jesterTOV.inference.base.transform.NtoMTransform

class NtoMTransform(name_mapping)

Bases: Transform

N-to-M parameter transform (not necessarily invertible).

Note: This class follows the Jim/jimgw architecture. Used for likelihood transforms where you map N parameters to M different parameters without requiring invertibility or Jacobian corrections.

__init__(name_mapping)

Parameters:

name_mapping (tuple[list[str], list[str]]) – Tuple of (input_names, output_names) for the transform.

Methods

__init__(name_mapping)
forward(x)	Push forward the input x to transformed coordinate y.
propagate_name(x)	Propagate parameter names through the transform.

Attributes

transform_func
name_mapping

forward(x)

Push forward the input x to transformed coordinate y.

Parameters:

x (dict[str, Float]) – The input dictionary.

Return type:

dict[str, Float]

Returns:

y (dict[str, Float]) – The transformed dictionary.

transform_func: Callable[[dict[str, Float]], dict[str, Float]]