torchsig.transforms.metadata_transforms.MetadataTransform

class torchsig.transforms.metadata_transforms.MetadataTransform(required_metadata: list[str] = [], **kwargs)

Bases: Transform

Base class for metadata transforms.

This class defines the basic structure of a metadata 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.

__validate(metadata)

Validates the signal metadata before applying the transform.

__apply(metadata)

Applies the target transform to the metadata. Should be overridden by subclasses.

__call__(signal)

Applies the transform to a list of signal metadata dictionaries.

__str__()

Returns the string representation of the transform.

__repr__()

Returns a detailed string representation of the transform object.

Methods

add_parent	Add parent Seedable object and set up RNGs accordingly.
get_distribution	Create distribution function with proper seeding.
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_from_parent	Update numpy and torch number generators with parent seed.

__init__(required_metadata: list[str] = [], **kwargs) → None

Initialize the MetadataTransform.

Parameters:

• required_metadata – List of metadata fields required for applying the target transform.

• **kwargs – Additional keyword arguments passed to the parent class.

__call__(signal: Signal) → Signal

Applies the target transform to a list of signal metadata.

Parameters:

signal – The signal to transform.

Returns:

The transformed signal.

__repr__() → str

Returns a detailed string representation of the transform object.

Returns:

A string representation of the transform object.

__str__() → str

String representation of the transform.

Returns:

String representation of the transform.

add_parent(parent: Seedable, register: bool = True) → None

Add parent Seedable object and set up RNGs accordingly.

Parameters:

• parent – Parent Seedable object to add.

• register – If True (default), add self to parent.children so that future seed propagation reaches this object. Pass False for transient objects (e.g. per-sample Signal instances) that only need the parent link for metadata/RNG access during their lifetime but must not accumulate in the parent’s child list, which would otherwise cause unbounded memory growth.

get_distribution(params: list | tuple | float, scaling: str = 'linear') → Distribution

Create distribution function with proper seeding.

Parameters:

• params – Parameters for distribution.

• scaling – Scaling param for distribution. Defaults to ‘linear’.

Returns:

Distribution function, seeded.

Return type:

Distribution

get_second_seed(seed: int) → int

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

Parameters:

seed – Seed to use.

Returns:

New seed.

seed(seed: int) → None

Seed number generators with given seed.

Parameters:

seed – Seed to use.

setup_rngs() → None

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

update_from_parent() → None

Update numpy and torch number generators with parent seed.