def loading_none_spliter_rule(self,
feature_list,
label_list,
sen_list=None):
rules = loading_data.load_spliter_rules()
print "Loading rules."
for rule in rules:
if rule[0] == "#":
continue
if rule[0] == "r":
rule = rule[1:]
print "Add a soft regex: %s" % rule
self.feature_model.add_none_spliter_regrex(rule)
continue
elif rule[0] == "h":
rule = rule[1:]
print "Add a hard rule regex: %s" % rule
self.feature_model.add_none_spliter_regrex(rule, True)
continue
idx = 0
for c in rule:
if Feature.is_spliter_candidate(c):
feature, _ = self.feature_model.gen_feature_vector(
rule, idx, is_forced=True)
feature_list.append(feature)
label_list.append(0)
if sen_list != None:
sen_list.append(rule)
idx += 1
def loading_forcing_spliter_rule(self):
rules = loading_data.load_spliter_rules(loading_data.raw_forcing_spliter_path)
for rule in rules:
if rule[0] == "#":
continue
elif rule[0] == "h":
rule = rule[1:]
print "Add a hard forcing rule regex: %s" % rule
self.feature_model.add_forcing_splitter_regrex(rule)
def load_custom_hard_rule(self, path):
rules = loading_data.load_spliter_rules(path)
for rule in rules:
if rule[0] == "#":
continue
elif rule[0] == "h":
rule = rule[1:]
print "Add a hard rule regex: %s" % rule
self.feature_model.add_none_spliter_regrex(rule, True)
continue