标签：util 操作 extract dataframe 销售 pandas hide org img
1、使用工具：py2neo ，官方操作文档 ：https://py2neo.org/v4/index.html
2、还包括一些neo4j的命令操作
1、数据展示
2、这个案例主要是读取Excel中的结构化数据购买方、销售方（节点）和金额（边），并实现在图中创建实体
1、DataToNeo4jClass.py（连接neo4j，创建节点和关系的工具）
# -*- 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("http://localhost:7474", username="neo4j", password="wzs208751") self.graph = link #self.graph = NodeMatcher(link) # 定义label self.buy = ‘buy‘ self.sell = ‘sell‘ self.graph.delete_all() 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)
2、invoice_neo4j.py
# -*- coding: utf-8 -*- from utils.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(‘./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[invoice_data.columns[19]][i])#金额 sell_list.append(invoice_data[invoice_data.columns[10]][i])#销售方方名称 buy_list.append(invoice_data[invoice_data.columns[6]][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() create_data = DataToNeo4j() create_data.create_node(data_extraction()[0], data_extraction()[1]) create_data.create_relation(relation_extraction())
增： 增加一个节点 create (n:Person {name:‘我‘,age:31}) 带有关系属性 create (p:Person{name:"我",age:"31"})-[:包工程{金额:10000}]->(n:Person{name:"好大哥",age:"35"}) 删 create (n:Person {name:‘TYD‘,age:31}) match (n:Person{name:"TYD"}) delete n 删除关系 match (p:Person{name:"我",age:"31"})-[f:包工程]->(n:Person{name:"好大哥",age:"35"}) delete f 改： 加上标签 match (t:Person) where id(t)=789 set t:好人return t 加上属性 match (a:好人) where id(a)=789 set a.战斗力=200 return a 修改属性 match (a:好人) where id(a)=789 set a.战斗力=500 return a 查：(查操作太多啦，直接参考neo4j例子就好) match (p:Person) - [:包工程] -> (n:Person) return p,n 快速清空数据库： MATCH (n) DETACH DELETE n
标签：util 操作 extract dataframe 销售 pandas hide org img
原文地址：https://www.cnblogs.com/20183544-wangzhengshuai/p/14876534.html
