python将csv数据导入neo4j

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: 0TS代码股票代码股票名称行业00000001.SZ1平安银行银行11000002.SZ2万科A全国地产22000004.SZ4国华网安互联网33000005.SZ5世纪星源环境保护44000006.SZ6深振业A区域地产

holder.head()

Unnamed: 0ts_codeann_dateend_dateholder_namehold_amounthold_ratio00000001.SZ2019030720181231新华人寿保险股份有限公司-分红-个人分红-018L-FH002深4.960350e+070.2911000001.SZ2019030720181231中国平安保险(集团)股份有限公司-集团本级-自有资金8.510493e+0949.5622000001.SZ2019030720181231中国平安人寿保险股份有限公司-自有资金1.049463e+096.1133000001.SZ2019030720181231香港中央结算有限公司(陆股通)4.307515e+082.5144000001.SZ2019030720181231中国证券金融股份有限公司4.292327e+082.50

concept_num.head()

Unnamed: 0codenamesrc00TS0密集调研ts11TS1南北船合并ts22TS25Gts33TS3机场ts44TS4高价股ts

concept.head()

Unnamed: 0idconcept_namets_codename00TS0密集调研000301.SZ东方盛虹11TS0密集调研000401.SZ冀东水泥22TS0密集调研000932.SZ华菱钢铁33TS0密集调研002013.SZ中航机电44TS0密集调研002106.SZ莱宝高科

sh.head()

ts_codehs_typein_dateout_dateis_new0601628.SHSH20141117NaN11601099.SHSH20141117NaN12601808.SHSH20141117NaN13601107.SHSH20141117NaN14601880.SHSH20141117NaN1

sz.head()

ts_codehs_typein_dateout_dateis_new0002910.SZSZ20171114NaN11000016.SZSZ20180102NaN12001872.SZSZ20180102NaN13000040.SZSZ20180102NaN14000401.SZSZ20180102NaN1

corr.head()

Unnamed: 0s1s2corr00000001.SZ.000001.SZ.1.00000011000001.SZ.000002.SZ.0.64894522000001.SZ.000005.SZ.0.34292033000001.SZ.000009.SZ.0.29721344000001.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:

continue

r = Relationship(a,'概念属于',b)

graph.create(r)

推荐文章

 您阅读本篇文章共花了：