# eachFolder = folder + "\\" + str(e)
# os.mkdir(eachFolder)
# rnn.save(eachFolder)
# """修改于2015/4/3"""
# words = numpy.asarray(cwords).astype("int32")
# labels = train_y[i]
# rnn.train(words, labels, s["clr"])
# print '[learning] epoch %i >> %2.2f%%'%(e,(i+1)*100./nsentences),'completed in %.2f (sec) <<\r'%(time.time()-tic),
# sys.stdout.flush()
# fileTime = time.strftime("%Y-%m-%d",time.localtime(time.time()))
# folder = "..\\paramInfor\\MyRnn(he)\\" + fileTime + os.path.basename(__file__).split('.')[0]
# if not os.path.exists(folder): os.mkdir(folder)
# else:
# folder = folder + "-win5"
# os.mkdir(folder)
# rnn.save(folder)
print " test the model, back into the real world : idx -> words"
preFile = open("myRnn-bio.txt","w")
for x in test_x:
lst = rnn.classify(numpy.asarray(contextwin(x, s['win'])).astype('int32'))
testViterbi = NewViterbi(transMatrix, lst[0].tolist(), intialState)
path = testViterbi.getFianlPath()
predictions_test=map(lambda x: idx2label[x], path)
for eachlag in predictions_test:
preFile.write(eachlag+" ")
preFile.write("\n")
preFile.close()
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']))
labels = train_y[i]
for word_batch, label_last_word in zip(words, labels):
rnn.train(word_batch, label_last_word, s['clr'])
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()
# evaluation // back into the real world : idx -> words
predictions_test = [ map(lambda x: idx2label[x], \
rnn.classify(numpy.asarray(contextwin(x, s['win'])).astype('int32')))\
# for dirpath, dirnames, filenames in os.walk(trainedParams):
# print "Traversal the folder"
# if len(filenames) != 0:
# print "params have been trained, now loading ..."
# rnn.load(trainedParams)
# else:
rnn.load("..\\paramInfor\\Elman(he)\\2015-03-22myElman-forward-3-21")
print "train with early stopping nepochs ..."
s['clr'] = s['lr']
for e in xrange(s['nepochs']):
# shuffle
shuffle([train_x, train_y], s['seed'])
tic = time.time()
for i in xrange(nsentences):
cwords = contextwin(train_x[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):
rnn.train(word_batch, label_last_word, s['clr'])
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()
fileTime = time.strftime("%Y-%m-%d",time.localtime(time.time()))
folder = "..\\paramInfor\\Elman(he)\\" + fileTime + os.path.basename(__file__).split('.')[0]
if not os.path.exists(folder): os.mkdir(folder)
else:
folder = folder + "-win5"
os.mkdir(folder)
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']))
labels = train_y[i]
for word_batch , label_last_word in zip(words, labels):
rnn.train(word_batch, label_last_word, s['clr'])
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()
# evaluation // back into the real world : idx -> words
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 ]
