1、准备数据集
数据集下载地址：https://github.com/wangle1218/QASystemOnMedicalKG/blob/master/data/medical.json
2、导入相关包
from py2neo import Graph,Node,Relationship
import pandas as pd
3、连接Neo4j
neo_graph = Graph(host="127.0.0.1",
user='neo4j',
password='xxxx')
neo_graph
4、构建知识图谱
from py2neo import Graph
import os
from tqdm import tqdm
import json
import datetime
class CreateKG():
def __init__(self, kg_host, kg_port, kg_user, kg_password, data_path):
self.graph = Graph(
host=kg_host,
user=kg_user,
password=kg_password)
if not data_path or data_path == '':
raise Exception("数据集地址为空")
if not os.path.exists(data_path):
raise Exception("数据集不存在")
self.data_path = data_path
def saveEntity(self, label, data):
print("\n写入实体：", label)
for item in tqdm(data, ncols=80):
try:
property = []
for key, value in item.items():
value = value.replace("'", "")
property.append(key + ":" + "'" + value + "'")
if len(property) == 0:
continue
cql = "MERGE(n:" + label + "{" + ",".join(property) + "})"
self.graph.run(cql)
except Exception as e:
pass
def saveRelation(self, s_label, e_label, label, data):
print("\n写入关系：", label)
for item in tqdm(data, ncols=80):
try:
s_name = item["s_name"]
e_name = item["e_name"]
cql = "MATCH(p:" + s_label + "),(q:" + e_label + ") WHERE p.name='" + s_name + "' AND q.name='" + e_name + "' MERGE (p)-[r:" + label + "]->(q)"
self.graph.run(cql)
except Exception as e:
pass
def getValue(self, key, data):
if key in data:
return data[key]
return ""
def init(self):
diseases = []
departments = []
symptoms = []
cureWays = []
checks = []
drugs = []
crowds = []
foods = []
diseaseDepartmentRelations = []
diseaseSymptomRelations = []
diseaseCureWayRelations = []
diseaseCheckRelations = []
diseaseDrugRelations = []
diseaseCrowdRelations = []
diseaseSuitableFoodRelations = []
diseaseTabooFoodRelations = []
diseaseDiseaseRelations = []
print("====数据抽取======")
with open(self.data_path, 'r', encoding='utf8') as f:
for line in tqdm(f.readlines(), ncols=80):
data = json.loads(line)
disease = {
"name": data["name"],
"desc": self.getValue("desc", data),
"prevent": self.getValue("prevent", data),
"cause": self.getValue("cause", data),
"get_prob": self.getValue("get_prob", data),
"get_way": self.getValue("get_way", data),
"cure_lasttime": self.getValue("cure_lasttime", data),
"cured_prob": self.getValue("cured_prob", data),
"cost_money": self.getValue("cost_money", data),
}
diseases.append(disease)
if "cure_department" in data:
for department in data["cure_department"]:
diseaseDepartmentRelations.append({
"s_name": data["name"],
"e_name": department
})
property = {
"name": department
}
if property not in departments:
departments.append(property)
if "symptom" in data:
for symptom in data["symptom"]:
diseaseSymptomRelations.append({
"s_name": data["name"],
"e_name": symptom
})
property = {
"name": symptom
}
if property not in symptoms:
symptoms.append(property)
if "cure_way" in data:
for cure_way in data["cure_way"]:
diseaseCureWayRelations.append({
"s_name": data["name"],
"e_name": cure_way
})
property = {
"name": cure_way
}
if property not in cureWays:
cureWays.append(property)
if "check" in data:
for check in data["check"]:
diseaseCheckRelations.append({
"s_name": data["name"],
"e_name": check
})
property = {
"name": check
}
if property not in checks:
checks.append(property)
if "common_drug" in data:
for common_drug in data["common_drug"]:
diseaseDrugRelations.append({
"s_name": data["name"],
"e_name": common_drug
})
property = {
"name": common_drug
}
if property not in drugs:
drugs.append(property)
if "easy_get" in data:
easy_get = data["easy_get"]
diseaseCrowdRelations.append({
"s_name": data["name"],
"e_name": easy_get
})
property = {
"name": easy_get
}
if property not in crowds:
crowds.append(property)
if "recommand_eat" in data:
for recommand_eat in data["recommand_eat"]:
diseaseSuitableFoodRelations.append({
"s_name": data["name"],
"e_name": recommand_eat
})
property = {
"name": recommand_eat
}
if property not in foods:
foods.append(property)
if "not_eat" in data:
for not_eat in data["not_eat"]:
diseaseTabooFoodRelations.append({
"s_name": data["name"],
"e_name": not_eat
})
property = {
"name": not_eat
}
if property not in foods:
foods.append(property)
if "acompany" in data:
for acompany in data["acompany"]:
diseaseDiseaseRelations.append({
"s_name": data["name"],
"e_name": acompany
})
self.saveEntity("disease", diseases)
self.saveEntity("department", departments)
self.saveEntity("symptom", symptoms)
self.saveEntity("cureWay", cureWays)
self.saveEntity("check", checks)
self.saveEntity("drug", drugs)
self.saveEntity("crowd", crowds)
self.saveEntity("food", foods)
self.saveRelation("disease", "department", "diseaseDepartmentRelations", diseaseDepartmentRelations)
self.saveRelation("disease", "symptom", "diseaseSymptomRelation", diseaseSymptomRelations)
self.saveRelation("disease", "cureWay", "diseaseCureWayRelation", diseaseCureWayRelations)
self.saveRelation("disease", "check", "diseaseCheckRelation", diseaseCheckRelations)
self.saveRelation("disease", "drug", "diseaseDrugRelation", diseaseDrugRelations)
self.saveRelation("disease", "crowd", "diseaseCrowdRelation", diseaseCrowdRelations)
self.saveRelation("disease", "food", "diseaseSuitableFoodRelation", diseaseSuitableFoodRelations)
self.saveRelation("disease", "food", "diseaseTabooFoodRelation", diseaseTabooFoodRelations)
self.saveRelation("disease", "disease", "diseaseDiseaseRelation", diseaseDiseaseRelations)
if __name__ == '__main__':
start = datetime.datetime.now()
kg_host = "127.0.0.1"
kg_port = 7474
kg_user = "neo4j"
kg_password = "960418.hmx"
data_path = "dataset/知识图谱/medical.json"
kg = CreateKG(kg_host, kg_port, kg_user, kg_password, data_path)
kg.init()
end = datetime.datetime.now()
print("共耗时：{}".format(end - start))
5、实验结果
构建的知识图谱
鼻炎的病症描述：
match (n:disease) where n.name = ‘鼻炎’ return n.descol
鼻炎所属的科室：
match (n:disease)-[e:diseaseDepartmentRelations]->(n1:department) where n.name = ‘鼻炎’ return n,n1
鼻炎的症状：
match (n:disease)-[e:diseaseSymptomRelation]->(n1:symptom) where n.name = ‘鼻炎’ return n,n1
鼻炎的治疗方式：
match (n:disease)-[e:diseaseCureWayRelation]->(n1:cureWay) where n.name = ‘鼻炎’ return n,n1
鼻炎应该用什么药：
match (n:disease)-[e:diseaseDrugRelation]->(n1:drug) where n.name = ‘鼻炎’ return n,n1
