-
大小: 30KB文件類型: .zip金幣: 2下載: 0 次發布日期: 2021-05-14
- 語言: Python
- 標簽:
資源簡介
利用pandas將excel中數據抽取,以三元組形式加載到neo4j數據庫中構建相關知識圖譜

代碼片段和文件信息
#?-*-?coding:?utf-8?-*-
from?invoice_data.dataToNeo4jClass.DataToNeo4jClass?import?DataToNeo4j
import?os
import?pandas?as?pd
#?提取excel表格中數據,將其轉換成dateframe類型
os.chdir(‘xxxx‘)
invoice_data?=?pd.read_excel(‘./Invoice_data_Demo.xls‘?header=0?encoding=‘utf8‘)
print(invoice_data)
def?data_extraction():
????“““節點數據抽取“““
????#?取出發票名稱到list
????node_list_key?=?[]
????for?i?in?range(0?len(invoice_data)):
????????node_list_key.append(invoice_data[‘發票名稱‘][i])
????#?去除重復的發票名稱
????node_list_key?=?list(set(node_list_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)):
????????????#?取出表頭名稱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))
????#?將list中浮點及整數類型全部轉成string類型
????node_list_value?=?[str(i)?for?i?in?node_list_value]
????return?node_list_key?node_list_value
def?relation_extraction():
????“““聯系數據抽取“““
????links_dict?=?{}
????name_list?=?[]
????relation_list?=?[]
????name2_list?=?[]
????for?i?in?range(0?len(invoice_data)):
????????m?=?0
????????name_node?=?invoice_data[invoice_data.columns[m]][i]
????????while?m?????????????relation_list.append(invoice_data.columns[m+1])
????????????name2_list.append(invoice_data[invoice_data.columns[m+1]][i])
????????????name_list.append(name_node)
????????????m?+=?1
????#?將數據中int類型全部轉成string
????name_list?=?[str(i)?for?i?in?name_list]
????name2_list?=?[str(i)?for?i?in?name2_list]
????#?整合數據,將三個list整合成一個dict
????links_dict[‘name‘]?=?name_list
????links_dict[‘relation‘]?=?relation_list
????links_dict[‘name2‘]?=?name2_list
????#?將數據轉成Dataframe
????df_data?=?pd.Dataframe(links_dict)
????return?df_data
#?實例化對象
data_extraction()
relation_extraction()
create_data?=?DataToNeo4j()
create_data.create_node(data_extraction()[0]?data_extraction()[1])
create_data.create_relation(relation_extraction())
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\
?????文件????????1262??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\README.md
?????文件??????????30??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\__init__.py
?????目錄???????????0??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\__pycache__\
?????文件?????????181??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\__pycache__\__init__.cpython-36.pyc
?????目錄???????????0??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\data\
?????文件???????51200??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\data\Invoice_data_Demo.xls
?????目錄???????????0??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\dataToNeo4jClass\
?????文件????????1377??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\dataToNeo4jClass\DataToNeo4jClass.py
?????文件??????????30??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\dataToNeo4jClass\__init__.py
?????目錄???????????0??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\dataToNeo4jClass\__pycache__\
?????文件????????1589??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\dataToNeo4jClass\__pycache__\DataToNeo4jClass.cpython-36.pyc
?????文件?????????198??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\dataToNeo4jClass\__pycache__\__init__.cpython-36.pyc
?????文件????????2210??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\invoice_neo4j.py
?????目錄???????????0??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\jieba_code\
?????文件????????4372??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\jieba_code\doubt.txt
?????文件????????2252??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\jieba_code\jieba_doubt.py
?????文件?????????753??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\jieba_code\jieba_interface.py
?????文件????????6490??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\neo4j_matrix.py
?????文件????????2544??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\neo4j_to_datafr
?????文件?????????632??2019-07-19?09:50??neo4j-python-pandas-py2neo-v3-master\requirements.txt
評論
共有 條評論