def evaluate(self , gold_path , predict_path) :
gold_ite = DatasetHandler.read_dev_data(gold_path)
predict_ite = DatasetHandler.read_dev_data(predict_path)
nr_processing = 0
nr_gold = 0
nr_processing_right = 0
nr_line = 0
while True :
try :
gold_instance = gold_ite.next()
predict_instance = predict_ite.next()
except StopIteration :
break
nr_line += 1
gold_unigrams , gold_tags = self._processing_one_segmented_WSAtom_instance2unigrams_and_tags(gold_instance)
predict_unigrams , predict_tags = self._processing_one_segmented_WSAtom_instance2unigrams_and_tags(predict_instance)
gold_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(gold_tags)
predict_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(predict_tags)
cur_nr_gold , cur_nr_processing , cur_nr_processing_right = (
self.__innerfunc_4evaluate_get_nr_gold_and_processing_and_processing_right(gold_coor_seq , predict_coor_seq) )
nr_gold += cur_nr_gold
nr_processing += cur_nr_processing
nr_processing_right += cur_nr_processing_right
p , r , f = self.__innerfunc_4evaluate_calculate_prf(nr_gold , nr_processing , nr_processing_right)
print ("Eval result :\np : %.2f%% r : %.2f%% f : %.2f%%\n"
"line num : %d total word num : %d total predict word num : %d predict right num : %d ") %(
p * 100 , r * 100, f * 100 , nr_line , nr_gold , nr_processing , nr_processing_right
)
def _4training_evaluate_processing(self, dev_path):
nr_processing_right = 0
nr_gold = 0
nr_processing = 0
for instance in DatasetHandler.read_dev_data(dev_path):
unigrams, gold_tags = Segmentor._processing_one_segmented_WSAtom_instance2unigrams_and_tags(
instance)
predict_tags = Decoder.decode_for_predict(self.extractor,
self.model,
self.constrain, unigrams)
gold_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(
gold_tags)
predict_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(
predict_tags)
cur_nr_gold, cur_nr_processing, cur_nr_processing_right = (
self.
__innerfunc_4evaluate_get_nr_gold_and_processing_and_processing_right(
gold_coor_seq, predict_coor_seq))
nr_gold += cur_nr_gold
nr_processing += cur_nr_processing
nr_processing_right += cur_nr_processing_right
p, r, f = self.__innerfunc_4evaluate_calculate_prf(
nr_gold, nr_processing, nr_processing_right)
print >> sys.stderr, (
"Eval result :\np : %.2f%% r : %.2f%% f : %.2f%%\n"
"total word num : %d total predict word num : %d predict right num : %d "
) % (p * 100, r * 100, f * 100, nr_gold, nr_processing,
nr_processing_right)
return f
def evaluate(self, gold_path, predict_path):
gold_ite = DatasetHandler.read_dev_data(gold_path)
predict_ite = DatasetHandler.read_dev_data(predict_path)
nr_processing = 0
nr_gold = 0
nr_processing_right = 0
nr_line = 0
while True:
try:
gold_instance = gold_ite.next()
predict_instance = predict_ite.next()
except StopIteration:
break
nr_line += 1
gold_unigrams, gold_tags = self._processing_one_segmented_WSAtom_instance2unigrams_and_tags(
gold_instance)
predict_unigrams, predict_tags = self._processing_one_segmented_WSAtom_instance2unigrams_and_tags(
predict_instance)
gold_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(
gold_tags)
predict_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(
predict_tags)
cur_nr_gold, cur_nr_processing, cur_nr_processing_right = (
self.
__innerfunc_4evaluate_get_nr_gold_and_processing_and_processing_right(
gold_coor_seq, predict_coor_seq))
nr_gold += cur_nr_gold
nr_processing += cur_nr_processing
nr_processing_right += cur_nr_processing_right
p, r, f = self.__innerfunc_4evaluate_calculate_prf(
nr_gold, nr_processing, nr_processing_right)
print(
"Eval result :\np : %.2f%% r : %.2f%% f : %.2f%%\n"
"line num : %d total word num : %d total predict word num : %d predict right num : %d "
) % (p * 100, r * 100, f * 100, nr_line, nr_gold, nr_processing,
nr_processing_right)
def _4training_evaluate_processing(self , dev_path) :
nr_processing_right = 0
nr_gold = 0
nr_processing = 0
for instance in DatasetHandler.read_dev_data(dev_path) :
unigrams , gold_tags = Segmentor._processing_one_segmented_WSAtom_instance2unigrams_and_tags(instance)
predict_tags = Decoder.decode_for_predict(self.extractor , self.model , self.constrain , unigrams)
gold_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(gold_tags)
predict_coor_seq = self.__innerfunc_4evaluate_generate_word_coordinate_sequence_from_tags(predict_tags)
cur_nr_gold , cur_nr_processing , cur_nr_processing_right = (
self.__innerfunc_4evaluate_get_nr_gold_and_processing_and_processing_right(gold_coor_seq , predict_coor_seq)
)
nr_gold += cur_nr_gold
nr_processing += cur_nr_processing
nr_processing_right += cur_nr_processing_right
p , r , f = self.__innerfunc_4evaluate_calculate_prf(nr_gold , nr_processing , nr_processing_right)
print >>sys.stderr , ("Eval result :\np : %.2f%% r : %.2f%% f : %.2f%%\n"
"total word num : %d total predict word num : %d predict right num : %d ")%(
p * 100 , r * 100, f * 100 , nr_gold , nr_processing , nr_processing_right
)
return f