python写入csv/xlsx文件--三元组

写入csv文件

import re
import csv
def get_entity_and_ralation_csv(src_preds, src_preds_outputs, tgt):
	f1 = open(src_preds, 'r', encoding='utf-8')
	f2 = open(src_preds_outputs, 'r', encoding='utf-8')
	g = open(tgt, 'w', newline='')#不用写utf-8
	csv_writer = csv.writer(g)
	csv_writer.writerow(["实体","关系","实体"])
	lines_f1 = f1.readlines()
	lines_f2 = f2.readlines()
	file_len = len(lines_f1)
	i = 0
	while i < file_len:
		text = lines_f1[i].strip('\ufeff\n').replace(' ','')
		relation = lines_f2[i],strip('\ufeff\n')
		# e1_start = text.index('<e1>')
		# e2_end = text.index('</e1>')
		# e1_start = text.index('<e2>')
		# e2_end = text.index('</e2>')
		e1 = re.findall(r"<e1>(.+?)</e1>")
		e2 = re.findall(r"<e2>(.+?)</e2>")
		e1 = e1.pop()
		e2 = e2.pop()
		if relation != 'Other':
			csv_writer.writerow([e1,relation,e2])
		
		i += 1

写入xlsx文件

import os
import openpyxl as xl
def get_entity_and_ralation_csv(src_preds, src_preds_outputs, tgt):
	f1 = open(src_preds, 'r', encoding='utf-8')
	f2 = open(src_preds_outputs, 'r', encoding='utf-8')
	
	if os.path.exists(tgt):
		workbook = xl.load_workbook(tgt)
	else:
		workbook = xl.Workbook()
		workbook.save(tgt)
	
	sheet = workbook.active
	headers = ["实体","关系","实体"]
	sheet.append(headers)
	
	lines_f1 = f1.readlines()
	lines_f2 = f2.readlines()
	file_len = len(lines_f1)
	i = 0
	while i < file_len:
		text = lines_f1[i].strip('\ufeff\n').replace(' ','')
		relation = lines_f2[i],strip('\ufeff\n')
		# e1_start = text.index('<e1>')
		# e2_end = text.index('</e1>')
		# e1_start = text.index('<e2>')
		# e2_end = text.index('</e2>')
		e1 = re.findall(r"<e1>(.+?)</e1>")
		e2 = re.findall(r"<e2>(.+?)</e2>")
		e1 = e1.pop()
		e2 = e2.pop()
		data = [e1,relation,e2]
		if relation != 'Other':
			sheet.append(data)
		
		i += 1
	
	workbook.save(tgt)
	f1.close()
	f2.close()

1、src_preds中每行是一句话，其中两个实体分别被特殊字符分割，如：

一种<e1>育苗纸容器机</e1>，包括<e2>导向机构</e2>、分切机构、切虚线机构、印胶机构、甩刀机构和送纸机构。

2、src_preds_outputs每行为一个词，对应src_preds每句话中两个实体的关系，如：

Whole-Component(e1,e2)

3、 tgt存储三元组