parser.add_argument('output', help='output file')
options = parser.parse_args()
phrases_file = options.phrases
word_vector_file = options.word_vector_file
theta_file = options.theta
output_file = options.output
print >> stderr, 'load word vectors...'
word_vectors = WordVectors.load_vectors(word_vector_file)
embsize = word_vectors.embsize()
# print "embsize: ",embsize
# print "theta file: ",theta_file
print >> stderr, 'load RAE parameters...'
theta = unpickle(theta_file)
rae = RecursiveAutoencoder.build(theta, embsize)
total_cost = 0
total_instance_num = 0
total_internal_node_num = 0
print '='*63
print '%20s %20s %20s' % ('all', 'avg/node', 'internal node')
print '-'*63
with Reader(phrases_file) as reader, Writer(output_file) as writer:
for phrase in reader:
instance = Instance.parse_from_str(phrase, word_vectors)
words_embedded = word_vectors[instance.words]
root_node, cost = rae.forward(words_embedded)
print >> stderr, 'lambda_reg_sem: %20.18f' % lambda_reg_sem
print >> stderr, 'alpha: %20.18f' % alpha
print >> stderr, 'Max iterations_la: %d' % maxiter_la
if _seed:
print >> stderr, 'Random seed: %s' % _seed
print >> stderr, ''
print >> stderr, 'load word vectors...'
# 载入词向量的输入放入word_vectors中
src_word_vectors = WordVectors.load_vectors( src_word_vector_file )
trg_word_vectors = WordVectors.load_vectors( trg_word_vector_file )
#embsize为词向量的维度
src_embsize = src_word_vectors.embsize()
trg_embsize = trg_word_vectors.embsize()
src_theta_opt = unpickle( src_theta_file )
trg_theta_opt = unpickle( trg_theta_file )
theta_opt = []
theta_opt.extend( src_theta_opt )
theta_opt.extend( trg_theta_opt )
src_instances, _, src_total_internal_node, bad_src_instances,\
trg_instances, _, trg_total_internal_node, bad_trg_instances\
= prepare_data_la( src_word_vectors, src_instances_file,\
trg_word_vectors, trg_instances_file )
timer = Timer()
timer.tic()
if _seed != None:
_seed = int(_seed)
else:
parser.add_argument('word_vector_file', help='word vector file')
parser.add_argument('theta', help='RAE parameter file (pickled)')
parser.add_argument('output', help='output file')
options = parser.parse_args()
phrases_file = options.phrases
word_vector_file = options.word_vector_file
theta_file = options.theta
output_file = options.output
print >> stderr, 'load word vectors...'
word_vectors = WordVectors.load_vectors(word_vector_file)
embsize = word_vectors.embsize()
print >> stderr, 'load RAE parameters...'
theta = unpickle(theta_file)
rae = RecursiveAutoencoder.build(theta, embsize)
total_cost = 0
total_instance_num = 0
total_internal_node_num = 0
print '=' * 63
print '%20s %20s %20s' % ('all', 'avg/node', 'internal node')
print '-' * 63
with Reader(phrases_file) as reader, Writer(output_file) as writer:
for phrase in reader:
instance = Instance.parse_from_str(phrase, word_vectors)
words_embedded = word_vectors[instance.words]
root_node, cost = rae.forward(words_embedded)