python 利用已有Ner模型进行数据清洗合并代码

我就废话不多说了，直接上代码吧！

# -*- coding: utf-8 -*-
from kashgari.corpus import DataReader
import re
from tqdm import tqdm


def cut_text(text, lenth):
  textArr = re.findall('.{' + str(lenth) + '}', text)
  textArr.append(text[(len(textArr) * lenth):])
  return textArr


def clean_data(source_file, target_file, ner_model):

  data_x, data_y = DataReader().read_conll_format_file(source_file)

  with tqdm(total=len(data_x)) as pbar:
    for idx, text_array in enumerate(data_x):
      if len(text_array) <= 100:
        ners = ner_model.predict([text_array])
        ner = ners[0]
      else:
        texts = cut_text(''.join(text_array), 100)
        ners = []
        for text in texts:
          ner = ner_model.predict([[char for char in text]])
          ners = ners + ner[0]
        ner = ners     
      # print('[-----------------------', idx, len(data_x))
      # print(data_y[idx])
      # print(ner)

      for jdx, t in enumerate(text_array):
        if ner[jdx].startswith('B') or ner[jdx].startswith('I') :
          if data_y[idx][jdx] == 'O':
            data_y[idx][jdx] = ner[jdx]

      # print(data_y[idx])
      # print('-----------------------]') 
      pbar.update(1)

  f = open(target_file, 'a', encoding="utf-8")  
  for idx, text_array in enumerate(data_x):
    if idx != 0:
      f.writelines(['\n'])  
    for jdx, t in enumerate(text_array):
      text = t + ' ' + data_y[idx][jdx] 
      if idx == 0 and jdx == 0:
        text = text
      else:
        text = '\n' + text
      f.writelines([text])  

  f.close()  

  data_x2, data_y2 = DataReader().read_conll_format_file(source_file)
  print(data_x == data_x2, len(data_y) == len(data_y2), '数据清洗完成')       

# -*- coding: utf-8 -*-
import kashgari
from data_tools import clean_data
time_ner = kashgari.utils.load_model('time_ner.h5')
clean_data('./data/example.dev', 'example.dev', time_ner)

以上这篇python 利用已有Ner模型进行数据清洗合并代码就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持python博客。