本节的主要内容是将开源项目QASystemOnMedicalGraph 导入本地Neo4j中,并阅读相关源码
首先补充运行该代码需要安装的ahocorasick库:anaconda search -t conda pyahocorasick
;conda install -c https://conda.anaconda.org/conda-forge pyahocorasick
,其他pip inatall安装就可以
class MedicalGraph:
def __init__(self):
pass
# 读取文件,获得实体,实体关系
def read_file(self):
psss
# 创建节点
def create_node(self, label, nodes):
pass
# 创建疾病节点的属性
def create_diseases_nodes(self, disease_info):
pass
# 创建知识图谱实体
def create_graphNodes(self):
pass
# 创建实体关系边
def create_graphRels(self):
pass
# 创建实体关系边
def create_relationship(self, start_node, end_node, edges, rel_type, rel_name):
pass
if __name__ == "__main__":
handler = MedicalGraph()
handler.create_graphNodes()
handler.create_graphRels()
入口函数首先实例化了MedicalGraph类,并调用创建实体节点和边的方法
init函数在类实例化过程中自动调用,主要内容为定义类属性
cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
self.data_path = os.path.join(cur_dir, 'DATA/disease.csv')
self.graph = Graph("http://localhost:7474", username="neo4j", password="xxxxx")
os.path.join()函数用于拼接两个或更多的路径,该函数首先获取了该文件的绝对路径,并定义了数据存放路径和Neo4j连接参数。
该函数主要是调用read_file函数读取文件获得实体和实体关系,并创建实体
def create_graphNodes(self):
"""
创建知识图谱实体
:return:
"""
disease, symptom, alias, part, department, complication, drug, rel_alias, rel_symptom, rel_part, \
rel_department, rel_complication, rel_drug, rel_infos = self.read_file()
self.create_diseases_nodes(rel_infos)
self.create_node("Symptom", symptom)
self.create_node("Alias", alias)
self.create_node("Part", part)
self.create_node("Department", department)
self.create_node("Complication", complication)
self.create_node("Drug", drug)
return
该函数主要是调用read_file函数读取文件获得实体和实体关系,并创建实体关系。
def create_graphRels(self):
disease, symptom, alias, part, department, complication, drug, rel_alias, rel_symptom, rel_part, \
rel_department, rel_complication, rel_drug, rel_infos = self.read_file()
self.create_relationship("Disease", "Alias", rel_alias, "ALIAS_IS", "别名")
self.create_relationship("Disease", "Symptom", rel_symptom, "HAS_SYMPTOM", "症状")
self.create_relationship("Disease", "Part", rel_part, "PART_IS", "发病部位")
self.create_relationship("Disease", "Department", rel_department, "DEPARTMENT_IS", "所属科室")
self.create_relationship("Disease", "Complication", rel_complication, "HAS_COMPLICATION", "并发症")
self.create_relationship("Disease", "Drug", rel_drug, "HAS_DRUG", "药品")
注意:上面两个函数每次都重新调用了read_file函数,该函数其实可以放进init函数中,将读进来的数据作为该类的属性保存
该函数就是读取数据文件,并对该文件数据预处理
def read_file(self):
"""
读取文件,获得实体,实体关系
:return:
"""
# cols = ["name", "alias", "part", "age", "infection", "insurance", "department", "checklist", "symptom",
# "complication", "treatment", "drug", "period", "rate", "money"]
# 实体
diseases = [] # 疾病
aliases = [] # 别名
symptoms = [] # 症状
parts = [] # 部位
departments = [] # 科室
complications = [] # 并发症
drugs = [] # 药品
# 疾病的属性:age, infection, insurance, checklist, treatment, period, rate, money
diseases_infos = []
# 关系
disease_to_symptom = [] # 疾病与症状关系
disease_to_alias = [] # 疾病与别名关系
diseases_to_part = [] # 疾病与部位关系
disease_to_department = [] # 疾病与科室关系
disease_to_complication = [] # 疾病与并发症关系
disease_to_drug = [] # 疾病与药品关系
all_data = pd.read_csv(self.data_path, encoding='gb18030').loc[:, :].values
for data in all_data:
disease_dict = {} # 疾病信息
# 疾病
disease = str(data[0]).replace("...", " ").strip()
disease_dict["name"] = disease
# 别名
line = re.sub("[,、;,.;]", " ", str(data[1])) if str(data[1]) else "未知"
for alias in line.strip().split():
aliases.append(alias)
disease_to_alias.append([disease, alias])
# 部位
part_list = str(data[2]).strip().split() if str(data[2]) else "未知"
for part in part_list:
parts.append(part)
diseases_to_part.append([disease, part])
# 年龄
age = str(data[3]).strip()
disease_dict["age"] = age
# 传染性
infect = str(data[4]).strip()
disease_dict["infection"] = infect
# 医保
insurance = str(data[5]).strip()
disease_dict["insurance"] = insurance
# 科室
department_list = str(data[6]).strip().split()
for department in department_list:
departments.append(department)
disease_to_department.append([disease, department])
# 检查项
check = str(data[7]).strip()
disease_dict["checklist"] = check
# 症状
symptom_list = str(data[8]).replace("...", " ").strip().split()[:-1]
for symptom in symptom_list:
symptoms.append(symptom)
disease_to_symptom.append([disease, symptom])
# 并发症
complication_list = str(data[9]).strip().split()[:-1] if str(data[9]) else "未知"
for complication in complication_list:
complications.append(complication)
disease_to_complication.append([disease, complication])
# 治疗方法
treat = str(data[10]).strip()[:-4]
disease_dict["treatment"] = treat
# 药品
drug_string = str(data[11]).replace("...", " ").strip()
for drug in drug_string.split()[:-1]:
drugs.append(drug)
disease_to_drug.append([disease, drug])
# 治愈周期
period = str(data[12]).strip()
disease_dict["period"] = period
# 治愈率
rate = str(data[13]).strip()
disease_dict["rate"] = rate
# 费用
money = str(data[14]).strip() if str(data[14]) else "未知"
disease_dict["money"] = money
diseases_infos.append(disease_dict)
return set(diseases), set(symptoms), set(aliases), set(parts), set(departments), set(complications), \
set(drugs), disease_to_alias, disease_to_symptom, diseases_to_part, disease_to_department, \
disease_to_complication, disease_to_drug, diseases_infos
def create_node(self, label, nodes):
"""
创建节点
:param label: 标签
:param nodes: 节点
:return:
"""
count = 0
for node_name in nodes:
node = Node(label, name=node_name)
self.graph.create(node)
count += 1
print(count, len(nodes))
return
def create_diseases_nodes(self, disease_info):
"""
创建疾病节点的属性
:param disease_info: list(Dict)
:return:
"""
count = 0
for disease_dict in disease_info:
node = Node("Disease", name=disease_dict['name'], age=disease_dict['age'],
infection=disease_dict['infection'], insurance=disease_dict['insurance'],
treatment=disease_dict['treatment'], checklist=disease_dict['checklist'],
period=disease_dict['period'], rate=disease_dict['rate'],
money=disease_dict['money'])
self.graph.create(node)
count += 1
print(count)
return
def create_relationship(self, start_node, end_node, edges, rel_type, rel_name):
"""
创建实体关系边
:param start_node:
:param end_node:
:param edges:
:param rel_type:
:param rel_name:
:return:
"""
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.graph.run(query)
count += 1
print(rel_type, count, all)
except Exception as e:
print(e)
return