torchsig.transforms.target_transforms.TargetTransform

class torchsig.transforms.target_transforms.TargetTransform(**kwargs)

Bases: Transform

Target Transform base class

This class defines the basic structure of a target transform, which includes: - The ability to validate metadata before applying the transform. - A method for applying the transform on signal metadata. - A callable interface to apply the transform to a list of signal metadata.

required_metadata

List of metadata fields required for applying the target transform.

Type:

List[str]

targets_metadata

List of target metadata fields to be added to output of target transform.

Type:

List[str]

__validate(metadata

Dict[str, Any]) -> Dict[str, Any]: Validates the signal metadata before applying the transform.

__apply(metadata

Dict[str, Any]) -> Dict[str, Any]: Applies the target transform to the metadata. Should be overridden by subclasses.

__call__(metadatas

List[Dict[str, Any]], enable_verify: bool = True) -> List[Dict[str, Any]]: Applies the transform to a list of signal metadata dictionaries.

__str__() → str

Returns the string representation of the transform.

__repr__() → str

Returns a detailed string representation of the transform object.

Methods

add_parent	Add parent Seedable object and set up RNGs accordingly
get_distribution
get_second_seed	Gets second seed, usually used to seed both torch and numpy generators with slightly different seeds
seed	Seed number generators with given seed.
setup_rngs	Initialize torch and numpy number generators, and update its children.
update	Update bookeeping for signals
update_from_parent	Update numpy and torch number generators with parent seed

__init__(**kwargs) → None

Transform initialization as Seedable.

__call__(metadatas: List[Dict[str, Any]], enable_verify=True) → List[Any] | Dict[str, Any]

Applies the target transform to a list of signal metadata.

Parameters:

• metadatas (List[Dict[str, Any]]) – The list of metadata dictionaries to transform.

• enable_verify (bool, optional) – Whether to verify metadata before transforming. Defaults to True.

Returns:

The transformed list of metadata dictionaries.

Return type:

List[Dict[str, Any]]

__str__() → str

Return str(self).

__repr__() → str

Transform string representation. Should be able to recreate class from this string.

Returns:

Transform representation.

Return type:

str

add_parent(parent) → None

Add parent Seedable object and set up RNGs accordingly

get_second_seed(seed: int) → int

Gets second seed, usually used to seed both torch and numpy generators with slightly different seeds

Parameters:

seed (int) – Seed to use.

Returns:

New seed.

Return type:

int

seed(seed: int) → None

Seed number generators with given seed.

Parameters:

seed (int) – Seed to use.

setup_rngs() → None

Initialize torch and numpy number generators, and update its children.

update(signal: Signal | DatasetSignal) → None

Update bookeeping for signals

Parameters:

signal (Signal | DatasetSignal) – signal to update metadata.

Raises:

NotImplementedError – Inherited classes must override this method.

update_from_parent() → None

Update numpy and torch number generators with parent seed