Dataset Handlers

Researcher supplied Python modules that contain a dataset class (to handle processing, splitting, etc.) that are passed to the sacroml.attacks.target.Target must implement one of these abstract classes.

Scikit-learn models that use numpy arrays should implement SklearnDataHandler.

PyTorch models that use DataLoaders should implement PyTorchDataHandler.

API Reference

Abstract data handler supporting both PyTorch and scikit-learn.

class sacroml.attacks.data.BaseDataHandler

Base data handling interface.

abstract __init__() → None

Instantiate a data handler.

class sacroml.attacks.data.PyTorchDataHandler

PyTorch dataset handling interface.

Methods

get_dataloader(dataset, indices[, ...])	Return a data loader with a requested subset of samples.
get_dataset()	Return a processed dataset.
get_raw_dataset()	Return a raw unprocessed dataset.

abstract __init__() → None

Instantiate a data handler.

abstract get_dataloader(dataset: Dataset, indices: Sequence[int], batch_size: int = 32, shuffle: bool = False) → DataLoader

Return a data loader with a requested subset of samples.

Parameters:

datasetDataset

A (processed) PyTorch dataset.

indicesSequence[int]

The indices to load from the dataset.

batch_sizeint

The batch_size to sample the dataset.

shufflebool

Whether to shuffle the data.

Returns:

DataLoader

A PyTorch DataLoader.

abstract get_dataset() → Dataset

Return a processed dataset.

Returns:

Dataset

A (processed) PyTorch dataset.

abstract get_raw_dataset() → Dataset | None

Return a raw unprocessed dataset.

Returns:

Dataset | None

An unprocessed PyTorch dataset.

class sacroml.attacks.data.SklearnDataHandler

Scikit-learn data handling interface.

Methods

get_data()	Return the processed data arrays.
get_raw_data()	Return the original unprocessed data arrays.
get_subset(X, y, indices)	Return a subset of the data.

abstract __init__() → None

Instantiate a data handler.

abstract get_data() → tuple[ndarray, ndarray]

Return the processed data arrays.

Returns:

tuple[np.ndarray, np.ndarray]

Features (X) and targets (y) as numpy arrays.

abstract get_raw_data() → tuple[ndarray, ndarray] | None

Return the original unprocessed data arrays.

Returns:

tuple[np.ndarray, np.ndarray] | None

Features (X) and targets (y) as numpy arrays.

abstract get_subset(X: ndarray, y: ndarray, indices: Sequence[int]) → tuple[ndarray, ndarray]

Return a subset of the data.

Parameters:

Xnp.ndarray

Feature array.

ynp.ndarray

Target array.

indicesSequence[int]

The indices to extract.

Returns:

tuple[np.ndarray, np.ndarray]

Subset of features and targets.