'lbranch': LBranch,
'upcfg': UPCFG
}
if __name__ == '__main__':
opts = docopt(__doc__)
print('Loading corpus ...')
PATH = "./../../ancora-3.0.1es"
files = 'CESS-CAST-(A|AA|P)/.*\.tbf\.xml'
corpus = SimpleAncoraCorpusReader(PATH, files)
print('Training model ...')
# x = list(corpus.parsed_sents())[:10]
m = opts['-m'] # Modelo Elegido
n = opts['-n'] # Orden Markovizacion Horizontal
if (n is not None) and (m == "upcfg"):
model = models[opts['-m']](corpus.parsed_sents(), horzMarkov=int(n))
else:
model = models[opts['-m']](corpus.parsed_sents())
# model = models[opts['-m']](corpus.parsed_sents())
# x = corpus.parsed_sents()
# model = models[opts['-m']](x)
print('Saving ...')
filename = opts['-o']
f = open(filename, 'wb')
pickle.dump(model, f)
f.close()
'lbranch': LBranch,
'upcfg': UPCFG
}
if __name__ == '__main__':
opts = docopt(__doc__)
print('\nLoading corpus...')
files = 'CESS-CAST-(A|AA|P)/.*\.tbf\.xml'
corpus = SimpleAncoraCorpusReader('corpus/ancora-2.0/', files)
print('Training model...')
om, on = opts['-m'], opts['-n']
if om == 'upcfg':
n = None if on is None else int(on)
print('UPCFG model selected n={}.'.format(n))
model = models[om](corpus.parsed_sents(), horzMarkov=n)
elif om in ['flat', 'rbranch', 'lbranch']:
print(om + ' model selected.')
model = models[om](corpus.parsed_sents())
else:
print('Bad model type.')
exit()
print('Saving...\n')
filename = opts['-o']
f = open(filename, 'wb')
pickle.dump(model, f)
f.close()
sys.stdout.flush()
if __name__ == '__main__':
opts = docopt(__doc__)
print('Loading model...')
filename = opts['-i']
f = open(filename, 'rb')
model = pickle.load(f)
f.close()
print('Loading corpus...')
files = '3LB-CAST/.*\.tbf\.xml'
corpus = SimpleAncoraCorpusReader('ancora/ancora-2.0/', files)
parsed_sents = list(corpus.parsed_sents())
print('Parsing...')
hits, total_gold, total_model = 0, 0, 0
n = len(parsed_sents)
format_str = '{:3.1f}% ({}/{}) (P={:2.2f}%, R={:2.2f}%, F1={:2.2f}%)'
progress(format_str.format(0.0, 0, n, 0.0, 0.0, 0.0))
for i, gold_parsed_sent in enumerate(parsed_sents):
tagged_sent = gold_parsed_sent.pos()
# parse
model_parsed_sent = model.parse(tagged_sent)
# compute labeled scores
gold_spans = spans(gold_parsed_sent, unary=False)
model_spans = spans(model_parsed_sent, unary=False)
from docopt import docopt
import pickle
from corpus.ancora import SimpleAncoraCorpusReader
from parsing.baselines import Flat, RBranch, LBranch
models = {
'flat': Flat,
'rbranch': RBranch,
'lbranch': LBranch,
}
if __name__ == '__main__':
opts = docopt(__doc__)
print('Loading corpus...')
files = 'CESS-CAST-(A|AA|P)/.*\.tbf\.xml'
corpus = SimpleAncoraCorpusReader('ancora/ancora-2.0/', files)
print('Training model...')
model = models[opts['-m']](corpus.parsed_sents())
print('Saving...')
filename = opts['-o']
f = open(filename, 'wb')
pickle.dump(model, f)
f.close()
