上接菜哥学知识图谱(通过“基于医疗知识图谱的问答系统”)(三)(代码分析)
6.build_medicalgraph.py # 将结构化json数据导入neo4j
create_graphnodes()方法创建节点,create_graphrels()创建边
#!/usr/bin/env python3
# coding: utf-8
# File: MedicalGraph.py
# Author: lhy<lhy_in_blcu@126.com,https://huangyong.github.io>
# Date: 18-10-3
import os
import json
from py2neo import Graph,Node
class MedicalGraph:
def __init__(self):
cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
self.data_path = os.path.join(cur_dir, 'data/medical.json') #json地址
#创建实例
self.g = Graph(
host="127.0.0.1", # neo4j 搭载服务器的ip地址,ifconfig可获取到
http_port=7474, # neo4j 服务器监听的端口号
user="neo4j", # 数据库user name,如果没有更改过,应该是neo4j
password="neo4jzl")
'''读取文件'''#返回包含所有节点/关系的元组
def read_nodes(self):
# 共7类节点
drugs = [] # 药品
foods = [] # 食物
checks = [] # 检查
departments = [] #科室
producers = [] #药品大类
diseases = [] #疾病
symptoms = []#症状
disease_infos = []#疾病信息 ,里面是字典格式[{'name':...,'desc':...,...,...},{}],里面是所有的实体节点
# 构建节点实体关系
rels_department = [] # 科室-科室关系
rels_noteat = [] # 疾病-忌吃食物关系
rels_doeat = [] # 疾病-宜吃食物关系
rels_recommandeat = [] # 疾病-推荐吃食物关系
rels_commonddrug = [] # 疾病-通用药品关系
rels_recommanddrug = [] # 疾病-热门药品关系
rels_check = [] # 疾病-检查关系
rels_drug_producer = [] # 厂商-药物关系
rels_symptom = [] #疾病症状关系
rels_acompany = [] # 疾病并发关系
rels_category = [] # 疾病与科室之间的关系
count = 0
for data in open(self.data_path, encoding='utf-8'):
disease_dict = {}
count += 1
print(count)
data_json = json.loads(data)
disease = data_json['name']
disease_dict['name'] = disease #疾病名称
diseases.append(disease) #疾病名称的list
disease_dict['desc'] = '' #创建空值键值对
disease_dict['prevent'] = ''
disease_dict['cause'] = ''
disease_dict['easy_get'] = ''
disease_dict['cure_department'] = ''
disease_dict['cure_way'] = ''
disease_dict['cure_lasttime'] = ''
disease_dict['symptom'] = ''
disease_dict['cured_prob'] = ''
if 'symptom' in data_json:
symptoms += data_json['symptom'] #症状加入列表symptoms
for symptom in data_json['symptom']:
rels_symptom.append([disease, symptom]) #疾病症状关系,list,[疾病,症状]
if 'acompany' in data_json:
for acompany in data_json['acompany']:
rels_acompany.append([disease, acompany]) #[疾病,并发症]
if 'desc' in data_json:
disease_dict['desc'] = data_json['desc'] #疾病简介
if 'prevent' in data_json:
disease_dict['prevent'] = data_json['prevent']
if 'cause' in data_json:
disease_dict['cause'] = data_json['cause']
if 'get_prob' in data_json:
disease_dict['get_prob'] = data_json['get_prob']
if 'easy_get' in data_json:
disease_dict['easy_get'] = data_json['easy_get']
if 'cure_department' in data_json:
cure_department = data_json['cure_department'] #就诊科室
if len(cure_department) == 1:
rels_category.append([disease, cure_department[0]])
if len(cure_department) == 2:
big = cure_department[0]
small = cure_department[1]
rels_department.append([small, big]) #科室_科室关系,如[ "内科", "消化内科" ]
rels_category.append([disease, small]) #疾病_科室关系
disease_dict['cure_department'] = cure_department
departments += cure_department
if 'cure_way' in data_json:
disease_dict['cure_way'] = data_json['cure_way']
if 'cure_lasttime' in data_json:
disease_dict['cure_lasttime'] = data_json['cure_lasttime']
if 'cured_prob' in data_json:
disease_dict['cured_prob'] = data_json['cured_prob']
if 'common_drug' in data_json:
common_drug = data_json['common_drug']
for drug in common_drug:
rels_commonddrug.append([disease, drug]) #疾病,常用药
drugs += common_drug
if 'recommand_drug' in data_json:
recommand_drug = data_json['recommand_drug']
drugs += recommand_drug
for drug in recommand_drug:
rels_recommanddrug.append([disease, drug])
if 'not_eat' in data_json:
not_eat = data_json['not_eat']
for _not in not_eat:
rels_noteat.append([disease, _not])
foods += not_eat
do_eat = data_json['do_eat']
for _do in do_eat:
rels_doeat.append([disease, _do])
foods += do_eat
recommand_eat = data_json['recommand_eat']
for _recommand in recommand_eat:
rels_recommandeat.append([disease, _recommand])
foods += recommand_eat
if 'check' in data_json:
check = data_json['check']
for _check in check:
rels_check.append([disease, _check])
checks += check
if 'drug_detail' in data_json:
drug_detail = data_json['drug_detail']
producer = [i.split('(')[0] for i in drug_detail]
rels_drug_producer += [[i.split('(')[0], i.split('(')[-1].replace(')', '')] for i in drug_detail]
producers += producer
disease_infos.append(disease_dict)
return set(drugs), set(foods), set(checks), set(departments), set(producers), set(symptoms), set(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
'''建立节点'''#这是操作数据库的
def create_node(self, label, nodes):
count = 0
for node_name in nodes: #新建节点,每个节点有一个name属性
node = Node(label, name=node_name)
self.g.create(node) #新建数据库节点
count += 1
print(count, len(nodes))
return
'''创建知识图谱中心疾病的节点'''
def create_diseases_nodes(self, disease_infos):
count = 0
for disease_dict in disease_infos: #创建所有的实体节点,每个节点具有以下9个属性
node = Node("Disease", name=disease_dict['name'], desc=disease_dict['desc'],
prevent=disease_dict['prevent'] ,cause=disease_dict['cause'],
easy_get=disease_dict['easy_get'],cure_lasttime=disease_dict['cure_lasttime'],
cure_department=disease_dict['cure_department']
,cure_way=disease_dict['cure_way'] , cured_prob=disease_dict['cured_prob'])
self.g.create(node) #新建实体节点
count += 1
print(count)
return
'''创建知识图谱实体节点类型schema'''
def create_graphnodes(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()
self.create_diseases_nodes(disease_infos) #为每一个疾病都创建了一个节点,每个节点有9个属性
self.create_node('Drug', Drugs) #为每个药品创建一个节点,有一个属性name = 药品名称
print(len(Drugs))
self.create_node('Food', Foods) #同上,name=食物名称
print(len(Foods))
self.create_node('Check', Checks) #检查
print(len(Checks))
self.create_node('Department', Departments) #科室
print(len(Departments))
self.create_node('Producer', Producers) #药品
print(len(Producers))
self.create_node('Symptom', Symptoms) #症状
return
'''创建实体关系边'''
def create_graphrels(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()
self.create_relationship('Disease', 'Food', rels_recommandeat, 'recommand_eat', '推荐食谱')
self.create_relationship('Disease', 'Food', rels_noteat, 'no_eat', '忌吃')
self.create_relationship('Disease', 'Food', rels_doeat, 'do_eat', '宜吃')
self.create_relationship('Department', 'Department', rels_department, 'belongs_to', '属于')
self.create_relationship('Disease', 'Drug', rels_commonddrug, 'common_drug', '常用药品')
self.create_relationship('Producer', 'Drug', rels_drug_producer, 'drugs_of', '生产药品')
self.create_relationship('Disease', 'Drug', rels_recommanddrug, 'recommand_drug', '好评药品')
self.create_relationship('Disease', 'Check', rels_check, 'need_check', '诊断检查')
self.create_relationship('Disease', 'Symptom', rels_symptom, 'has_symptom', '症状')
self.create_relationship('Disease', 'Disease', rels_acompany, 'acompany_with', '并发症')
self.create_relationship('Disease', 'Department', rels_category, 'belongs_to', '所属科室')
'''创建实体关联边'''
def create_relationship(self, start_node, end_node, edges, rel_type, rel_name):
#start_node是边的起点名称,标准叫法叫类型lable,如'Disease', end_node是边的终点如'Food', edges是边的关系(实际关联项) 如rels_recommandeat, rel_type关联名如 'recommand_eat', rel_name中文关联名如'推荐食谱'
count = 0
# 去重处理.实体关系为形如[[“a”,“b”],[“c”,“d”]]的嵌套list,无法直接用set去重,所以先将嵌套内层的list转为字符串,再用set。
set_edges = []
for edge in edges:
set_edges.append('###'.join(edge)) #这就转化为字符串了
all = len(set(set_edges))
for edge in set(set_edges): #这就去重了
edge = edge.split('###')
p = edge[0]
q = edge[1]
query = "match(p:%s),(q:%s) where p.name='%s'and q.name='%s' create (p)-[rel:%s{name:'%s'}]->(q)" % (
start_node, end_node, p, q, rel_type, rel_name)
try:
self.g.run(query)
#run()的用法大概是这样的,比如start_node, end_node这两种节点已经提前存进去了,比如label分别是Disease和Food,现在需要在他们间建立关系,括号里面是neo4j的查询语句cql,语法jiegou类似sql语句。关系就是rel_typ,还带了一个属性{name:'rel_name'}。
#run("MATCH (p:start_node),(q:end_node) WHERE p.name='p' and q.name='q' create (p)-[rel:'rel_type'{name:'rel_name'}]->(q))
count += 1
print(rel_type, count, all)
except Exception as e:
print(e)
return
'''导出数据''' 数据放到txt文件里了.
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.write('\n'.join(list(Drugs)))
f_food.write('\n'.join(list(Foods)))
f_check.write('\n'.join(list(Checks)))
f_department.write('\n'.join(list(Departments)))
f_producer.write('\n'.join(list(Producers)))
f_symptom.write('\n'.join(list(Symptoms)))
f_disease.write('\n'.join(list(Diseases)))
f_drug.close()
f_food.close()
f_check.close()
f_department.close()
f_producer.close()
f_symptom.close()
f_disease.close()
return
if __name__ == '__main__':
handler = MedicalGraph()
# handler.export_data()
#handler.create_graphnodes()
handler.create_graphrels()