data_models.domain.features.Inputs

data_models.domain.features.Inputs()

Container of input features, only input features are allowed.

Attributes

Name	Type	Description
features	List(Inputs	list of the features.

Methods

Name	Description
get_bounds	Returns the boundaries of the optimization problem based on the transformations
get_categorical_combinations	Get a list of tuples pairing the feature keys with a list of valid categories
get_feature_indices	Returns a list of indices of the given feature key list.
get_fixed	Gets all features in `self` that are fixed and returns them as new
get_free	Gets all features in `self` that are not fixed and returns them as
get_number_of_categorical_combinations	Get the total number of unique categorical combinations.
inverse_transform	Transform a dataframe back to the original representations.
is_fulfilled	Check if the provided experiments fulfill all constraints defined on the
sample	Draw sobol samples
to_pydantic_model	Build a dynamic Pydantic model with one field per input feature.
transform	Transform a dataframe to the representation specified in `specs`.
validate_candidates	Validate a pandas dataframe with input feature values.

get_bounds

data_models.domain.features.Inputs.get_bounds(
    specs,
    experiments=None,
    reference_experiment=None,
    relax_allow_zero=False,
)

Returns the boundaries of the optimization problem based on the transformations defined in the specs dictionary.

Parameters

Name	Type	Description	Default
specs	InputTransformSpecs	Dictionary specifying which input feature is transformed by which encoder.	required
experiments	Optional[pd.DataFrame]	Dataframe with input features. If provided the real feature bounds are returned based on both the opt. feature bounds and the extreme points in the dataframe. Defaults to None,	`None`
reference_experiment	Optional[pd.Series]	If a reference experiment provided,	`None`
relax_allow_zero	bool	If True, semi-continuous continuous inputs (`allow_zero=True` with positive lower bound) report a relaxed lower bound of 0. Other input types ignore this flag. Defaults to False.	`False`

Raises

Name	Type	Description
	ValueError	If a feature type is not known.
	ValueError	If no transformation is provided for a categorical feature.

Returns

Name	Type	Description
	Tuple[List[float], List[float]]	Tuple[List[float], List[float]]: list with lower bounds, list with upper bounds.

get_categorical_combinations

data_models.domain.features.Inputs.get_categorical_combinations(
    include=Input,
    exclude=None,
    include_semicontinuous=True,
)

Get a list of tuples pairing the feature keys with a list of valid categories

Parameters

Name	Type	Description	Default
include	Feature	Features to be included. Defaults to Input.	`Input`
exclude	Feature	Features to be excluded, e.g. subclasses of the included features. Defaults to None.	`None`
include_semicontinuous	bool	When True (default), each semi-continuous feature (`ContinuousInput` with `allow_zero=True` and a positive lower bound, un-fixed) doubles the number of combinations via its on/off enumeration. When False, semi-continuous features are excluded from the enumeration – useful when the caller handles them via a post-optimisation pruning step rather than by AF-time enumeration. Mirrors the flag of the same name on `get_number_of_categorical_combinations`; the two must be passed the same value to stay consistent.	`True`

Returns

Name	Type	Description
	list[tuple[tuple[str, float] \| tuple[str, str], …]]	List[(str, List[str])]: Returns a list of tuples pairing the feature keys with a list of valid categories (str)

get_feature_indices

data_models.domain.features.Inputs.get_feature_indices(specs, feature_keys)

Returns a list of indices of the given feature key list.

Parameters

Name	Type	Description	Default
specs	InputTransformSpecs	Dictionary specifying which input feature is transformed by which encoder.	required
feature_keys	List[str]	List of feature keys.	required

Returns

Name	Type	Description
	List[int]	List[int]: The list of indices.

get_fixed

data_models.domain.features.Inputs.get_fixed()

Gets all features in self that are fixed and returns them as new Inputs object.

Returns

Name	Type	Description
Inputs	Inputs	Input features object containing only fixed features.

get_free

data_models.domain.features.Inputs.get_free()

Gets all features in self that are not fixed and returns them as new Inputs object.

Returns

Name	Type	Description
Inputs	Inputs	Input features object containing only non-fixed features.

get_number_of_categorical_combinations

data_models.domain.features.Inputs.get_number_of_categorical_combinations(
    include=Input,
    exclude=None,
    include_semicontinuous=True,
)

Get the total number of unique categorical combinations.

This is used before generating all of the categorical combinations, which may cause memory issues if there are too many.

Parameters

Name	Type	Description	Default
include	Feature	Features to be included. Defaults to Input.	`Input`
exclude	Feature	Features to be excluded, e.g. subclasses of the included features. Defaults to None.	`None`
include_semicontinuous	bool	When True (default), each semi-continuous feature (`ContinuousInput` with `allow_zero=True` and a positive lower bound, un-fixed) contributes a factor of 2 for its on/off enumeration. When False, semi-continuous features are excluded from the count – useful when the caller handles them via a post-optimisation pruning step rather than by AF-time enumeration.	`True`

Returns: int: Returns the number of unique combinations of discrete and categorical features.

inverse_transform

data_models.domain.features.Inputs.inverse_transform(experiments, specs)

Transform a dataframe back to the original representations.

The original applied transformation has to be provided via the specs dictionary. Currently only input categoricals are supported.

Parameters

Name	Type	Description	Default
experiments	pd.DataFrame	Transformed data dataframe.	required
specs	InputTransformSpecs	Dictionary specifying which input feature is transformed by which encoder.	required

Returns

Name	Type	Description
	pd.DataFrame	pd.DataFrame: Back transformed dataframe. Only input features are included.

is_fulfilled

data_models.domain.features.Inputs.is_fulfilled(experiments)

Check if the provided experiments fulfill all constraints defined on the input features itself like the bounds or the allowed categories.

Parameters

Name	Type	Description	Default
experiments	pd.DataFrame	Dataframe with input features.	required

Returns

Name	Type	Description
	pd.Series	Series with boolean values indicating if the experiments fulfill the constraints on the input features.

sample

data_models.domain.features.Inputs.sample(
    n=1,
    method=SamplingMethodEnum.UNIFORM,
    seed=None,
    sampler_kwargs=None,
)

Draw sobol samples

Parameters

Name	Type	Description	Default
n	int	Number of samples, has to be larger than 0. Defaults to 1.	`1`
method	SamplingMethodEnum	Method to use, implemented methods are `UNIFORM`, `SOBOL` and `LHS`. Defaults to `UNIFORM`.	`SamplingMethodEnum.UNIFORM`
seed	int	random seed. Defaults to None.	`None`
sampler_kwargs	Dict	Additional arguments for the sampler. Defaults to None.	`None`

Returns

Name	Type	Description
	pd.DataFrame	pd.DataFrame: Dataframe containing the samples.

to_pydantic_model

data_models.domain.features.Inputs.to_pydantic_model(name='CandidatePoint')

Build a dynamic Pydantic model with one field per input feature.

Each feature’s to_pydantic_field() determines the field type and constraints (e.g., ge/le for continuous, Literal for categorical).

Returns

Name	Type	Description
		A Pydantic BaseModel subclass with typed fields matching the inputs.

transform

data_models.domain.features.Inputs.transform(experiments, specs)

Transform a dataframe to the representation specified in specs.

Currently only input categoricals are supported.

Parameters

Name	Type	Description	Default
experiments	pd.DataFrame	Data dataframe to be transformed.	required
specs	InputTransformSpecs	Dictionary specifying which input feature is transformed by which encoder.	required

Returns

Name	Type	Description
	pd.DataFrame	pd.DataFrame: Transformed dataframe. Only input features are included.

validate_candidates

data_models.domain.features.Inputs.validate_candidates(candidates)

Validate a pandas dataframe with input feature values.

Parameters

Name	Type	Description	Default
candidates	pd.Dataframe	Inputs to validate.	required

Raises

Name	Type	Description
	ValueError	Raises a Valueerror if a feature based validation raises an exception.

Returns

Name	Type	Description
	pd.DataFrame	pd.Dataframe: Validated dataframe

# data_models.domain.features.Inputs { #bofire.data_models.domain.features.Inputs } ```python data_models.domain.features.Inputs() ``` Container of input features, only input features are allowed. ## Attributes {.doc-section .doc-section-attributes} | Name | Type | Description | |----------|-------------|-----------------------| | features | List(Inputs | list of the features. | ## Methods | Name | Description | | --- | --- | | [get_bounds](#bofire.data_models.domain.features.Inputs.get_bounds) | Returns the boundaries of the optimization problem based on the transformations | | [get_categorical_combinations](#bofire.data_models.domain.features.Inputs.get_categorical_combinations) | Get a list of tuples pairing the feature keys with a list of valid categories | | [get_feature_indices](#bofire.data_models.domain.features.Inputs.get_feature_indices) | Returns a list of indices of the given feature key list. | | [get_fixed](#bofire.data_models.domain.features.Inputs.get_fixed) | Gets all features in `self` that are fixed and returns them as new | | [get_free](#bofire.data_models.domain.features.Inputs.get_free) | Gets all features in `self` that are not fixed and returns them as | | [get_number_of_categorical_combinations](#bofire.data_models.domain.features.Inputs.get_number_of_categorical_combinations) | Get the total number of unique categorical combinations. | | [inverse_transform](#bofire.data_models.domain.features.Inputs.inverse_transform) | Transform a dataframe back to the original representations. | | [is_fulfilled](#bofire.data_models.domain.features.Inputs.is_fulfilled) | Check if the provided experiments fulfill all constraints defined on the | | [sample](#bofire.data_models.domain.features.Inputs.sample) | Draw sobol samples | | [to_pydantic_model](#bofire.data_models.domain.features.Inputs.to_pydantic_model) | Build a dynamic Pydantic model with one field per input feature. | | [transform](#bofire.data_models.domain.features.Inputs.transform) | Transform a dataframe to the representation specified in `specs`. | | [validate_candidates](#bofire.data_models.domain.features.Inputs.validate_candidates) | Validate a pandas dataframe with input feature values. | ### get_bounds { #bofire.data_models.domain.features.Inputs.get_bounds } ```python data_models.domain.features.Inputs.get_bounds( specs, experiments=None, reference_experiment=None, relax_allow_zero=False, ) ``` Returns the boundaries of the optimization problem based on the transformations defined in the `specs` dictionary. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |----------------------|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------| | specs | InputTransformSpecs | Dictionary specifying which input feature is transformed by which encoder. | _required_ | | experiments | Optional\[pd.DataFrame\] | Dataframe with input features. If provided the real feature bounds are returned based on both the opt. feature bounds and the extreme points in the dataframe. Defaults to None, | `None` | | reference_experiment | Optional\[pd.Series\] | If a reference experiment provided, | `None` | | relax_allow_zero | bool | If True, semi-continuous continuous inputs (`allow_zero=True` with positive lower bound) report a relaxed lower bound of 0. Other input types ignore this flag. Defaults to False. | `False` | #### Raises {.doc-section .doc-section-raises} | Name | Type | Description | |--------|------------|-------------------------------------------------------------| | | ValueError | If a feature type is not known. | | | ValueError | If no transformation is provided for a categorical feature. | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|---------------------------------------|----------------------------------------------------------------------------------| | | Tuple\[List\[float\], List\[float\]\] | Tuple[List[float], List[float]]: list with lower bounds, list with upper bounds. | ### get_categorical_combinations { #bofire.data_models.domain.features.Inputs.get_categorical_combinations } ```python data_models.domain.features.Inputs.get_categorical_combinations( include=Input, exclude=None, include_semicontinuous=True, ) ``` Get a list of tuples pairing the feature keys with a list of valid categories #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |------------------------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------| | include | Feature | Features to be included. Defaults to Input. | `Input` | | exclude | Feature | Features to be excluded, e.g. subclasses of the included features. Defaults to None. | `None` | | include_semicontinuous | bool | When True (default), each semi-continuous feature (`ContinuousInput` with `allow_zero=True` and a positive lower bound, un-fixed) doubles the number of combinations via its on/off enumeration. When False, semi-continuous features are excluded from the enumeration -- useful when the caller handles them via a post-optimisation pruning step rather than by AF-time enumeration. Mirrors the flag of the same name on `get_number_of_categorical_combinations`; the two must be passed the same value to stay consistent. | `True` | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|----------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------| | | list\[tuple\[tuple\[str, float\] \| tuple\[str, str\], ...\]\] | List[(str, List[str])]: Returns a list of tuples pairing the feature keys with a list of valid categories (str) | ### get_feature_indices { #bofire.data_models.domain.features.Inputs.get_feature_indices } ```python data_models.domain.features.Inputs.get_feature_indices(specs, feature_keys) ``` Returns a list of indices of the given feature key list. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |--------------|---------------------|----------------------------------------------------------------------------|------------| | specs | InputTransformSpecs | Dictionary specifying which input feature is transformed by which encoder. | _required_ | | feature_keys | List\[str\] | List of feature keys. | _required_ | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|-------------|---------------------------------| | | List\[int\] | List[int]: The list of indices. | ### get_fixed { #bofire.data_models.domain.features.Inputs.get_fixed } ```python data_models.domain.features.Inputs.get_fixed() ``` Gets all features in `self` that are fixed and returns them as new `Inputs` object. #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------|-------------------------------------------------------| | Inputs | Inputs | Input features object containing only fixed features. | ### get_free { #bofire.data_models.domain.features.Inputs.get_free } ```python data_models.domain.features.Inputs.get_free() ``` Gets all features in `self` that are not fixed and returns them as new `Inputs` object. #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------|-----------------------------------------------------------| | Inputs | Inputs | Input features object containing only non-fixed features. | ### get_number_of_categorical_combinations { #bofire.data_models.domain.features.Inputs.get_number_of_categorical_combinations } ```python data_models.domain.features.Inputs.get_number_of_categorical_combinations( include=Input, exclude=None, include_semicontinuous=True, ) ``` Get the total number of unique categorical combinations. This is used before generating all of the categorical combinations, which may cause memory issues if there are too many. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |------------------------|---------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------| | include | Feature | Features to be included. Defaults to Input. | `Input` | | exclude | Feature | Features to be excluded, e.g. subclasses of the included features. Defaults to None. | `None` | | include_semicontinuous | bool | When True (default), each semi-continuous feature (`ContinuousInput` with `allow_zero=True` and a positive lower bound, un-fixed) contributes a factor of 2 for its on/off enumeration. When False, semi-continuous features are excluded from the count -- useful when the caller handles them via a post-optimisation pruning step rather than by AF-time enumeration. | `True` | Returns: int: Returns the number of unique combinations of discrete and categorical features. ### inverse_transform { #bofire.data_models.domain.features.Inputs.inverse_transform } ```python data_models.domain.features.Inputs.inverse_transform(experiments, specs) ``` Transform a dataframe back to the original representations. The original applied transformation has to be provided via the specs dictionary. Currently only input categoricals are supported. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |-------------|---------------------|----------------------------------------------------------------------------|------------| | experiments | pd.DataFrame | Transformed data dataframe. | _required_ | | specs | InputTransformSpecs | Dictionary specifying which input feature is transformed by which encoder. | _required_ | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------------|-----------------------------------------------------------------------------| | | pd.DataFrame | pd.DataFrame: Back transformed dataframe. Only input features are included. | ### is_fulfilled { #bofire.data_models.domain.features.Inputs.is_fulfilled } ```python data_models.domain.features.Inputs.is_fulfilled(experiments) ``` Check if the provided experiments fulfill all constraints defined on the input features itself like the bounds or the allowed categories. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |-------------|--------------|--------------------------------|------------| | experiments | pd.DataFrame | Dataframe with input features. | _required_ | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|-----------|---------------------------------------------------------------------------------------------------------| | | pd.Series | Series with boolean values indicating if the experiments fulfill the constraints on the input features. | ### sample { #bofire.data_models.domain.features.Inputs.sample } ```python data_models.domain.features.Inputs.sample( n=1, method=SamplingMethodEnum.UNIFORM, seed=None, sampler_kwargs=None, ) ``` Draw sobol samples #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |----------------|--------------------|---------------------------------------------------------------------------------------------|------------------------------| | n | int | Number of samples, has to be larger than 0. Defaults to 1. | `1` | | method | SamplingMethodEnum | Method to use, implemented methods are `UNIFORM`, `SOBOL` and `LHS`. Defaults to `UNIFORM`. | `SamplingMethodEnum.UNIFORM` | | seed | int | random seed. Defaults to None. | `None` | | sampler_kwargs | Dict | Additional arguments for the sampler. Defaults to None. | `None` | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------------|-------------------------------------------------| | | pd.DataFrame | pd.DataFrame: Dataframe containing the samples. | ### to_pydantic_model { #bofire.data_models.domain.features.Inputs.to_pydantic_model } ```python data_models.domain.features.Inputs.to_pydantic_model(name='CandidatePoint') ``` Build a dynamic Pydantic model with one field per input feature. Each feature's ``to_pydantic_field()`` determines the field type and constraints (e.g., ge/le for continuous, Literal for categorical). #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------|----------------------------------------------------------------------| | | | A Pydantic BaseModel subclass with typed fields matching the inputs. | ### transform { #bofire.data_models.domain.features.Inputs.transform } ```python data_models.domain.features.Inputs.transform(experiments, specs) ``` Transform a dataframe to the representation specified in `specs`. Currently only input categoricals are supported. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |-------------|---------------------|----------------------------------------------------------------------------|------------| | experiments | pd.DataFrame | Data dataframe to be transformed. | _required_ | | specs | InputTransformSpecs | Dictionary specifying which input feature is transformed by which encoder. | _required_ | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------------|------------------------------------------------------------------------| | | pd.DataFrame | pd.DataFrame: Transformed dataframe. Only input features are included. | ### validate_candidates { #bofire.data_models.domain.features.Inputs.validate_candidates } ```python data_models.domain.features.Inputs.validate_candidates(candidates) ``` Validate a pandas dataframe with input feature values. #### Parameters {.doc-section .doc-section-parameters} | Name | Type | Description | Default | |------------|--------------|---------------------|------------| | candidates | pd.Dataframe | Inputs to validate. | _required_ | #### Raises {.doc-section .doc-section-raises} | Name | Type | Description | |--------|------------|------------------------------------------------------------------------| | | ValueError | Raises a Valueerror if a feature based validation raises an exception. | #### Returns {.doc-section .doc-section-returns} | Name | Type | Description | |--------|--------------|-----------------------------------| | | pd.DataFrame | pd.Dataframe: Validated dataframe |