def _get_pretrain_model():
pos_tagger = PerceptronTagger(load=False)
pos_tagger.train(sentences=train_sents, save_loc=PICKLE)
print('Accuracy : ', pos_tagger.evaluate(test_sents))
ret, tags, err = pipe_through_prog(prog, ' '.join(tokens))
return tags
def tag_sents(self, sentences):
text = []
for s in sentences:
text.append(' '.join(s))
return self.tag(text)
def evaluate(self, gold):
tagged_sents = self.tag_sents(untag(sent) for sent in gold)
gold_tokens = list(itertools.chain(*gold))
return accuracy(gold_tokens, tagged_sents)
if __name__ == '__main__':
sents = treebank.tagged_sents()
PT = PerceptronTagger()
now = time.time()
PT.tag_sents(untag(sent) for sent in sents)
pt_time = time.time() - now
headers = ['Library', 'Accuracy', 'Time (sec)']
table = [['NLTK', round(PT.evaluate(sents), 3),
round(pt_time, 3)],
[
'Prose',
round(APTagger().evaluate(sents), 3),
round(AP_TIME, 3)
]]
print(tabulate(table, headers, tablefmt='pipe'))
gold_tokens = list(itertools.chain(*gold))
print(json.dumps(gold_tokens))
print(len(tagged_sents), len(gold_tokens))
return accuracy(gold_tokens, tagged_sents)
if __name__ == '__main__':
sents = treebank.tagged_sents()
PT = PerceptronTagger()
print("Timing NLTK ...")
pt_times = []
for _ in range(5):
now = time.time()
PT.tag_sents(untag(sent) for sent in sents)
pt_times.append(time.time() - now)
pt_time = round(sum(pt_times) / len(pt_times), 3)
'''NOTE: Moved to tag_test.go
print("Timing prose ...")
acc = round(APTagger().evaluate(sents), 3)
ap_time = round(sum(AP_TIME) / len(AP_TIME), 3)
'''
print("Evaluating accuracy ...")
headers = ['Library', 'Accuracy', '5-Run Average (sec)']
table = [
['NLTK', round(PT.evaluate(sents), 3), pt_time],
# ['`prose`', acc, ap_time]
]
print(tabulate(table, headers, tablefmt='pipe'))
import cowparser as cp
train_sents = []
test_sents = []
gen = cp.sentences_for_dir(separate=False)
for i, (metadata, data) in enumerate(gen):
train_sents.append([(a,b) for a,b,c in data])
if i == 2000000:
break
for i, (metadata, data) in enumerate(gen):
test_sents.append([(a,b) for a,b,c in data])
if i == 5000:
break
from nltk.tag.perceptron import PerceptronTagger
pt = PerceptronTagger(load=False)
pt.train(train_sents,'model2.perc.dutch_tagger')
print(pt.evaluate(test_sents))
