ABSA-PyTorch/data_utils.py at master · uveges/ABSA-PyTorch · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
import os
import pickle

import numpy as np
from torch.utils.data import Dataset
from transformers import AutoTokenizer


def build_tokenizer(fnames, max_seq_len, dat_fname):
    if os.path.exists(dat_fname):
        print('loading tokenizer:', dat_fname)
        tokenizer = pickle.load(open(dat_fname, 'rb'))
    else:
        text = ''
        for fname in fnames:
            fin = open(fname, 'r', encoding='utf-8', newline='\n', errors='ignore')
            lines = fin.readlines()
            fin.close()
            for i in range(0, len(lines), 3):
                text_left, _, text_right = [s.lower().strip() for s in lines[i].partition("$T$")]
                aspect = lines[i + 1].lower().strip()
                text_raw = text_left + " " + aspect + " " + text_right
                text += text_raw + " "

        tokenizer = Tokenizer(max_seq_len)
        tokenizer.fit_on_text(text)
        pickle.dump(tokenizer, open(dat_fname, 'wb'))
    return tokenizer


def pad_and_truncate(sequence, maxlen, dtype='int64', padding='post', truncating='post', value=0):
    x = (np.ones(maxlen) * value).astype(dtype)
    if truncating == 'pre':
        trunc = sequence[-maxlen:]
    else:
        trunc = sequence[:maxlen]
    trunc = np.asarray(trunc, dtype=dtype)
    if padding == 'post':
        x[:len(trunc)] = trunc
    else:
        x[-len(trunc):] = trunc
    return x


class Tokenizer(object):
    def __init__(self, max_seq_len, lower=True):
        self.lower = lower
        self.max_seq_len = max_seq_len
        self.word2idx = {}
        self.idx2word = {}
        self.idx = 1

    def fit_on_text(self, text):
        if self.lower:
            text = text.lower()
        words = text.split()
        for word in words:
            if word not in self.word2idx:
                self.word2idx[word] = self.idx
                self.idx2word[self.idx] = word
                self.idx += 1

    def text_to_sequence(self, text, reverse=False, padding='post', truncating='post'):
        if self.lower:
            text = text.lower()
        words = text.split()
        unknownidx = len(self.word2idx)+1
        sequence = [self.word2idx[w] if w in self.word2idx else unknownidx for w in words]
        if len(sequence) == 0:
            sequence = [0]
        if reverse:
            sequence = sequence[::-1]
        return pad_and_truncate(sequence, self.max_seq_len, padding=padding, truncating=truncating)

#tokenizert írom felül azzal a model tokenizerrel amit szeretnék használni
# self.tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-cased')
# self.tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-uncased')
class Tokenizer4Bert:
    def __init__(self, max_seq_len, pretrained_bert_name):
        self.tokenizer = AutoTokenizer.from_pretrained(pretrained_bert_name)
        self.max_seq_len = max_seq_len

    def text_to_sequence(self, text, reverse=False, padding='post', truncating='post'):
        sequence = self.tokenizer.convert_tokens_to_ids(self.tokenizer.tokenize(text))
        if len(sequence) == 0:
            sequence = [0]
        if reverse:
            sequence = sequence[::-1]
        return pad_and_truncate(sequence, self.max_seq_len, padding=padding, truncating=truncating)


class ABSADataset(Dataset):
    def __init__(self, fname, tokenizer):
        fin = open(fname, 'r', encoding='utf-8', newline='\n', errors='ignore')
        lines = fin.readlines()
        fin.close()

        all_data = []
        for i in range(0, len(lines), 3):
            text_left, _, text_right = [s.lower().strip() for s in lines[i].partition("$T$")]
            aspect = lines[i + 1].lower().strip()
            polarity = lines[i + 2].strip()

            text_indices = tokenizer.text_to_sequence(text_left + " " + aspect + " " + text_right)
            context_indices = tokenizer.text_to_sequence(text_left + " " + text_right)
            left_indices = tokenizer.text_to_sequence(text_left)
            left_with_aspect_indices = tokenizer.text_to_sequence(text_left + " " + aspect)
            right_indices = tokenizer.text_to_sequence(text_right, reverse=True)
            right_with_aspect_indices = tokenizer.text_to_sequence(aspect + " " + text_right, reverse=True)
            aspect_indices = tokenizer.text_to_sequence(aspect)
            left_len = np.sum(left_indices != 0)
            aspect_len = np.sum(aspect_indices != 0)
            aspect_boundary = np.asarray([left_len, left_len + aspect_len - 1], dtype=np.int64)
            polarity = int(polarity) + 1

            text_len = np.sum(text_indices != 0)
            concat_bert_indices = tokenizer.text_to_sequence('[CLS] ' + text_left + " " + aspect + " " + text_right + ' [SEP] ' + aspect + " [SEP]")
            concat_segments_indices = [0] * (text_len + 2) + [1] * (aspect_len + 1)
            concat_segments_indices = pad_and_truncate(concat_segments_indices, tokenizer.max_seq_len)

            text_bert_indices = tokenizer.text_to_sequence("[CLS] " + text_left + " " + aspect + " " + text_right + " [SEP]")
            aspect_bert_indices = tokenizer.text_to_sequence("[CLS] " + aspect + " [SEP]")

            data = {
                'concat_bert_indices': concat_bert_indices,
                'concat_segments_indices': concat_segments_indices,
                'text_bert_indices': text_bert_indices,
                'aspect_bert_indices': aspect_bert_indices,
                'text_indices': text_indices,
                'context_indices': context_indices,
                'left_indices': left_indices,
                'left_with_aspect_indices': left_with_aspect_indices,
                'right_indices': right_indices,
                'right_with_aspect_indices': right_with_aspect_indices,
                'aspect_indices': aspect_indices,
                'aspect_boundary': aspect_boundary,
                'polarity': polarity,
            }

            all_data.append(data)
        self.data = all_data

    def __getitem__(self, index):
        return self.data[index]

    def __len__(self):
        return len(self.data)