Target

Store information about the target model and data.

class sacroml.attacks.target.Target(model: ~typing.Any = None, model_path: str = '', model_module_path: str = '', model_name: str = '', model_params: dict | None = None, train_module_path: str = '', train_params: dict | None = None, dataset_name: str = '', dataset_module_path: str = '', features: dict = <factory>, X_train: ~numpy.ndarray | None = None, y_train: ~numpy.ndarray | None = None, X_test: ~numpy.ndarray | None = None, y_test: ~numpy.ndarray | None = None, X_orig: ~numpy.ndarray | None = None, y_orig: ~numpy.ndarray | None = None, X_train_orig: ~numpy.ndarray | None = None, y_train_orig: ~numpy.ndarray | None = None, X_test_orig: ~numpy.ndarray | None = None, y_test_orig: ~numpy.ndarray | None = None, proba_train: ~numpy.ndarray | None = None, proba_test: ~numpy.ndarray | None = None, safemodel: list = <factory>)

Store information about the target model and data.

Attributes:

modelAny

Trained target model.

model_pathstr

Path to a saved model.

model_module_pathstr

Path to module containing model class.

model_namestr

Class name of model.

model_paramsdict or None

Hyperparameters for instantiating the model.

train_module_pathstr

Path to module containing training function.

train_paramsdict or None

Hyperparameters for training the model.

dataset_namestr

The name of the dataset.

dataset_module_pathstr

Path to module containing dataset loading function.

featuresdict

Dictionary describing the dataset features.

X_trainnp.ndarray or None

The (processed) training inputs.

y_trainnp.ndarray or None

The (processed) training outputs.

X_testnp.ndarray or None

The (processed) testing inputs.

y_testnp.ndarray or None

The (processed) testing outputs.

X_orignp.ndarray or None

The original (unprocessed) dataset inputs.

y_orignp.ndarray or None

The original (unprocessed) dataset outputs.

X_train_orignp.ndarray or None

The original (unprocessed) training inputs.

y_train_orignp.ndarray or None

The original (unprocessed) training outputs.

X_test_orignp.ndarray or None

The original (unprocessed) testing inputs.

y_test_orignp.ndarray or None

The original (unprocessed) testing outputs.

proba_trainnp.ndarray or None

The model predicted training probabilities.

proba_testnp.ndarray or None

The model predicted testing probabilities.

safemodellist

Results of safemodel disclosure checking.

Methods

add_feature(name, indices, encoding)	Add a feature description to the data dictionary.
add_safemodel_results(data)	Add safemodel disclosure checking results.
get_generalisation_error()	Calculate model generalisation error.
has_data()	Return whether the target has all processed data.
has_model()	Return whether the target has a loaded model.
has_probas()	Return whether the target has all probability data.
has_raw_data()	Return whether the target has all raw data.
load([path])	Load target from persistent storage.
load_array(arr_path, attr_name)	Load array from pickle or CSV file.
save([path, ext])	Save target to persistent storage.

__init__(model: ~typing.Any = None, model_path: str = '', model_module_path: str = '', model_name: str = '', model_params: dict | None = None, train_module_path: str = '', train_params: dict | None = None, dataset_name: str = '', dataset_module_path: str = '', features: dict = <factory>, X_train: ~numpy.ndarray | None = None, y_train: ~numpy.ndarray | None = None, X_test: ~numpy.ndarray | None = None, y_test: ~numpy.ndarray | None = None, X_orig: ~numpy.ndarray | None = None, y_orig: ~numpy.ndarray | None = None, X_train_orig: ~numpy.ndarray | None = None, y_train_orig: ~numpy.ndarray | None = None, X_test_orig: ~numpy.ndarray | None = None, y_test_orig: ~numpy.ndarray | None = None, proba_train: ~numpy.ndarray | None = None, proba_test: ~numpy.ndarray | None = None, safemodel: list = <factory>) → None

add_feature(name: str, indices: list[int], encoding: str) → None

Add a feature description to the data dictionary.

add_safemodel_results(data: list) → None

Add safemodel disclosure checking results.

get_generalisation_error() → float

Calculate model generalisation error.

has_data() → bool

Return whether the target has all processed data.

has_model() → bool

Return whether the target has a loaded model.

has_probas() → bool

Return whether the target has all probability data.

has_raw_data() → bool

Return whether the target has all raw data.

load(path: str = 'target') → None

Load target from persistent storage.

load_array(arr_path: str, attr_name: str) → None

Load array from pickle or CSV file.

save(path: str = 'target', ext: str = 'pkl') → None

Save target to persistent storage.

X_orig: ndarray | None = None

X_test: ndarray | None = None

X_test_orig: ndarray | None = None

X_train: ndarray | None = None

X_train_orig: ndarray | None = None

dataset_module_path: str = ''

dataset_name: str = ''

features: dict

model: Any = None

model_module_path: str = ''

model_name: str = ''

model_params: dict | None = None

model_path: str = ''

property n_features: int

Number of features.

proba_test: ndarray | None = None

proba_train: ndarray | None = None

safemodel: list

train_module_path: str = ''

train_params: dict | None = None

y_orig: ndarray | None = None

y_test: ndarray | None = None

y_test_orig: ndarray | None = None

y_train: ndarray | None = None

y_train_orig: ndarray | None = None