| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111 |
- import os, sys
- import numpy as np
- import re
- import tensorflow as tf
- import jieba
- import gensim
- maxlen = 512
- words_size = 128
- w2v_filepath = os.path.dirname(os.path.abspath(__file__))+"/wiki_128_word_embedding_new.vector"
- model_w2v = gensim.models.KeyedVectors.load_word2vec_format(w2v_filepath, binary=True)
- def get_words_matrix(words):
- if words in model_w2v.key_to_index:
- return model_w2v[words]
- else:
- return model_w2v['unk']
- class ModelRelationExtraction:
- def __init__(self):
- self.model_file = os.path.dirname(os.path.abspath(__file__))+"/models/model_attachment_classify"
- self.sess = tf.compat.v1.Session(graph=tf.Graph())
- self.classes_dict = {
- 0: '其他',
- 1: '招标文件',
- 2: '限价（控制价）',
- 3: '工程量清单',
- 4: '采购清单',
- 5: '评标办法'
- }
- self.get_model()
- def get_model(self):
- with self.sess.as_default() as sess:
- with sess.graph.as_default():
- meta_graph_def = tf.compat.v1.saved_model.loader.load(sess, tags=["serve"], export_dir=self.model_file)
- signature_key = tf.compat.v1.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY
- signature_def = meta_graph_def.signature_def
- input0 = sess.graph.get_tensor_by_name(signature_def[signature_key].inputs["input0"].name)
- print(input0.shape)
- output = sess.graph.get_tensor_by_name(signature_def[signature_key].outputs["outputs"].name)
- self.model = [input0, output]
- return self.model
- def text_process(self, attachmentcon):
- text = attachmentcon
- text = re.sub("\n+", '，', text)
- text = re.sub("\s+|？+", '', text)
- text = re.sub("[\.·_]{2,}", '，', text)
- text = re.sub("_", '', text)
- text = text[:2500]
- tokens = list(jieba.cut(text))
- return tokens
- def evaluate(self, attachmentcon):
- text = str(attachmentcon)
- tokens = self.text_process(text)
- maxlen = 512
- tokens = tokens[:maxlen]
- words_matrix = np.zeros((maxlen, words_size))
- for i in range(len(tokens)):
- words_matrix[i] = np.array(get_words_matrix(tokens[i]))
- words_matrix = np.array([words_matrix])
- pred = limit_run(self.sess, [self.model[1]], feed_dict={self.model[0]: words_matrix})[0]
- pred_label = np.argmax(pred[0])
- cn_label = self.classes_dict[pred_label]
- return pred_label, cn_label
- def limit_run(sess, list_output, feed_dict, max_batch=1024):
- len_sample = 0
- if len(feed_dict.keys()) > 0:
- len_sample = len(feed_dict[list(feed_dict.keys())[0]])
- if len_sample > max_batch:
- list_result = [[] for _ in range(len(list_output))]
- _begin = 0
- while _begin < len_sample:
- new_dict = dict()
- for _key in feed_dict.keys():
- if isinstance(feed_dict[_key], (float, int, np.int32, np.float_, np.float16, np.float32, np.float64)):
- new_dict[_key] = feed_dict[_key]
- else:
- new_dict[_key] = feed_dict[_key][_begin:_begin+max_batch]
- _output = sess.run(list_output,feed_dict=new_dict)
- for _index in range(len(list_output)):
- list_result[_index].extend(_output[_index])
- _begin += max_batch
- else:
- list_result = sess.run(list_output, feed_dict=feed_dict)
- return list_result
- if __name__ == '__main__':
- text = '''招标文件项目编号：SDGP370302202102000110项目名称:淄川经济开发区中心小学校园智能化采购项目采购人:山东淄川经
- 济开发区管理委员会采购代理机构：淄博正益招标有限公司发出日期：2021年8月目录第一章投标邀请7一、项目基本情况7二、申请人的资格要
- 求8三、获取招标文件8四、提交投标文件截止时间、开标时间和地点8五、公告期限9六、其他补充事宜9第二章投标人须知11一、总则161.采
- 购人、采购代理机构及投标人162.资金来源183.投标费用184.适用法律18二、招标文件185.招标文件构成186.招标文件的澄清与修改207.投
- 标截止时间的顺延20三、投标文件的编制208.编制要求209.投标范围及投标文件中标准和计量单位的使用2110.投标文件构成2211.投标报价241
- 2.电子版投标文件2513.投标保证金2614.投标有效期2615.投标文件的签署及规定26四、投标文件的递交2616.投标文件的递交2617.递交
- 投标文件的截止时间2718.投标文件的接收、修改与撤回27五、开标及评标2719.开标2720.资格审查2821.组建评标委员会2922.投标文件符
- 合性审查与澄清3023.投标偏离3224.投标无效3225.比较和评价3326.废标3527.保密要求36六、确定中标3628.中标候选人的确定原则及标
- 准3629.确定中标候选人和中标人3630.采购任务取消3631.中标通知书3632.签订合同3633.履约保证金3734.政府采购融资担保3735.预付
- 款3736.廉洁自律规定3737.人员回避3738.质疑与接收3739.项目其他相关费用3940.合同公示3941.验收4042.履约验收公示4043.招标文
- 件解释权40第三章货物需求41一、项目概述41
- '''
- test_text = re.sub('\n', '', text)
- model = ModelRelationExtraction()
- print(model.evaluate(test_text))
|
