bayes_opt.parameter¶
Parameter classes for Bayesian optimization.
- class bayes_opt.parameter.BayesParameter(name: str, bounds: NDArray[Any]) None¶
Base class for Bayesian optimization parameters.
- Parameters:
name (
str) – The name of the parameter.bounds (NDArray[Any])
- property bounds: ndarray[tuple[Any, ...], dtype[Any]]¶
The bounds of the parameter in float space.
- abstract property dim: int¶
The dimensionality of the parameter.
- abstract property is_continuous: bool¶
Whether the parameter is continuous.
- abstractmethod kernel_transform(value: ndarray[tuple[Any, ...], dtype[floating[Any]]]) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Transform a parameter value for use in a kernel.
- Parameters:
value (
ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value(s) to transform, should be a float.- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray
- random_sample(n_samples: int, random_state: RandomState | int | None) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Generate random samples from the parameter.
- Parameters:
n_samples (
int) – The number of samples to generate.random_state (
RandomState|int|None) – The random state to use for sampling.
- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray – The samples.
- abstractmethod to_float(value: Any) float | ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Convert a parameter value to a float.
- Parameters:
value (
Any) – The value to convert, should be the canonical representation of the parameter.- Return type:
float|ndarray[tuple[Any,...],dtype[floating[Any]]]
- abstractmethod to_param(value: float | ndarray[tuple[Any, ...], dtype[floating[Any]]]) Any¶
Convert a float value to a parameter.
- Parameters:
value (
float|ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value to convert, should be a float.- Return type:
Any- Returns:
Any – The canonical representation of the parameter.
- to_string(value: Any, str_len: int) str¶
Represent a parameter value as a string.
- Parameters:
value (
Any) – The value to represent.str_len (
int) – The maximum length of the string representation.
- Return type:
str- Returns:
str
- class bayes_opt.parameter.CategoricalParameter(name: str, categories: Sequence[Any]) None¶
A parameter with categorical values.
- Parameters:
name (
str) – The name of the parameter.categories (
Sequence[Any]) – The categories of the parameter.
- property dim: int¶
The dimensionality of the parameter.
- property is_continuous: bool¶
Whether the parameter is continuous.
- kernel_transform(value: ndarray[tuple[Any, ...], dtype[floating[Any]]]) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Transform a parameter value for use in a kernel.
- Parameters:
value (
ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value(s) to transform, should be a float.- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray
- random_sample(n_samples: int, random_state: RandomState | int | None) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Generate random float-format samples from the parameter.
- Parameters:
n_samples (
int) – The number of samples to generate.random_state (
RandomState|int|None) – The random state to use for sampling.
- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray – The samples.
- to_float(value: Any) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Convert a parameter value to a float.
- Parameters:
value (
Any) – The value to convert, should be the canonical representation of the parameter.- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]
- to_param(value: float | ndarray[tuple[Any, ...], dtype[floating[Any]]]) Any¶
Convert a float value to a parameter.
- Parameters:
value (
float|ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value to convert, should be a float.- Return type:
Any- Returns:
Any – The canonical representation of the parameter.
- to_string(value: Any, str_len: int) str¶
Represent a parameter value as a string.
- Parameters:
value (
Any) – The value to represent.str_len (
int) – The maximum length of the string representation.
- Return type:
str- Returns:
str
- class bayes_opt.parameter.FloatParameter(name: str, bounds: tuple[float, float]) None¶
A parameter with float values.
- Parameters:
name (
str) – The name of the parameter.bounds (
tuple[float,float]) – The bounds of the parameter.
- property dim: int¶
The dimensionality of the parameter.
- property is_continuous: bool¶
Whether the parameter is continuous.
- kernel_transform(value: ndarray[tuple[Any, ...], dtype[floating[Any]]]) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Transform a parameter value for use in a kernel.
- Parameters:
value (
ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value(s) to transform, should be a float.- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray
- to_float(value: float) float¶
Convert a parameter value to a float.
- Parameters:
value (
float) – The value to convert, should be the canonical representation of the parameter.- Return type:
float
- to_param(value: float | ndarray[tuple[Any, ...], dtype[floating[Any]]]) float¶
Convert a float value to a parameter.
- Parameters:
value (
float|ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value to convert, should be a float.- Return type:
float- Returns:
Any – The canonical representation of the parameter.
- to_string(value: float, str_len: int) str¶
Represent a parameter value as a string.
- Parameters:
value (
float) – The value to represent.str_len (
int) – The maximum length of the string representation.
- Return type:
str- Returns:
str
- class bayes_opt.parameter.IntParameter(name: str, bounds: tuple[int, int]) None¶
A parameter with int values.
- Parameters:
name (
str) – The name of the parameter.bounds (
tuple[int,int]) – The bounds of the parameter.
- property dim: int¶
The dimensionality of the parameter.
- property is_continuous: bool¶
Whether the parameter is continuous.
- kernel_transform(value: ndarray[tuple[Any, ...], dtype[floating[Any]]]) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Transform a parameter value for use in a kernel.
- Parameters:
value (
ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value(s) to transform, should be a float.- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray
- random_sample(n_samples: int, random_state: RandomState | int | None) ndarray[tuple[Any, ...], dtype[floating[Any]]]¶
Generate random samples from the parameter.
- Parameters:
n_samples (
int) – The number of samples to generate.random_state (
RandomState|int|None) – The random state to use for sampling.
- Return type:
ndarray[tuple[Any,...],dtype[floating[Any]]]- Returns:
np.ndarray – The samples.
- to_float(value: int | float) float¶
Convert a parameter value to a float.
- Parameters:
value (
int|float) – The value to convert, should be the canonical representation of the parameter.- Return type:
float
- to_param(value: int | float | ndarray[tuple[Any, ...], dtype[integer[Any]]] | ndarray[tuple[Any, ...], dtype[floating[Any]]]) int¶
Convert a float value to a parameter.
- Parameters:
value (
int|float|ndarray[tuple[Any,...],dtype[integer[Any]]] |ndarray[tuple[Any,...],dtype[floating[Any]]]) – The value to convert, should be a float.- Return type:
int- Returns:
Any – The canonical representation of the parameter.
- bayes_opt.parameter.is_numeric(value: Any) bool¶
Check if a value is numeric.
- Return type:
bool- Parameters:
value (Any)
- bayes_opt.parameter.wrap_kernel(kernel: Kernel, transform: Callable[[Any], Any]) Kernel¶
Wrap a kernel to transform input data before passing it to the kernel.
- Parameters:
kernel (
Kernel) – The kernel to wrap.transform (
Callable[[Any],Any]) – The transformation function to apply to the input data.
- Return type:
Kernel- Returns:
kernels.Kernel – The wrapped kernel.
Notes
See https://arxiv.org/abs/1805.03463 for more information.