CustomTextDataset.py

class CustomTextDataset(Dataset):
    '''
    Simple Dataset initializes with X and y vectors
    We start by sorting our X and y vectors by sequence lengths
    '''
    def __init__(self,X,y=None):
        self.data = list(zip(X,y))
        # Sort by length of first element in tuple
        self.data = sorted(self.data, key=lambda x: len(x[0]))
        
    def __len__(self):
        return len(self.data)

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