Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

bug fix: fix illegal multibyte sequence #42

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

bug fix: fix illegal multibyte sequence #42

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions build_medicalgraph.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ def read_nodes(self):


count = 0
for data in open(self.data_path):
for data in open(self.data_path, encoding='utf-8'):
disease_dict = {}
count += 1
print(count)
Expand Down Expand Up @@ -237,13 +237,13 @@ def create_relationship(self, start_node, end_node, edges, rel_type, rel_name):
'''导出数据'''
def export_data(self):
Drugs, Foods, Checks, Departments, Producers, Symptoms, Diseases, disease_infos, rels_check, rels_recommandeat, rels_noteat, rels_doeat, rels_department, rels_commonddrug, rels_drug_producer, rels_recommanddrug, rels_symptom, rels_acompany, rels_category = self.read_nodes()
f_drug = open('drug.txt', 'w+')
f_food = open('food.txt', 'w+')
f_check = open('check.txt', 'w+')
f_department = open('department.txt', 'w+')
f_producer = open('producer.txt', 'w+')
f_symptom = open('symptoms.txt', 'w+')
f_disease = open('disease.txt', 'w+')
f_drug = open('drug.txt', 'w+', encoding='utf-8')
f_food = open('food.txt', 'w+', encoding='utf-8')
f_check = open('check.txt', 'w+', encoding='utf-8')
f_department = open('department.txt', 'w+', encoding='utf-8')
f_producer = open('producer.txt', 'w+', encoding='utf-8')
f_symptom = open('symptoms.txt', 'w+', encoding='utf-8')
f_disease = open('disease.txt', 'w+', encoding='utf-8')

f_drug.write('\n'.join(list(Drugs)))
f_food.write('\n'.join(list(Foods)))
Expand Down
16 changes: 8 additions & 8 deletions question_classifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,15 +20,15 @@ def __init__(self):
self.symptom_path = os.path.join(cur_dir, 'dict/symptom.txt')
self.deny_path = os.path.join(cur_dir, 'dict/deny.txt')
# 加载特征词
self.disease_wds= [i.strip() for i in open(self.disease_path) if i.strip()]
self.department_wds= [i.strip() for i in open(self.department_path) if i.strip()]
self.check_wds= [i.strip() for i in open(self.check_path) if i.strip()]
self.drug_wds= [i.strip() for i in open(self.drug_path) if i.strip()]
self.food_wds= [i.strip() for i in open(self.food_path) if i.strip()]
self.producer_wds= [i.strip() for i in open(self.producer_path) if i.strip()]
self.symptom_wds= [i.strip() for i in open(self.symptom_path) if i.strip()]
self.disease_wds= [i.strip() for i in open(self.disease_path, encoding='utf-8') if i.strip()]
self.department_wds= [i.strip() for i in open(self.department_path, encoding='utf-8') if i.strip()]
self.check_wds= [i.strip() for i in open(self.check_path, encoding='utf-8') if i.strip()]
self.drug_wds= [i.strip() for i in open(self.drug_path, encoding='utf-8') if i.strip()]
self.food_wds= [i.strip() for i in open(self.food_path, encoding='utf-8') if i.strip()]
self.producer_wds= [i.strip() for i in open(self.producer_path, encoding='utf-8') if i.strip()]
self.symptom_wds= [i.strip() for i in open(self.symptom_path, encoding='utf-8') if i.strip()]
self.region_words = set(self.department_wds + self.disease_wds + self.check_wds + self.drug_wds + self.food_wds + self.producer_wds + self.symptom_wds)
self.deny_words = [i.strip() for i in open(self.deny_path) if i.strip()]
self.deny_words = [i.strip() for i in open(self.deny_path, encoding='utf-8') if i.strip()]
# 构造领域actree
self.region_tree = self.build_actree(list(self.region_words))
# 构建词典
Expand Down