TweetDataset

TweetDataset.py

import torch
from torch.utils.data import Dataset
import json


class TweetDataset(Dataset):
    def __init__(self, path, device):
        self.device = device

        # Load the JSON file containing our pre-processed data
        with open(path, 'r') as fp:
            self.data = json.load(fp)

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

    def __getitem__(self, item):
        # Return four different tensors (3 inputs and the label)
        ids, att, tokens, labels = list(map(lambda o: torch.tensor(o).to(self.device), self.data[item]))

        return ids.long(), att.float(), tokens.long(), labels.long()