classes.py

import pandas as pd
import torch
from torch.utils.data import DataLoader, Dataset, RandomSampler, SequentialSampler
from transformers import BertTokenizer, BertForSequenceClassification, AdamW, get_linear_schedule_with_warmup
from sklearn.metrics import accuracy_score, f1_score
from sklearn.model_selection import train_test_split
from tqdm import tqdm
import numpy as np
from torch.optim import AdamW
from torch.optim import AdamW as TorchAdamW 
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
import torch.nn.functional as F


class TextDataset(Dataset):
    def __init__(self, texts, labels, tokenizer, max_len):
        self.texts = texts
        self.labels = labels
        self.tokenizer = tokenizer
        self.max_len = max_len
        self.indices = list(range(len(texts))) 

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

    def __getitem__(self, idx):
        text = self.texts[idx]
        label = self.labels[idx]
        index = self.indices[idx]  
        encoding = self.tokenizer.encode_plus(
            text,
            add_special_tokens=True,
            max_length=self.max_len,
            truncation=True,
            padding='max_length',
            return_attention_mask=True,
            return_tensors='pt'
        )
        return {
            'input_ids': encoding['input_ids'].flatten(),
            'attention_mask': encoding['attention_mask'].flatten(),
            'labels': torch.tensor(label, dtype=torch.long),
            'indices': torch.tensor(index, dtype=torch.long) 
        }