continuous

Parameters that can be sampled continuously between a minimum and maximum

Classes

Param_Continuous(name, min, max[, ...])	Represents a continuous parameter.
Param_Observational(name, min, max[, ...])	This is an observational numeric variable that is used for fitting but is not leveraged during optimization

class obsidian.parameters.continuous.Param_Continuous(name: str, min: int | float, max: int | float, search_min: int | float | None = None, search_max: int | float | None = None)

Bases: Parameter

Represents a continuous parameter.

name

The name of the parameter.

Type:

str

min

The minimum value of the parameter.

Type:

int or float

max

The maximum value of the parameter.

Type:

int or float

Properties:

range (int): The range of the parameter (max - min).

decode(X)

Decode parameter from transformed space

encode(X)

Encode parameter to a format that can be used for training

open_search()

Set the search space to the parameter space

property range

The range of the parameter (max - min)

set_search(search_min: int | float, search_max: int | float)

Set the search space for the parameter

Parameters:

• search_min (int or float) – The minimum value of the search space.

• search_max (int or float) – The maximum value of the search space.

class obsidian.parameters.continuous.Param_Observational(name: str, min: int | float, max: int | float, search_min: int | float | None = None, search_max: int | float | None = None, design_point: int | float | None = None)

Bases: Param_Continuous

This is an observational numeric variable that is used for fitting but is not leveraged during optimization

name

The name of the parameter.

Type:

str

min

The minimum value of the parameter.

Type:

int or float

max

The maximum value of the parameter.

Type:

int or float

design_point

The point which the observational value will be locked to during experiment optimization

Type:

int or float