【知识图谱】知识图谱的构建-python-neo4j
代码参考：https://github.com/liuhuanyong/QASystemOnMedicalKG
自己做了的一些注释和改动：https://github.com/taishan1994/medical_question_and_answer_knowledge_graph/
环境依赖
jdk、neo4j图数据库
neo4j具体的安装过程可以参考这里：https://cloud.tencent.com/developer/article/1387732
json数据
{
"_id": {
"$oid": "5bb578b6831b973a137e3ee6"
},
"name": "肺泡蛋白质沉积症",
"desc": "肺泡蛋白质沉积症(简称PAP)，又称Rosen-Castle-man-Liebow综合征，是一种罕见疾病。该病以肺泡和细支气管腔内充满PAS染色阳性，来自肺的富磷脂蛋白质物质为其特征，好发于青中年，男性发病约3倍于女性。",
"category": ["疾病百科", "内科", "呼吸内科"],
"prevent": "1、避免感染分支杆菌病，卡氏肺囊肿肺炎，巨细胞病毒等。\n2、注意锻炼身体，提高免疫力。",
"cause": "病因未明，推测与几方面因素有关：如大量粉尘吸入（铝，二氧化硅等），机体免疫功能下降（尤其婴幼儿），遗传因素，酗酒，微生物感染等，而对于感染，有时很难确认是原发致病因素还是继发于肺泡蛋白沉着症，例如巨细胞病毒，卡氏肺孢子虫，组织胞浆菌感染等均发现有肺泡内高蛋白沉着。\n虽然启动因素尚不明确，但基本上同意发病过程为脂质代谢障碍所致，即由于机体内，外因素作用引起肺泡表面活性物质的代谢异常，到目前为止，研究较多的有肺泡巨噬细胞活力，动物实验证明巨噬细胞吞噬粉尘后其活力明显下降，而病员灌洗液中的巨噬细胞内颗粒可使正常细胞活力下降，经支气管肺泡灌洗治疗后，其肺泡巨噬细胞活力可上升，而研究未发现Ⅱ型细胞生成蛋白增加，全身脂代谢也无异常，因此目前一般认为本病与清除能力下降有关。",
"symptom": ["紫绀", "胸痛", "呼吸困难", "乏力", "毓卓"],
"yibao_status": "否",
"get_prob": "0.00002%",
"get_way": "无传染性",
"acompany": ["多重肺部感染"],
"cure_department": ["内科", "呼吸内科"],
"cure_way": ["支气管肺泡灌洗"],
"cure_lasttime": "约3个月",
"cured_prob": "约40%",
"cost_money": "根据不同医院，收费标准不一致，省市三甲医院约（ 8000——15000 元）",
"check": ["胸部CT检查", "肺活检", "支气管镜检查"],
"recommand_drug": [],
"drug_detail": []
} ......
实例
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\\medical2.json')
self.g = Graph("http://localhost:7474", username="neo4j", password="rhino1qaz@wsx")
def read_nodes(self):
diseases = [] # 疾病
drugs = [] # 药品
departments = [] # 科室
disease_infos = []
rels_disease_drug = [] #疾病和药品之间的关系
rels_disease_department = [] #疾病和科室之间的关系
rels_department_department = [] #科室和科室之间的关系
count = 0
for data in open(self.data_path):
disease_dict = {}
count += 1
print(count)
# 读取每一行数据
data_json = json.loads(data)
print(data_json)
disease = data_json['name']
disease_dict['name'] = disease # 疾病名
diseases.append(disease)
if 'cure_department' in data_json:
cure_department = data_json['cure_department']
if len(cure_department) == 1:
rels_disease_department.append([disease, cure_department[0]])
if len(cure_department) == 2:
big = cure_department[0]
small = cure_department[1]
rels_department_department.append([small, big])
rels_disease_department.append([disease, small])
disease_dict['cure_department'] = cure_department
departments += cure_department
if 'recommand_drug' in data_json:
recommand_drug = data_json['recommand_drug']
drugs += recommand_drug
for drug in recommand_drug:
rels_disease_drug.append([disease, drug])
disease_dict['recommand_drug'] = recommand_drug
disease_infos.append(disease_dict)
return set(diseases), set(drugs), set(departments), disease_infos, \
rels_disease_drug, rels_disease_department, rels_department_department
def create_node(self, label, nodes):
count = 0
for node_name in nodes:
node = Node(label, name=node_name)
self.g.create(node)
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:
node = Node("Disease", name=disease_dict['name'], recommand_drug=disease_dict['recommand_drug'],
cure_department=disease_dict['cure_department'])
self.g.create(node)
count += 1
print(count)
return
'''创建知识图谱实体节点类型schema'''
def create_graphnodes(self):
diseases, Drugs, Departments, disease_infos, \
rels_disease_drug, rels_disease_department, rels_department_department = self.read_nodes()
self.create_diseases_nodes(disease_infos)
self.create_node('Drug', Drugs)
print(len(Drugs))
self.create_node('Department', Departments)
print(len(Departments))
return
'''创建实体关系边'''
def create_graphrels(self):
diseases, Drugs, Departments, disease_infos, \
rels_disease_drug, rels_disease_department, rels_department_department = self.read_nodes()
self.create_relationship('Disease', 'Drug', rels_disease_drug, 'recommand_eat', '宜吃')
self.create_relationship('Disease', 'Department', rels_disease_department, 'belongs_to', '所属科室')
self.create_relationship('Department', 'Department', rels_department_department, 'belongs_to', '属于')
def create_relationship(self, start_node, end_node, edges, rel_type, rel_name):
count = 0
# 去重处理
set_edges = []
for edge in edges:
set_edges.append('###'.join(edge))
all = len(set(set_edges))
for edge in set(set_edges):
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)
count += 1
print(rel_type, count, all)
except Exception as e:
print(e)
return
'''导出数据'''
def export_data(self):
diseases, Drugs, Departments, disease_infos, \
rels_disease_drug, rels_disease_department, rels_department_department = self.read_nodes()
f_disease = open('disease.txt', 'w+')
f_drug = open('drug.txt', 'w+')
f_department = open('department.txt', 'w+')
f_disease.write('\n'.join(list(diseases)))
f_drug.write('\n'.join(list(Drugs)))
f_department.write('\n'.join(list(Departments)))
f_disease.close()
f_drug.close()
f_department.close()
return
if __name__ == '__main__':
medicalGraph = MedicalGraph()
medicalGraph.create_graphnodes()
medicalGraph.create_graphrels()
medicalGraph.export_data()
无非就是连接图数据库，然后创建节点、创建关系，当做模板来看就行了，最后结果：
