def main():
if len(sys.argv) != 2:
print('usage: python postagger-runner.py model-prefix < input > output', file=sys.stderr)
return
model_prefix = sys.argv[1]
# load dictionary
word_ids = Dictionary.load(model_prefix + '.wordid')
pos_ids = Dictionary.load(model_prefix + '.posid')
# load and test tagger
tagger = POSTagger.load(model_prefix)
# output queue
qs = []
wss = []
# input iterator
def iterate_words():
for l in sys.stdin:
ls = l.strip('\n').split(' ')
wss.append(ls)
for w in ls:
yield word_ids[w]
for w, p in tagger.iterate(iterate_words()):
qs.append(pos_ids.get_name(p))
if len(qs) >= len(wss[0]):
print(' '.join('%s/%s' % wq for wq in zip(wss[0], qs)))
sys.stdout.flush()
qs = []
wss.pop(0)
def main():
if len(sys.argv) != 3:
print('usage: python postagger-test.py', file=sys.stderr)
print(' <str: test prefix>', file=sys.stderr)
print(' <str: model prefix>', file=sys.stderr)
return
test_prefix = sys.argv[1]
model_prefix = sys.argv[2]
print('loading data ...', file=sys.stderr)
# load test data
test_words = [w.lower() for w in utils.read_data(test_prefix + '.words')]
test_pos = utils.read_data(test_prefix + '.pos')
# load dictionary
word_ids = Dictionary.load(model_prefix + '.wordid')
pos_ids = Dictionary.load(model_prefix + '.posid')
# make word/POS IDs
test_wids = [word_ids[w] for w in test_words]
test_pids = [pos_ids[w] for w in test_pos]
# load and test tagger
tagger = POSTagger.load(model_prefix)
tagger.test(test_wids, test_pids)
def main():
if len(sys.argv) != 9:
print('usage: python postagger-train.py', file=sys.stderr)
print(' <str: train prefix>', file=sys.stderr)
print(' <str: dev prefix>', file=sys.stderr)
print(' <str: model prefix>', file=sys.stderr)
print(' <int: word n-gram size>', file=sys.stderr)
print(' <int: POS n-gram size>', file=sys.stderr)
print(' <int: word window size>', file=sys.stderr)
print(' <int: POS history size>', file=sys.stderr)
print(' <int: max iteration>', file=sys.stderr)
return
train_prefix = sys.argv[1]
dev_prefix = sys.argv[2]
model_prefix = sys.argv[3]
word_ngram_size = int(sys.argv[4])
pos_ngram_size = int(sys.argv[5])
word_window_size = int(sys.argv[6])
pos_history_size = int(sys.argv[7])
max_iteration = int(sys.argv[8])
print('loading data ...', file=sys.stderr)
# load train/dev data
train_words = [w.lower() for w in utils.read_data(train_prefix + '.words')]
train_pos = utils.read_data(train_prefix + '.pos')
dev_words = [w.lower() for w in utils.read_data(dev_prefix + '.words')]
dev_pos = utils.read_data(dev_prefix + '.pos')
# make dictionary
word_ids = Dictionary(train_words, frozen=True)
pos_ids = Dictionary(train_pos, frozen=True)
word_ids.save(model_prefix + '.wordid')
pos_ids.save(model_prefix + '.posid')
# make word/POS IDs
train_wids = [word_ids[w] for w in train_words]
train_pids = [pos_ids[w] for w in train_pos]
dev_wids = [word_ids[w] for w in dev_words]
dev_pids = [pos_ids[w] for w in dev_pos]
# train
tagger = POSTagger(word_ngram_size, pos_ngram_size, word_window_size, pos_history_size)
tagger.train(len(pos_ids), train_wids, train_pids, dev_wids, dev_pids, max_iteration, model_prefix)
