（（八）自然语言处理笔记------基于Neo4j的医疗问答系统
使用py2neo链接Neo4j数据库
python
pip install py2neo --default-timeout=100 -i https://pypi.tuna.tsinghua.edu.cn/simple测试能否正常连接：
python
from py2neo import Graph
graph = Graph(
"bolt://192.168.8.216:7687",
auth=("neo4j", "googosoft")
)
result = graph.run("CALL dbms.components() YIELD name, versions RETURN name, versions").data()
print(result)
reset_cypher = """
MATCH (n)
DETACH DELETE n
"""
graph.run(reset_cypher)
print("数据库已清空！")
创建节点与关系用法
python
from py2neo import Node, Graph, Relationship,NodeMatcher
class DataToNeo4j(object):
"""将excel中数据存入neo4j"""
def __init__(self):
"""建立连接"""
link = Graph(
"bolt://192.168.8.216:7687",
auth=("neo4j", "googosoft")
)
self.graph = link
#self.graph = NodeMatcher(link)
# 定义label
self.buy = 'buy'
self.sell = 'sell'
self.graph.delete_all() # 清空数据库中所有数据
self.matcher = NodeMatcher(link)
"""
node3 = Node('animal' , name = 'cat')
node4 = Node('animal' , name = 'dog')
node2 = Node('Person' , name = 'Alice')
node1 = Node('Person' , name = 'Bob')
r1 = Relationship(node2 , 'know' , node1)
r2 = Relationship(node1 , 'know' , node3)
r3 = Relationship(node2 , 'has' , node3)
r4 = Relationship(node4 , 'has' , node2)
self.graph.create(node1)
self.graph.create(node2)
self.graph.create(node3)
self.graph.create(node4)
self.graph.create(r1)
self.graph.create(r2)
self.graph.create(r3)
self.graph.create(r4)
"""详细用法类：
python
# -*- coding: utf-8 -*-
from py2neo import Node, Graph, Relationship,NodeMatcher
class DataToNeo4j(object):
"""将excel中数据存入neo4j"""
def __init__(self):
"""建立连接"""
link = Graph(
"bolt://192.168.8.216:7687",
auth=("neo4j", "googosoft")
)
self.graph = link
#self.graph = NodeMatcher(link)
# 定义label
self.buy = 'buy'
self.sell = 'sell'
self.graph.delete_all() # 清空数据库中所有数据
self.matcher = NodeMatcher(link)
"""
node3 = Node('animal' , name = 'cat')
node4 = Node('animal' , name = 'dog')
node2 = Node('Person' , name = 'Alice')
node1 = Node('Person' , name = 'Bob')
r1 = Relationship(node2 , 'know' , node1)
r2 = Relationship(node1 , 'know' , node3)
r3 = Relationship(node2 , 'has' , node3)
r4 = Relationship(node4 , 'has' , node2)
self.graph.create(node1)
self.graph.create(node2)
self.graph.create(node3)
self.graph.create(node4)
self.graph.create(r1)
self.graph.create(r2)
self.graph.create(r3)
self.graph.create(r4)
"""
def create_node(self, node_buy_key,node_sell_key):
"""建立节点"""
for name in node_buy_key:
buy_node = Node(self.buy, name=name)
self.graph.create(buy_node)
for name in node_sell_key:
sell_node = Node(self.sell, name=name)
self.graph.create(sell_node)
def create_relation(self, df_data):
"""建立联系"""
m = 0
for m in range(0, len(df_data)):
try:
print(list(self.matcher.match(self.buy).where("_.name=" + "'" + df_data['buy'][m] + "'")))
print(list(self.matcher.match(self.sell).where("_.name=" + "'" + df_data['sell'][m] + "'")))
rel = Relationship(self.matcher.match(self.buy).where("_.name=" + "'" + df_data['buy'][m] + "'").first(),
df_data['money'][m], self.matcher.match(self.sell).where("_.name=" + "'" + df_data['sell'][m] + "'").first())
self.graph.create(rel)
except AttributeError as e:
print(e, m)
将数据写入到Neo4j数据库中Demo
数据格式：
python
# -*- coding: utf-8 -*-
from py2neo import Node, Graph, Relationship,NodeMatcher
class DataToNeo4j(object):
"""将excel中数据存入neo4j"""
def __init__(self):
"""建立连接"""
link = Graph(
"bolt://192.168.8.216:7687",
auth=("neo4j", "googosoft")
)
self.graph = link
#self.graph = NodeMatcher(link)
# 定义label
self.buy = 'buy'
self.sell = 'sell'
self.graph.delete_all() # 清空数据库中所有数据
self.matcher = NodeMatcher(link)
"""
node3 = Node('animal' , name = 'cat')
node4 = Node('animal' , name = 'dog')
node2 = Node('Person' , name = 'Alice')
node1 = Node('Person' , name = 'Bob')
r1 = Relationship(node2 , 'know' , node1)
r2 = Relationship(node1 , 'know' , node3)
r3 = Relationship(node2 , 'has' , node3)
r4 = Relationship(node4 , 'has' , node2)
self.graph.create(node1)
self.graph.create(node2)
self.graph.create(node3)
self.graph.create(node4)
self.graph.create(r1)
self.graph.create(r2)
self.graph.create(r3)
self.graph.create(r4)
"""
def create_node(self, node_buy_key,node_sell_key):
"""建立节点"""
for name in node_buy_key:
buy_node = Node(self.buy, name=name)
self.graph.create(buy_node)
for name in node_sell_key:
sell_node = Node(self.sell, name=name)
self.graph.create(sell_node)
def create_relation(self, df_data):
"""建立联系"""
m = 0
for m in range(0, len(df_data)):
try:
print(list(self.matcher.match(self.buy).where("_.name=" + "'" + df_data['buy'][m] + "'")))
print(list(self.matcher.match(self.sell).where("_.name=" + "'" + df_data['sell'][m] + "'")))
rel = Relationship(self.matcher.match(self.buy).where("_.name=" + "'" + df_data['buy'][m] + "'").first(),
df_data['money'][m], self.matcher.match(self.sell).where("_.name=" + "'" + df_data['sell'][m] + "'").first())
self.graph.create(rel)
except AttributeError as e:
print(e, m)
"""
Relationship(start_node, rel_type, end_node) 用法：
start_node：关系起点节点对象
rel_type：关系类型（通常是字符串，比如 'SELL_TO'）
end_node：关系终点节点对象
"""
python
# -*- coding: utf-8 -*-
from dataToNeo4jClass.DataToNeo4jClass import DataToNeo4j
import os
import pandas as pd
#pip install py2neo==5.0b1 注意版本，要不对应不了
invoice_data = pd.read_excel('/home/data/project/customer_AAA/NLP/Heima/018_Neo4j_pandasDemo/Invoice_data_Demo.xls', header=0)
#print(invoice_data)
#可以先阅读下文档：https://py2neo.org/v4/index.html
def data_extraction():
"""节点数据抽取"""
# 取出购买方名称到list
node_buy_key = []
for i in range(0, len(invoice_data)):
node_buy_key.append(invoice_data['购买方名称'][i])
node_sell_key = []
for i in range(0, len(invoice_data)):
node_sell_key.append(invoice_data['销售方名称'][i])
# 去除重复的发票名称
node_buy_key = list(set(node_buy_key))
node_sell_key = list(set(node_sell_key))
# value抽出作node
node_list_value = []
for i in range(0, len(invoice_data)):
for n in range(1, len(invoice_data.columns)):
# 取出表头名称invoice_data.columns[i]
node_list_value.append(invoice_data[invoice_data.columns[n]][i])
# 去重
node_list_value = list(set(node_list_value))
# 将list中浮点及整数类型全部转成string类型
node_list_value = [str(i) for i in node_list_value]
return node_buy_key, node_sell_key,node_list_value
def relation_extraction():
"""联系数据抽取"""
links_dict = {}
sell_list = []
money_list = []
buy_list = []
for i in range(0, len(invoice_data)):
money_list.append(invoice_data['金额'][i]) #金额
sell_list.append(invoice_data['销售方名称'][i]) #销售方方名称
buy_list.append(invoice_data['购买方名称'][i]) #购买方名称
# 将数据中int类型全部转成string
sell_list = [str(i) for i in sell_list]
buy_list = [str(i) for i in buy_list]
money_list = [str(i) for i in money_list]
# 整合数据，将三个list整合成一个dict
links_dict['buy'] = buy_list
links_dict['money'] = money_list
links_dict['sell'] = sell_list
# 将数据转成DataFrame
df_data = pd.DataFrame(links_dict)
print(df_data)
return df_data
relation_extraction() # 提取关系
create_data = DataToNeo4j() # 初始化Neo4j数据库
create_data.create_node(data_extraction()[0], data_extraction()[1]) # 图数据库创建节点的语句
create_data.create_relation(relation_extraction()) # 图数据库创建关系的语句写入后。结果如下：
代码下载：
python
https://download.csdn.net/download/guoqingru0311/92443705