def __getitem__()

in code/data_prep.py [0:0]

• 19 lines of code
• 1 McCabe index (conditional complexity)

    def __getitem__(self, item):
        sequence = str(self.sequence[item])
        target = self.targets[item]
        encoding = self.tokenizer.encode_plus(
            sequence,
            truncation=True,
            add_special_tokens=True,
            max_length=self.max_len,
            return_token_type_ids=False,
            padding='max_length',
            return_attention_mask=True,
            return_tensors='pt',
        )
        return {
          'protein_sequence': sequence,
          'input_ids': encoding['input_ids'].flatten(),
          'attention_mask': encoding['attention_mask'].flatten(),
          'targets': torch.tensor(target, dtype=torch.long)
        }