vocsize = len(words2idx)
nclasses = len(labels2idx)
nsentences = len(test_lex)
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'] )
rnn.load(folder)
#select a few popular words show, me, movies, what, in
#w_idx = word2idx['show'];
#print w_idx
#w_emb = rnn.emb[w_idx]
#print w_emb
#word->index->emb
#find n nearest embeddings
#emb->index->word
predictions_test = [ map(lambda x: idx2label[x], \
rnn.classify(numpy.asarray(contextwin(x, s['win'])).astype('int32')))\
for x in test_lex ]
groundtruth_test = [ map(lambda x: idx2label[x], y) for y in test_y ]
words_test = [ map(lambda x: idx2word[x], w) for w in test_lex]
res_test = conlleval(predictions_test, groundtruth_test, words_test, sys.argv[6])
#print 'Test set performance -- F1: ', res_test['f1'], ' '*20
print res_test['a'],' ',res_test['p'],' ',res_test['r'],' ',res_test['f1'],' '
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_y], s['seed'])
s['ce'] = e
tic = time.time()
total_cost = 0
count = 0
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']))
labels = train_y[i]
for word_batch , label_last_word in zip(words, labels):
total_cost += rnn.train(word_batch, label_last_word, s['clr'])
count +=1
rnn.normalize()
if s['verbose']:
print '[learning] epoch %i >> %2.2f%%'%(e,(i+1)*100./nsentences),'completed in %.2f (sec) <<\r'%(time.time()-tic),
sys.stdout.flush()
print ''
print 'Learning rate: %2.4f'%(s['clr'])
print 'Average Training Cost: %2.4f'%(total_cost/count)
predictions_valid = [ map(lambda x: idx2label[x], \
