def run_tag_sentences(self, tag_tree_path, sentences_market_path, tags_path, untag_sentence_path) :
file_operator = TextFileOperator()
sentences = [u'技能贴 | 黑色打底裤的10种正确穿搭方式', u'春季男鞋韩版潮流行英伦男士休闲鞋']
cmd_list = file_operator.reading(tag_tree_path)
tag_tree = TagTree(cmd_list)
robot = Robot()
tags, untag_sentences = robot.tag_sentences(tag_tree, sentences[0:1000])
print 'finish'
def run_robot(self, tag_tree_path, sentences_market_path, tags_path) :
robot = Robot()
loader = PickleMarket()
file_operator = TextFileOperator()
cmd_list = file_operator.reading(tag_tree_path)
tag_tree = TagTree(cmd_list)
sentences = loader.load_market(sentences_market_path)
tags = loader.load_market(tags_path)
print 'start'
string = raw_input().decode('gb18030')
# string = u'我想要毛衣'
sentences = robot.question_and_answer(string, sentences, tags, tag_tree)
def run_tag_sentences(self, tag_tree_path, sentences_market_path, tags_martket_path, dict_market_path) :
file_operator = TextFileOperator()
loader = PickleMarket()
sentences = loader.load_market(sentences_market_path)
cmd_list = file_operator.reading(tag_tree_path)
tag_tree = TagTree(cmd_list)
robot = Robot()
tags, tags_show, untag_sentences = robot.tag_sentences(tag_tree, sentences[0:])
loader = JsonMarket()
loader.dump_market(tags, tags_martket_path)
loader.dump_market(tag_tree.dict_tuple, dict_market_path)
print '%.2f%% article >= 1 tags, number is, %d.' \
% (100.0 * len([tag for tag in tags_show if len(tag) >= 1]) / len(sentences)) \
% len([tag for tag in tags_show if len(tag) >= 1])
def run_test(self, tag_tree_path, sentences_market_path, tags_path, \
tags_martket_path, untag_sentence_path) :
file_operator = TextFileOperator()
loader = PickleMarket()
sentences = loader.load_market(sentences_market_path)
cmd_list = file_operator.reading(tag_tree_path)
tag_tree = TagTree(cmd_list)
robot = Robot()
tags, tags_show, untag_sentences = robot.tag_sentences(tag_tree, sentences[0:])
loader = JsonMarket()
self.write_tags(sentences, tags_show, tags_path)
loader.dump_market(tags, tags_martket_path)
file_operator.writing(untag_sentences, untag_sentence_path)
# loader.dump_market(untag_sentences, sentences_market_path)
# print '%.2f%% article >= 2 tags' % (100.0 * len([tag for tag in tags_show if len(tag) >= 1]) / len(sentences))
print '%.2f%% article >= 3 tags' % (100.0 * len([tag for tag in tags_show if len(tag) >= 1]) / len(sentences))
