex + test_lex)))
num_classes = len(set(reduce(lambda x, y: list(x) + list(y), train_y + valid_y + test_y)))
num_sentences = len(train_lex)
# instantiate the model
numpy.random.seed(s['seed'])
random.seed(s['seed'])
if rnn_type == "elman":
rnn = elman.model(nh=s['nhidden'],
nc=num_classes,
ne=voc_size,
de=s['emb_dimension'],
cs=s['win'],
em=dataset["embeddings"],
init=initialize,
featdim=14)
elif rnn_type == "jordan":
rnn = jordan.model(nh=s['nhidden'],
nc=num_classes,
ne=voc_size,
de=s['emb_dimension'],
cs=s['win'],
em=dataset["embeddings"],
init=initialize)
else:
print "Invalid RNN type: ", rnn_type
sys.exit(-1)
idx2word = dict((k,v) for v,k in dic['words2idx'].items())
train_lex, train_ne, train_y = train_set
valid_lex, valid_ne, valid_y = valid_set
test_lex, test_ne, test_y = test_set
vocsize = len(dic['words2idx'])
nclasses = len(dic['labels2idx'])
nsentences = len(train_lex)
# instanciate the model
numpy.random.seed(s['seed'])
random.seed(s['seed'])
rnn = model( nh = s['nhidden'],
nc = nclasses,
ne = vocsize,
de = s['emb_dimension'],
cs = s['win'] )
# train with early stopping on validation set
best_f1 = -numpy.inf
s['clr'] = s['lr']
for e in range(s['nepochs']):
# shuffle
shuffle([train_lex, train_ne, train_y], s['seed'])
s['ce'] = e
tic = time.time()
for i in range(nsentences):
cwords = contextwin(train_lex[i], s['win'])
words = map(lambda x: numpy.asarray(x).astype('int32'),\
minibatch(cwords, s['bs']))
vocsize = len(set(reduce(\
lambda x, y: list(x)+list(y),\
train_lex+valid_lex+test_lex)))
nclasses = len(set(reduce(\
lambda x, y: list(x)+list(y),\
train_y+test_y+valid_y)))
nsentences = len(train_lex)
# instanciate the model
numpy.random.seed(s['seed'])
random.seed(s['seed'])
rnn = model( nh = s['nhidden'],
nc = nclasses,
ne = vocsize,
de = s['emb_dimension'],
cs = s['win'] )
# train with early stopping on validation set
best_f1 = -numpy.inf
s['clr'] = s['lr']
for e in xrange(s['nepochs']):
# shuffle
shuffle([train_lex, train_ne, train_y], s['seed'])
s['ce'] = e
tic = time.time()
for i in xrange(nsentences):
cwords = contextwin(train_lex[i], s['win'])
words = map(lambda x: numpy.asarray(x).astype('int32'),\
minibatch(cwords, s['bs']))