def __init__(self,batch,train_kbest = None,train_gold = None,dev_kbest = None,dev_gold = None,
test_kbest = None,test_gold = None,vocab_path = None):
self.vocab = None
self.train_kbest = train_kbest
self.train_gold = train_gold
self.dev_kbest = dev_kbest
self.dev_gold = dev_gold
self.batch = batch
self.test_kbest = test_kbest
self.test_gold = test_gold
if os.path.exists(vocab_path):
print 'load vocab'
self.max_degree,self.vocab = data_util.load_dict(vocab_path)
else:
print 'creat vocab'
self.vocab = Vocab.Vocab(self.train_gold)
print 'get max_degree'
self.max_degree = self.get_max_degree()
print 'save dictionary'
data_util.save_dict(self.vocab,self.max_degree, vocab_path)
print 'vocab size:' + str(self.vocab.size())
print 'max_degree' + str(self.max_degree)
print 'get dev data'
self.dev_data = dev_reader.read_dev(dev_kbest,dev_gold,self.vocab)
print 'number of dev:'+str(len(self.dev_data))
#self.test_data = dev_reader.read_dev(test_kbest,test_gold,self.vocab)
# print 'create train batch'
# self.train_iter = train_iterator.train_iterator(train_kbest,train_gold,self.vocab,self.batch)
print 'get train data'
self.train_data = dev_reader.read_dev(train_kbest,train_gold,self.vocab)
print 'number of train:'+str(len(self.train_data))
def test_model():
max_degree, vocab = data_util.load_dict(os.path.join(DIR, OUTPUT_DICT))
dev_data = dev_reader.read_dev(os.path.join(DIR, DEV + '.kbest'),
os.path.join(DIR, DEV + '.gold'), vocab)
test_data = dev_reader.read_dev(os.path.join(DIR, TEST + '.kbest'),
os.path.join(DIR, TEST + '.gold'), vocab)
print 'model file name %s' % OUTPUT_MODEL
print 'build model'
#model = dependency_model.get_model(vocab.size(),vocab.tagsize(),max_degree,PAIR_WISE)
print 'load params'
#model.set_parmas(os.path.join(DIR,OUTPUT_MODEL))
model = 0
max = 0
max_r = 0
for i in range(200):
if PAIR_WISE:
res = evaluate_dataset_pair(model, dev_data, True, ratio=0.005 * i)
else:
res = evaluate_dataset_point(model,
dev_data,
True,
ratio=0.005 * i)
if res[0] > max:
max = res[0]
max_r = 0.005 * i
print max_r, max
def test_model():
max_degree,vocab = data_util.load_dict(os.path.join(DIR,OUTPUT_DICT))
dev_data = dev_reader.read_dev(os.path.join(DIR, DEV + '.kbest'),
os.path.join(DIR, DEV + '.gold'), vocab)
test_data = dev_reader.read_dev(os.path.join(DIR, TEST + '.kbest'),
os.path.join(DIR, TEST + '.gold'), vocab)
print 'build model'
model = dependency_model.get_model(vocab.size(), max_degree)
print 'load params'
model.set_parmas(os.path.join(DIR,OUTPUT_MODEL))
print 'addbase'
max = 0
for i in range(200):
res = evaluate_dataset(model,dev_data,True,ratio=0.005*i)
if res[0]>max:
max = res[0]
def test_model():
max_degree,vocab = data_util.load_dict(os.path.join(DIR, OUTPUT_DICT))
dev_data = dev_reader.read_dev(os.path.join(DIR, DEV + '.kbest'),
os.path.join(DIR, DEV + '.gold'), vocab)
# test_data = dev_reader.read_dev(os.path.join(DIR, TEST + '.kbest'),
# os.path.join(DIR, TEST + '.gold'), vocab)
#evaluate_oracle_worst(test_data)
evaluate_baseline_random(dev_data)
evaluate_oracle_worst(dev_data)
print 'build model'
model = dependency_model.get_model(vocab.size(),vocab.tagsize(), max_degree,PAIR_WISE)
print 'load params'
model.set_parmas(os.path.join(DIR,OUTPUT_MODEL))
if model.Pairwise:
evaluate_dataset_pair(model,dev_data)
else:
evaluate_dataset_point(model, dev_data,False)
def test_model():
max_degree,vocab = data_util.load_dict(os.path.join(DIR,OUTPUT_DICT))
dev_data = dev_reader.read_dev(os.path.join(DIR, DEV + '.kbest'),
os.path.join(DIR, DEV + '.gold'), vocab)
# test_data = dev_reader.read_dev(os.path.join(DIR, TEST + '.kbest'),
# os.path.join(DIR, TEST + '.gold'), vocab)
#evaluate_oracle_worst(test_data)
evaluate_oracle_worst(dev_data)
print 'build model'
model = dependency_model.get_model(vocab.size(), max_degree)
print 'load params'
model.set_parmas(os.path.join(DIR,OUTPUT_MODEL))
print 'addbase'
evaluate_dataset(model,dev_data,True)
#evaluate_dataset(model, test_data, True)
print 'withoutbase'
evaluate_dataset(model,dev_data,False)
import dev_reader
import os
import parser_test
DIR = 'd:\\MacShare\\32best\\'
TRAIN = 'train'
DEV = 'dev32'
TEST = 'test32'
if __name__ == '__main__':
test_data = dev_reader.read_dev(os.path.join(DIR, DEV + '.kbest'),
os.path.join(DIR, DEV + '.gold'), None)
parser_test.evaluate_oracle_worst(test_data)
test_data = dev_reader.read_dev(os.path.join(DIR, TEST + '.kbest'),
os.path.join(DIR, TEST + '.gold'), None)
parser_test.evaluate_oracle_worst(test_data)