xesn.optim.transform

xesn.optim.transform(params, transformations)

Transform parameters for optimization, with only either log or log10. Parameters with unspecified transformations are untouched.

Parameters:

• parameters (dict) – parameter names and values contain either array/list or value of parameter

• transformations (dict) – with what we want to do to each variable for optimization, e.g. log

Returns:

transformed_params (dict) – with updated parameters based on transformations, or untouched if not specified

Example

>>> params = {"input_factor": 0.5, "adjacency_factor": 0.5, "bias_factor": 0.5}
>>> transforms = {"input_factor": "log", "adjacency_factor": "log10"}
>>> transform(params, transforms)
{'input_factor': -0.6931471805599453,
 'adjacency_factor': -0.3010299956639812,
 'bias_factor': 0.5}