實體分析
詩名實體
屬性
包含：作詩時間，詩名，內容，翻譯，背景。
關系
| 實體1 | 關系 | 實體2 |
| 詩名 | 形式 | 詩詞形式 |
| 詩名 | 作者 | 詩人 |
| 詩名 | 分類 | 類別 |
| 詩名 | 詞牌名 | 詞牌名 |
| 詩名 | 曲牌名 | 曲牌名 |
| 詩名 | 朝代 | 朝代 |
詩人實體
屬性
包含：出生時間，頭像鏈接，去世時間，詩詞數量，字，號，名字，簡介。
關系
| 實體1 | 關系 | 實體2 |
| 詩人 | 好友 | 詩人 |
| 詩人 | 合稱 | 詩人合稱 |
| 詩人 | 軌跡 | 地點 |
| 詩人 | 寫作 | 詩名 |
| 詩人 | 朝代 | 朝代 |
朝代實體
屬性
包含：朝代名稱（唐宋元明清）
關系
| 實體1 | 關系 | 實體2 |
| 朝代 | 包含 | 詩人 |
| 朝代 | 包含 | 詩名 |
類別實體
屬性
包含：類別名稱（寫景，抒懷，。。。）
關系
| 實體1 | 關系 | 實體2 |
| 類別 | 包含 | 詩名 |
詩詞形式實體
屬性
包含：詩詞形式名稱（五言律詩，五言絕句，五言，七言律詩，七言絕句，七言）
關系
| 實體1 | 關系 | 實體2 |
| 詩詞形式 | 包含 | 詩名 |
詞牌名實體
屬性
包含：詞牌名名稱
關系
| 實體1 | 關系 | 實體2 |
| 詞牌名 | 包含 | 詩名 |
曲牌名實體
屬性
包含：曲牌名名稱
關系
| 實體1 | 關系 | 實體2 |
| 曲牌名 | 包含 | 詩名 |
詩人合稱實體
屬性
詩人合稱名稱
關系
| 實體1 | 關系 | 實體2 |
| 詩人合稱 | 包含 | 詩人 |
地點實體
屬性
包含：古代地點名稱，經緯度，現今名稱
事件實體
屬性
包含：時間，事件名稱，地點
詩句實體與關鍵字實體
屬性
數據內容，關鍵字內容
關系
| 實體1 | 關系 | 實體2 |
| 詩句 | 關鍵字 | 字 |
| 字 | 詩句 | 詩句 |
實體構建
構建順序
構建的原則：
先構建單個實體，不易發生多種關系的單個實體。
例如：類別，詩詞形式，詞牌名，曲牌名，朝代，詩人合稱，軌跡，事件
多關系實體：詩人，詩名
類別實體構建
create_tag.py
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_tag(): file = './data2/tag_name.xlsx' data = pd.read_excel(file).fillna("無") tag=list(data.tag) tag_label="tag"
for it in tag: attr1={"name":it} CreateNode(graph, tag_label, attr1) print("創建詩詞分類："+it+"成功！！") if __name__ == '__main__': create_tag()
展示
詩詞形式實體構建
create_formal.py
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_formal(): formal=['七言','五言','七言律詩','七言絕句','五言律詩','五言絕句'] formal_label="formal"
for it in formal: attr1={"name":it} CreateNode(graph, formal_label, attr1) print("創建詩詞形式："+it+"成功！！") if __name__ == '__main__': create_formal()
展示
詞牌名與曲牌名實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_pai_name(): file = './data2/cipai_name.xlsx' data = pd.read_excel(file).fillna("無") title=list(data.title) cipai_label="ci_pai"
for it in title: attr1={"name":it} CreateNode(graph, cipai_label, attr1) print("創建詞牌名"+it+"成功！！") file2 = './data2/qupai_name.xlsx' data2 = pd.read_excel(file2).fillna("無") title2 = list(data2.qu_name) qupai_label = "qu_pai"
for it in title2: attr1 = {"name": it} CreateNode(graph, qupai_label, attr1) print("創建曲牌名" + it + "成功！！") if __name__ == '__main__': create_pai_name()
展示
飛花令關鍵字實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_word(): file = './data2/word.xlsx' data = pd.read_excel(file).fillna("無") word=list(data.word) word_label="word"
for it in word: attr1={"name":it} CreateNode(graph, word_label, attr1) print("創建飛花令："+it+"成功！！") if __name__ == '__main__': create_word()
展示
詩句實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): #根絕節點name屬性，查找節點
m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') #獲取指定文件夾下的excel
import os def get_filename(path,filetype): # 輸入路徑、文件類型例如'.xlsx'
name = [] for root,dirs,files in os.walk(path): for i in files: if os.path.splitext(i)[1]==filetype: name.append(i) return name # 輸出由有后綴的文件名組成的列表
def create_sentence(): file = 'sentences/' lists = get_filename(file, '.xlsx') for it in lists: newfile = file + it print(newfile) # 獲取詩詞內容
data = pd.read_excel(newfile).fillna("無") sentens = list(data.sentens) author = list(data.author) title = list(data.title) keys = list(data.word) sentence_label='sentence' word_label='word'
if len(sentens)>50000: lenth=50000
else: lenth=len(sentens) for i in range(lenth): print("第" + str(i) + "個") attr1 = {"name": sentens[i], "author": author[i], "title": title[i]} CreateNode(graph, sentence_label, attr1) print("創建詩句：" + sentens[i] + "成功！！") word_list=keys[i].split(',') for it in word_list: attr2 = {"name": it} # 創建關系
m_r_name1 = "關鍵字" reValue1 = CreateRelationship(graph, sentence_label, attr1, word_label, attr2, m_r_name1) print("創建關系：" + sentens[i] + "-關鍵字-" + it + "成功") m_r_name2 = "詩句" reValue2 = CreateRelationship(graph, word_label, attr2, sentence_label, attr1, m_r_name2) print("創建關系：" + it + "-詩句-" + sentens[i] + "成功") if __name__ == '__main__': create_sentence()
展示
詩人與朝代實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_author(): file='./data2/author.xlsx' data=pd.read_excel(file).fillna("無") author=list(data.author) produce=list(data.produce) num=list(data.num) src=list(data.src) desty=list(data.desty) bg_time=list(data.begin_time) ed_time=list(data.end_time) zi_list=list(data.zi) hao_list=list(data.hao) author_label='author' desty_label='desty'
for i in range(len(author)): print("第"+str(i)+"個") attr1 = {"name": author[i], "produce": produce[i], "num": num[i], "src": src[i],"bg_time":bg_time[i],"ed_time":ed_time[i],"zi":zi_list[i],"hao":hao_list[i]} CreateNode(graph, author_label, attr1) print("創建詩人：" + author[i] + "成功！！") attr2={"name":desty[i]} if MatchNode(graph,desty_label,attr2)==None: CreateNode(graph,desty_label,attr2) print("創建朝代："+desty[i]+"成功！！") #創建關系
m_r_name1 = "朝代" reValue1 = CreateRelationship(graph, author_label, attr1, desty_label, attr2, m_r_name1) print("創建關系："+author[i]+"-所屬朝代-"+desty[i]+"成功") m_r_name2 = "包含" reValue2 = CreateRelationship(graph,desty_label, attr2, author_label, attr1, m_r_name2) print("創建關系：" + desty[i] + "-包含-" + author[i] + "成功") if __name__ == '__main__': create_author()
展示
詩人好友關系構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): #根絕節點name屬性，查找節點
m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_friend(): file = 'data2/friend_ming.xlsx'
# 獲取詩詞內容
data = pd.read_excel(file).fillna("無") author=list(data.author) friend=list(data.friend) author_label='author'
for i in range(len(author)): print("第" + str(i) + "個") attr1 = {"name": author[i]} if MatchNode(graph, author_label, attr1) != None: friend_list=friend[i].split(',') for it in friend_list: attr2 = {"name": it} if MatchNode(graph, author_label, attr2) != None and it!=author[i]: # 創建關系
m_r_name1 = "好友" reValue1 = CreateRelationship(graph, author_label, attr1, author_label, attr2, m_r_name1) print("創建關系：" + author[i] + "-好友-" + it + "成功") m_r_name2 = "好友" reValue2 = CreateRelationship(graph, author_label, attr2, author_label, attr1, m_r_name2) print("創建關系：" + it + "-好友-" + author[i] + "成功") if __name__ == '__main__': create_friend()
展示
詩人合稱實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') def create_common_name(): file = './data2/common_name.xlsx' data = pd.read_excel(file).fillna("無") hc=list(data.hc) author=list(data.author) common_name_label="common_name" author_label="author"
for i in range(len(hc)): common_name=hc[i] authors=author[i].split(',') attr1={"name":common_name} CreateNode(graph, common_name_label, attr1) print("創建合稱："+common_name+"成功！！") for it in authors: attr2={"name":it} # 創建關系
m_r_name1 = "合稱" reValue1 = CreateRelationship(graph, author_label, attr2, common_name_label, attr1, m_r_name1) print("創建關系：" + it + "-合稱-" + common_name + "成功") # 創建關系
m_r_name2 = "包含" reValue2 = CreateRelationship(graph,common_name_label, attr1, author_label, attr2, m_r_name2) print("創建關系：" + common_name + "-包含-" + it+ "成功") if __name__ == '__main__': create_common_name()
展示
詩人事跡實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): #根絕節點name屬性，查找節點
m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') #獲取指定文件夾下的excel
import os def get_filename(path,filetype): # 輸入路徑、文件類型例如'.xlsx'
name = [] for root,dirs,files in os.walk(path): for i in files: if os.path.splitext(i)[1]==filetype: name.append(i) return name # 輸出由有后綴的文件名組成的列表
def read_real_where_name(): file='data2/gu_jin_lng_lat.xlsx' data=pd.read_excel(file) gu_name=list(data.gu_name) return gu_name def read_where(author,file,gu_name): data=pd.read_excel(file) date=list(data.data) where_name=list(data.wheres) things=list(data.things) for i in range(len(date)): #處理地區，滿足我們需要的地區條件
where_list=where_name[i].split(',') for it in where_list: if it in gu_name and it!='無': attr1={"name":things[i],"date":date[i],"where_name":where_name[i]} CreateNode(graph, things_label, attr1) print("創建事件：" + things[i] + "-成功！！") attr2 = {"name": author} # 創建關系
m_r_name1 = "事跡" reValue1 = CreateRelationship(graph, author_label, attr2, things_label, attr1, m_r_name1) print("創建關系：" + author + "-事跡-" + things[i] + "-成功") break
if __name__ == '__main__': file = 'author/' lists = get_filename(file, '.xlsx') gu_name = read_real_where_name() author_label='author' things_label='things'
for it in lists: newfile = file + it print(newfile) author = it.split('.')[0] print(author) read_where(author,newfile,gu_name)
展示
詩人軌跡地點實體構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): #根絕節點name屬性，查找節點
m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') #獲取指定文件夾下的excel
import os def get_filename(path,filetype): # 輸入路徑、文件類型例如'.xlsx'
name = [] for root,dirs,files in os.walk(path): for i in files: if os.path.splitext(i)[1]==filetype: name.append(i) return name # 輸出由有后綴的文件名組成的列表
def read_real_where_name(): file='data2/gu_jin_lng_lat.xlsx' data=pd.read_excel(file) gu_name=list(data.gu_name) return gu_name def read_gu_dict(): file = 'data2/gu_jin_lng_lat.xlsx' data = pd.read_excel(file) gu_name = list(data.gu_name) jin_name=list(data.jin_name) lng=list(data.lng) lat=list(data.lat) gu_dict={} for i in range(len(gu_name)): gu=gu_name[i] gu_dict[gu]={"jin_name":jin_name[i],"lng":lng[i],"lat":lat[i]} return gu_dict def read_where(author,file,gu_name): data=pd.read_excel(file) wheres=data.wheres real_where=[] for i in range(len(wheres)): where_name=wheres[i] where_list=where_name.split(',') for it in where_list: if it in gu_name and it!='無': real_where.append(it) real_where=list(set(real_where)) if len(real_where)!=0: for it in real_where: jin=gu_dict[it]['jin_name'] lat=gu_dict[it]['lat'] lng=gu_dict[it]['lng'] attr1 = {"name":it,"jin_name": jin,"lng":lng,"lat":lat} CreateNode(graph, where_name_label, attr1) print("創建地點：" + it + "成功！！") attr2 = {"name": author} # 創建關系
m_r_name1 = "軌跡" reValue1 = CreateRelationship(graph, author_label, attr2, where_name_label, attr1, m_r_name1) print("創建關系：" + author + "-軌跡-" + it + "成功") if __name__ == '__main__': file = 'author/' lists = get_filename(file, '.xlsx') gu_name = read_real_where_name() gu_dict = read_gu_dict() author_label='author' where_name_label='where_name'
for it in lists: newfile = file + it print(newfile) author = it.split('.')[0] read_where(author,newfile, gu_name)
展示
詩詞實體關系構建
import pandas as pd import numpy as np import re from py2neo import Node,Relationship,Graph,NodeMatcher,RelationshipMatcher # 創建節點
def CreateNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() #print(re_value)
if re_value is None: m_mode = Node(m_label,**m_attrs) n = graph.create(m_mode) return n return None # 查詢節點
def MatchNode(m_graph,m_label,m_attrs): m_n="_.name="+"\'"+m_attrs['name']+"\'" matcher = NodeMatcher(m_graph) re_value = matcher.match(m_label).where(m_n).first() return re_value # 創建關系
def CreateRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph,m_label1,m_attrs1) reValue2 = MatchNode(m_graph,m_label2,m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1,m_r_name,reValue2) n = graph.create(m_r) return n #查找關系
def findRelationship(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False m_r = Relationship(reValue1, m_r_name['name'], reValue2) return m_r def updateRelation(m_graph,m_label1,m_attrs1,m_label2,m_attrs2,m_r_name): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) reValue2 = MatchNode(m_graph, m_label2, m_attrs2) if reValue1 is None or reValue2 is None: return False print(m_r_name) propertyes={'value': m_r_name['value'], 'danwei': m_r_name['danwei']} m_r = Relationship(reValue1, m_r_name['name'], reValue2,**propertyes) graph.merge(m_r) #修改節點屬性
def updateNode(m_graph,m_label1,m_attrs1,new_attrs): reValue1 = MatchNode(m_graph, m_label1, m_attrs1) if reValue1 is None: return False reValue1.update(new_attrs) graph.push(reValue1) graph = Graph('http://localhost:7474',username='neo4j',password='fengge666') #獲取指定文件夾下的excel
import os def get_filename(path,filetype): # 輸入路徑、文件類型例如'.xlsx'
name = [] for root,dirs,files in os.walk(path): for i in files: if os.path.splitext(i)[1]==filetype: name.append(i) return name # 輸出由有后綴的文件名組成的列表
def create_poem(): file = 'data/' lists = get_filename(file, '.xlsx') for it in lists: newfile = file + it print(newfile) # 獲取詩詞內容
data = pd.read_excel(newfile).fillna("無") title=list(data.title) desty=list(data.desty) author=list(data.author) content=list(data.content) trans_content=list(data.trans_content) background=list(data.background) tag=list(data.tag) formal=list(data.formal) date=list(data.data) ci_name=list(data.ci_name) qu_name=list(data.qu_name) poem_label='poem' author_label='author' desty_label='desty' formal_label='formal' tag_label='tag' cipai_label='ci_pai' qupai_label='qu_pai'
for i in range(len(title)): print("第"+str(i)+"個") attr1 = {"name": title[i], "content": content[i], "trans_content": trans_content[i], "background": background[i],"date":date[i]} CreateNode(graph, poem_label, attr1) print("創建詩詞：" + title[i] + "成功！！") if tag[i]!='無': tag_list=tag[i].split(',') for it in tag_list: attr2={"name":it} # 創建關系
m_r_name1 = "分類" reValue1 = CreateRelationship(graph, poem_label, attr1, tag_label, attr2, m_r_name1) print("創建關系：" + title[i] + "-所屬類別-" + it + "成功") m_r_name2 = "包含" reValue2 = CreateRelationship(graph, tag_label, attr2, poem_label, attr1, m_r_name2) print("創建關系：" + it + "-包含-" + title[i] + "成功") if formal[i]!='無': attr2={"name":formal[i]} # 創建關系
m_r_name1 = "形式" reValue1 = CreateRelationship(graph, poem_label, attr1, formal_label, attr2, m_r_name1) print("創建關系：" + title[i] + "-所屬形式-" + formal[i] + "成功") m_r_name2 = "包含" reValue2 = CreateRelationship(graph, formal_label, attr2, poem_label, attr1, m_r_name2) print("創建關系：" + formal[i] + "-包含-" + title[i] + "成功") if ci_name[i]!='無': attr2 = {"name": ci_name[i]} if MatchNode(graph, cipai_label, attr2) == None: CreateNode(graph, cipai_label, attr2) print("創建詞牌名：" + ci_name[i] + "成功！！") # 創建關系
m_r_name1 = "詞牌名" reValue1 = CreateRelationship(graph, poem_label, attr1, cipai_label, attr2, m_r_name1) print("創建關系：" + title[i] + "-詞牌名-" + ci_name[i] + "成功") m_r_name2 = "包含" reValue2 = CreateRelationship(graph, cipai_label, attr2, poem_label, attr1, m_r_name2) print("創建關系：" + ci_name[i] + "-包含-" + title[i] + "成功") if qu_name[i]!='無': attr2 = {"name": qu_name[i]} if MatchNode(graph, qupai_label, attr2) == None: CreateNode(graph, qupai_label, attr2) print("創建曲牌名：" + qu_name[i] + "成功！！") # 創建關系
m_r_name1 = "曲牌名" reValue1 = CreateRelationship(graph, poem_label, attr1, qupai_label, attr2, m_r_name1) print("創建關系：" + title[i] + "-曲牌名-" + qu_name[i] + "成功") m_r_name2 = "包含" reValue2 = CreateRelationship(graph, qupai_label, attr2, poem_label, attr1, m_r_name2) print("創建關系：" + qu_name[i] + "-包含-" + title[i] + "成功") if author[i]!='無': #創建作者寫作關系
attr2={"name":author[i]} if MatchNode(graph,author_label,attr2)!=None: #創建關系
m_r_name1 = "寫作" reValue1 = CreateRelationship(graph, author_label, attr2, poem_label, attr1, m_r_name1) print("創建關系："+author[i]+"-寫作-"+title[i]+"成功") m_r_name2 = "作者" reValue2 = CreateRelationship(graph,poem_label, attr1, author_label, attr2, m_r_name2) print("創建關系：" + title[i] + "-作者-" + author[i] + "成功") if desty[i]!='無': attr2 = {"name": desty[i]} if MatchNode(graph, desty_label, attr2) == None: CreateNode(graph, desty_label, attr2) print("創建朝代：" + desty[i] + "成功！！") # 創建關系
m_r_name1 = "朝代" reValue1 = CreateRelationship(graph, poem_label, attr1, desty_label, attr2, m_r_name1) print("創建關系：" + title[i] + "-所屬朝代-" + desty[i] + "成功") m_r_name2 = "包含詩詞" reValue2 = CreateRelationship(graph, desty_label, attr2, poem_label, attr1, m_r_name2) print("創建關系：" + desty[i] + "-包含-" + title[i] + "成功") if __name__ == '__main__': create_poem()
展示
總結
實體關系構建完成，基本的古詩詞關系理清，之后可以進行相關的網頁展示。
整個關系結構圖，如下所示：
