python将csv数据导入neo4j

news/发布时间2024/6/1 4:42:57

参考链接：https://github.com/jm199504/Financial-Knowledge-Graphs/tree/master

from pandas import DataFrame
from py2neo import Graph,Node,Relationship,NodeMatcher
import pandas as pd
import numpy as np
import os
# 连接Neo4j数据库
from py2neo import Graph, Node, Relationship, walk, NodeMatcher, RelationshipMatcher
import pandas as pd
import json
# 连接数据库 输入地址、用户名、密码
from py2neo import Graph# 使用包含用户名和密码的 URI 连接到数据库
uri = "http://neo4j:neo4j@localhost:7474"
graph = Graph(uri)

a = Node('Person',name='Tom')
graph.create(a)
b = Node('Person',name='Bob')
graph.create(b)# 创建关系例子
r = Relationship(a,'KNOWS',b)
graph.create(r)# 读取节点信息
node = DataFrame(graph.run('MATCH (n:`Person`) RETURN n LIMIT 25'))
# print(node)# 读取关系信息
relation = DataFrame(graph.run('MATCH (n:`Person`)-[r]->(m:`Person`) return n,m,type(r)'))
# print(relation)# 删除所有节点
graph.run('MATCH (n) OPTIONAL MATCH (n)-[r]-() DELETE n,r')

(No data)

# 读取数据
stock = pd.read_csv('stock_basic.csv',encoding="gbk")
holder = pd.read_csv('stock_holders.csv',encoding="gbk")
concept_num = pd.read_csv('concept.csv',encoding="gbk")
concept = pd.read_csv('stock_concept.csv',encoding="gbk")
sh = pd.read_csv('sh.csv')
sz = pd.read_csv('sz.csv')
corr = pd.read_csv('corr.csv')

stock.head()

	Unnamed: 0	TS代码	股票代码	股票名称	行业
0	0	000001.SZ	1	平安银行	银行
1	1	000002.SZ	2	万科A	全国地产
2	2	000004.SZ	4	国华网安	互联网
3	3	000005.SZ	5	世纪星源	环境保护
4	4	000006.SZ	6	深振业A	区域地产

holder.head()

	Unnamed: 0	ts_code	ann_date	end_date	holder_name	hold_amount	hold_ratio
0	0	000001.SZ	20190307	20181231	新华人寿保险股份有限公司-分红-个人分红-018L-FH002深	4.960350e+07	0.29
1	1	000001.SZ	20190307	20181231	中国平安保险(集团)股份有限公司-集团本级-自有资金	8.510493e+09	49.56
2	2	000001.SZ	20190307	20181231	中国平安人寿保险股份有限公司-自有资金	1.049463e+09	6.11
3	3	000001.SZ	20190307	20181231	香港中央结算有限公司(陆股通)	4.307515e+08	2.51
4	4	000001.SZ	20190307	20181231	中国证券金融股份有限公司	4.292327e+08	2.50

concept_num.head()

	Unnamed: 0	code	name	src
0	0	TS0	密集调研	ts
1	1	TS1	南北船合并	ts
2	2	TS2	5G	ts
3	3	TS3	机场	ts
4	4	TS4	高价股	ts

concept.head()

	Unnamed: 0	id	concept_name	ts_code	name
0	0	TS0	密集调研	000301.SZ	东方盛虹
1	1	TS0	密集调研	000401.SZ	冀东水泥
2	2	TS0	密集调研	000932.SZ	华菱钢铁
3	3	TS0	密集调研	002013.SZ	中航机电
4	4	TS0	密集调研	002106.SZ	莱宝高科

sh.head()

	ts_code	hs_type	in_date	out_date	is_new
0	601628.SH	SH	20141117	NaN	1
1	601099.SH	SH	20141117	NaN	1
2	601808.SH	SH	20141117	NaN	1
3	601107.SH	SH	20141117	NaN	1
4	601880.SH	SH	20141117	NaN	1

sz.head()

	ts_code	hs_type	in_date	out_date	is_new
0	002910.SZ	SZ	20171114	NaN	1
1	000016.SZ	SZ	20180102	NaN	1
2	001872.SZ	SZ	20180102	NaN	1
3	000040.SZ	SZ	20180102	NaN	1
4	000401.SZ	SZ	20180102	NaN	1

corr.head()

	Unnamed: 0	s1	s2	corr
0	0	000001.SZ.	000001.SZ.	1.000000
1	1	000001.SZ.	000002.SZ.	0.648945
2	2	000001.SZ.	000005.SZ.	0.342920
3	3	000001.SZ.	000009.SZ.	0.297213
4	4	000001.SZ.	000010.SZ.	0.186165

# 数据预处理
stock['行业'] = stock['行业'].fillna('未知')
holder = holder.drop_duplicates(subset=None, keep='first', inplace=False)

# 创建实体（概念、股票、股东、股通）sz = Node('深股通',名字='深股通')
graph.create(sz)  sh = Node('沪股通',名字='沪股通')
graph.create(sh)  for i in concept_num.values:a = Node('概念',概念代码=i[1],概念名称=i[2])# print('概念代码:'+str(i[1]),'概念名称:'+str(i[2]))graph.create(a)for i in stock.values:a = Node('股票',TS代码=i[1],股票名称=i[3],行业=i[4])# print('TS代码:'+str(i[1]),'股票名称:'+str(i[3]),'行业:'+str(i[4]))graph.create(a)for i in holder.values:a = Node('股东',TS代码=i[0],股东名称=i[1],持股数量=i[2],持股比例=i[3])# print('TS代码:'+str(i[0]),'股东名称:'+str(i[1]),'持股数量:'+str(i[2]))graph.create(a)

# 创建关系（股票-股东、股票-概念、股票-公告、股票-股通）matcher = NodeMatcher(graph) 
for i in holder.values:    a = matcher.match("股票",TS代码=i[0]).first()b = matcher.match("股东",TS代码=i[0])for j in b:r = Relationship(j,'参股',a)graph.create(r)print('TS',str(i[0]))for i in concept.values:a = matcher.match("股票",TS代码=i[3]).first()b = matcher.match("概念",概念代码=i[1]).first()if a == None or b == None:continuer = Relationship(a,'概念属于',b)graph.create(r)