IDSDataset

import torchvision
import numpy as np
from torchvision import transforms
import torch
from torch.utils.data import Dataset
from torch.utils.data import Subset
from sklearn.model_selection import train_test_split
import avalanche
from avalanche.benchmarks.generators import nc_scenario, ni_scenario

class IDSDataset(Dataset):

    def __init__(self,transform=None):
        self.path_ds = '../data/dataset.npy'
        self.path_lab = '../data/labels.npy'
        self.ds = np.load(self.path_ds)

        self.label = np.load(self.path_lab)
        self.n_samples= len(self.ds)
        self.transform = transform

    def __len__(self):
        return self.n_samples

    def __getitem__(self,index):
        sample = self.ds[index],int(self.label[index,0])
        if self.transform:
            sample=self.transform(sample)
        return sample

class ToTensor:
    # Convert ndarrays to Tensors
    def __call__(self, sample):
        inputs, target = sample
        all_inputs_normalised = (inputs - inputs.min(axis=0))/(inputs.max(axis=0)-inputs.min(axis=0)+1e-5)
        # converts inputs to tensors
        return torch.Tensor(all_inputs_normalised), target

def train_val_dataset(dataset, val_split=0.33):
    train_idx, val_idx = train_test_split(list(range(len(dataset))), test_size=val_split,random_state=42)
    return Subset(dataset,train_idx),Subset(dataset,val_idx)


def IDS():
    whole = IDSDataset(transform=ToTensor())
    train_dataset, val_dataset = train_val_dataset(whole)
    return train_dataset, val_dataset

train_dataset,val_dataset = IDS()

print(f'''Type check here: Type of train_dataset: {type(train_dataset)}",
Type of inputs: {type(train_dataset[0][0])}, Type or Targets: {type(train_dataset[0][1])} \n One sample of TrainingData: \n {train_dataset[0]}''')

scenario = nc_scenario(
    train_dataset, val_dataset, n_experiences=15, shuffle=True, seed=1234,
    task_labels=False
)
train_stream = scenario.train_stream

for experience in train_stream:
    t = experience.task_label
    exp_id = experience.current_experience
    training_dataset = experience.dataset
    print('Task {} batch {} -> train'.format(t, exp_id))
    print('This batch contains', len(training_dataset), 'patterns')