BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/product/data_util.py

#!/usr/bin/python3
# -*- coding: utf-8 -*-
# @Author  : bidikeji
# @Time    : 2021/1/13 0013 14:19
import re
import math
import random
import numpy as np
from BiddingKG.dl.common.Utils import getVocabAndMatrix,getModel_word,viterbi_decode

id_to_tag = {0:'O',1:'B',2:'I',3:'E'}
word_model = getModel_word()
vocab, matrix = getVocabAndMatrix(word_model, Embedding_size=60)
word2id = {k: v for v, k in enumerate(vocab)}
max_id = len(vocab)


def get_label_data():
    import psycopg2
    conn = psycopg2.connect(dbname='iepy_product', user='postgres', password='postgres', host='192.168.2.101')
    cursor = conn.cursor()
    sql = "select human_identifier, text from corpus_iedocument where edittime NOTNULL AND jump_signal=0 \
      and creation_date > to_timestamp('2021-01-14 00:00:00','yyyy-MM-dd HH24:mi:ss');"
    cursor.execute(sql)
    writer = open('label_data.txt', 'w', encoding='utf-8')
    datas = []
    for row in cursor.fetchall():
        docid = row[0]
        text = row[1]
        # string = list(text)
        tags = [0]*len(text)
        sql_lb = "select b.value from brat_bratannotation as b where document_id = '{}' and b.value like 'T%product%';".format(docid)
        cursor.execute(sql_lb)
        for row_lb in cursor.fetchall():
            label = row_lb[0]
            _, _, begin, end, _ = re.split('\s',label)
            begin = int(begin)
            end = int(end)
            if end-begin>=2:
                tags[begin]=1
                tags[end-1]=3
                for i in range(begin+1,end-1):
                    tags[i]=2
        # datas.append([string, tags])
        text_sentence = []
        ids_sentence = []
        tag_sentence = []
        for i in range(len(text)):
            text_sentence.append(text[i])
            ids_sentence.append(word2id.get(text[i], max_id))
            tag_sentence.append(tags[i])
            writer.write("%s\t%s\n"%(text[i],tags[i]))
            if text[i] in ['。','?','!','；']:
                writer.write('\n')
                if text_sentence:
                    if len(text_sentence) > 100:
                    # if len(text_sentence)>5 and len(text_sentence)<1000:
                        datas.append([text_sentence, ids_sentence,tag_sentence])
                    elif len(text_sentence) > 5:
                        continue
                    else:
                        print('单句小于5或大于100，句子长度为：%d,文章ID：%s'%(len(text_sentence), docid))
                    text_sentence = []
                    ids_sentence = []
                    tag_sentence = []
        if text_sentence:
            if len(text_sentence) > 5:
            # if len(text_sentence) > 5 and len(text_sentence) < 1000:
                datas.append([text_sentence, ids_sentence, tag_sentence])
            else:
                print('单句小于5或大于100，句子长度为：%d,文章ID：%s' % (len(text_sentence), docid))
    writer.close()
    return datas

def input_from_line(line):
    string = list(line)
    ids = [word2id.get(k, max_id) for k in string]
    tags = []
    return [[string], [ids], [tags]]

def process_data(sentences):
    '''
    字符串数字化并统一长度
    :param sentences: 文章分句字符串列表['招标公告','招标代理']
    :return: 数字化后的统一长度
    '''
    maxLen = max([len(sentence) for sentence in sentences])
    tags = [[word2id.get(k, max_id) for k in sentence] for sentence in sentences]
    pad_tags = [tag[:maxLen]+[0]*(maxLen-len(tag)) for tag in tags]
    return pad_tags

def get_ner(BIE_tag):
    ner = set()
    for it in re.finditer('BI*E',BIE_tag):
        ner.add((it.start(),it.end()))
    return ner

def decode(logits, lengths, matrix):
    paths = []
    small = -1000.0
    start = np.asarray([[small]*4+[0]])
    for score, length in zip(logits, lengths):
        score = score[:length]
        pad = small * np.ones([length, 1])
        logits = np.concatenate([score, pad], axis=1)
        logits = np.concatenate([start, logits], axis=0)
        path, _  = viterbi_decode(logits, matrix)
        paths.append(path[1:])
    return paths

def result_to_json(line, tags):
    result = []
    ner = []
    tags = ''.join([str(it) for it in tags])
    for it in re.finditer("12*3", tags):
        start = it.start()
        end = it.end()
        ner.append([line[start:end], (start, end)])
    result.append([line, ner])
    print(tags)
    return result


class BatchManager(object):
    def __init__(self, data, batch_size):
        self.batch_data = self.sort_and_pad(data, batch_size)
        self.len_data = len(self.batch_data)

    def sort_and_pad(self, data, batch_size):
        num_batch = int(math.ceil(len(data)/batch_size))
        sorted_data = sorted(data, key=lambda x:len(x[0]))
        print('最小句子长度：%d；最大句子长度：%d' % (len(sorted_data[0][0]), len(sorted_data[-1][0])))  # 临时增加打印句子长度
        batch_data = list()
        for i in range(num_batch):
            batch_data.append(self.pad_data(sorted_data[i*int(batch_size):(i+1)*int(batch_size)]))
        return batch_data

    @staticmethod
    def pad_data(data):
        strings = []
        chars = []
        targets = []
        max_length = max([len(sentence[0]) for sentence in data])
        for line in data:
            string, char, target = line
            padding = [0]*(max_length-len(string))
            strings.append(string + padding)
            chars.append(char + padding)
            targets.append(target + padding)
        return [strings, chars, targets]

    def iter_batch(self, shuffle=False):
        if shuffle:
            random.shuffle(self.batch_data)
        for idx in range(self.len_data):
            yield self.batch_data[idx]