Expected Improvement Generators

ExpectedImprovementGenerator

Bases: BayesianGenerator

Bayesian optimization generator using Log Expected Improvement.

Source code in xopt/generators/bayesian/expected_improvement.py

class ExpectedImprovementGenerator(BayesianGenerator):
    """
    Bayesian optimization generator using Log Expected Improvement.
    """

    name = "expected_improvement"
    supports_batch_generation: bool = True
    supports_single_objective: bool = True
    supports_constraints: bool = True

    __doc__ = (
        "Bayesian optimization generator using Expected improvement\n"
        + formatted_base_docstring()
    )

    _compatible_turbo_controllers = [OptimizeTurboController, SafetyTurboController]

    def get_acquisition(self, model):
        """
        Returns a function that can be used to evaluate the acquisition function.
        Overwrites base `get_acquisition` method.

        Parameters
        ----------
        model : Model
            The model used for Bayesian Optimization.

        Returns
        -------
        acq : AcquisitionFunction
            The acquisition function.
        """
        if model is None:
            raise ValueError("model cannot be None")

        # get base acquisition function
        acq = self._get_acquisition(model)

        # apply fixed features if specified in the generator
        if self.fixed_features is not None:
            # get input dim
            dim = len(self.model_input_names)
            columns = []
            values = []
            for name, value in self.fixed_features.items():
                columns += [self.model_input_names.index(name)]
                values += [value]

            acq = FixedFeatureAcquisitionFunction(
                acq_function=acq, d=dim, columns=columns, values=values
            )

        acq = acq.to(**self.tkwargs)
        return acq

    def _get_acquisition(self, model: torch.nn.Module):
        """
        Get the acquisition function for Bayesian Optimization.

        Parameters
        ----------
        model : Model
            The model used for Bayesian Optimization.

        Returns
        -------
        acq : AcquisitionFunction
            The acquisition function.
        """
        objective = self._get_objective()
        best_f = self._get_best_f(self.data, objective)

        if (
            self.n_candidates > 1
            or isinstance(objective, CustomXoptObjective)
            or self.vocs.constraint_names != []
        ):
            # MC sampling for generating multiple candidate points
            sampler = self._get_sampler(model)
            acq = qLogExpectedImprovement(
                model,
                best_f=best_f,
                sampler=sampler,
                objective=objective,
                constraints=self._get_constraint_callables(),
            )
        else:
            # analytic acquisition function for single candidate generation with
            # basic objective
            # note that the analytic version cannot handle custom objectives or constraints
            weights = set_botorch_weights(self.vocs).to(**self.tkwargs)
            posterior_transform = ScalarizedPosteriorTransform(weights)
            acq = LogExpectedImprovement(
                model, best_f=best_f, posterior_transform=posterior_transform
            )

        return acq

    def _get_best_f(self, data: DataFrame, objective: CustomXoptObjective):
        """
        Get the best function value for Expected Improvement based on the objective.

        Parameters
        ----------
        data : pd.DataFrame
            The data used for optimization.
        objective : Objective
            The objective function.

        Returns
        -------
        best_f : Tensor
            The best function value.
        """
        if isinstance(objective, CustomXoptObjective):
            best_f = objective(
                torch.tensor(
                    get_observable_data(self.vocs, data).to_numpy(), **self.tkwargs
                )
            ).max()
        else:
            # return the best feasible objective value from the data
            # note: this is critical for proper handling of constraints since the base EI
            # function will be zero if an extreme value is in the constrained region
            if isinstance(
                self.vocs.objectives[self.vocs.objective_names[0]], MinimizeObjective
            ):
                multiplier = -1
            else:
                multiplier = 1

            try:
                _, value, _ = select_best(self.vocs, data)
            except FeasibilityError:
                raise RuntimeError(
                    "No feasible points found in the data; cannot compute expected improvement."
                )
            best_f = torch.tensor(value.item(), **self.tkwargs) * multiplier

        return best_f

model_input_names property

variable names corresponding to trained model

__init__(**kwargs)

Initialize the generator.

Source code in xopt/generator.py

def __init__(self, **kwargs):
    """
    Initialize the generator.
    """
    super().__init__(**kwargs)
    logger.info(f"Initialized generator {self.name}")

add_data(new_data)

Add new data to the generator for Bayesian Optimization.

Parameters:

Name	Type	Description	Default
new_data	DataFrame	The new data to be added to the generator.	required

Notes

This method appends the new data to the existing data in the generator.

Source code in xopt/generators/bayesian/bayesian_generator.py

def add_data(self, new_data: pd.DataFrame):
    """
    Add new data to the generator for Bayesian Optimization.

    Parameters
    ----------
    new_data : pd.DataFrame
        The new data to be added to the generator.

    Notes
    -----
    This method appends the new data to the existing data in the generator.
    """
    self.data = pd.concat([self.data, new_data], axis=0, ignore_index=True)

generate(n_candidates)

Generate candidates using Bayesian Optimization.

Parameters:

Name	Type	Description	Default
n_candidates	int	The number of candidates to generate in each optimization step.	required

Returns:

Type	Description
List[Dict]	A list of dictionaries containing the generated candidates.

Raises:

Type	Description
NotImplementedError	If the number of candidates is greater than 1, and the generator does not support batch candidate generation.
RuntimeError	If no data is contained in the generator, the 'add_data' method should be called to add data before generating candidates.

Notes

This method generates candidates for Bayesian Optimization based on the provided number of candidates. It updates the internal model with the current data and calculates the candidates by optimizing the acquisition function. The method returns the generated candidates in the form of a list of dictionaries.

Source code in xopt/generators/bayesian/bayesian_generator.py

def generate(self, n_candidates: int):
    """
    Generate candidates using Bayesian Optimization.

    Parameters
    ----------
    n_candidates : int
        The number of candidates to generate in each optimization step.

    Returns
    -------
    List[Dict]
        A list of dictionaries containing the generated candidates.

    Raises
    ------
    NotImplementedError
        If the number of candidates is greater than 1, and the generator does not
        support batch candidate generation.

    RuntimeError
        If no data is contained in the generator, the 'add_data' method should be
        called to add data before generating candidates.

    Notes
    -----
    This method generates candidates for Bayesian Optimization based on the
    provided number of candidates. It updates the internal model with the current
    data and calculates the candidates by optimizing the acquisition function.
    The method returns the generated candidates in the form of a list of dictionaries.
    """

    self.n_candidates = n_candidates
    if n_candidates > 1 and not self.supports_batch_generation:
        raise NotImplementedError(
            "This Bayesian algorithm does not currently support parallel candidate "
            "generation"
        )

    # if no data exists raise error
    if self.data is None:
        raise RuntimeError(
            "no data contained in generator, call `add_data` "
            "method to add data, see also `Xopt.random_evaluate()`"
        )

    else:
        # dict to track runtimes
        timing_results = {}

        # update internal model with internal data
        start_time = time.perf_counter()
        model = self.train_model(self.get_training_data(self.data))
        timing_results["training"] = time.perf_counter() - start_time

        # propose candidates given model
        start_time = time.perf_counter()
        candidates = self.propose_candidates(model, n_candidates=n_candidates)
        timing_results["acquisition_optimization"] = (
            time.perf_counter() - start_time
        )

        # post process candidates
        result = self._process_candidates(candidates)

        # append timing results to dataframe (if it exists)
        if self.computation_time is not None:
            self.computation_time = pd.concat(
                (
                    self.computation_time,
                    pd.DataFrame(timing_results, index=[0]),
                ),
                ignore_index=True,
            )
        else:
            self.computation_time = pd.DataFrame(timing_results, index=[0])

        if self.n_interpolate_points is not None:
            if self.n_candidates > 1:
                raise RuntimeError(
                    "cannot generate interpolated points for "
                    "multiple candidate generation"
                )
            else:
                assert len(result) == 1
                result = interpolate_points(
                    pd.concat(
                        (self.data.iloc[-1:][self.vocs.variable_names], result),
                        axis=0,
                        ignore_index=True,
                    ),
                    num_points=self.n_interpolate_points,
                )

        return result.to_dict("records")

get_acquisition(model)

Returns a function that can be used to evaluate the acquisition function. Overwrites base get_acquisition method.

Parameters:

Name	Type	Description	Default
model	Model	The model used for Bayesian Optimization.	required

Returns:

Name	Type	Description
acq	AcquisitionFunction	The acquisition function.

Source code in xopt/generators/bayesian/expected_improvement.py

def get_acquisition(self, model):
    """
    Returns a function that can be used to evaluate the acquisition function.
    Overwrites base `get_acquisition` method.

    Parameters
    ----------
    model : Model
        The model used for Bayesian Optimization.

    Returns
    -------
    acq : AcquisitionFunction
        The acquisition function.
    """
    if model is None:
        raise ValueError("model cannot be None")

    # get base acquisition function
    acq = self._get_acquisition(model)

    # apply fixed features if specified in the generator
    if self.fixed_features is not None:
        # get input dim
        dim = len(self.model_input_names)
        columns = []
        values = []
        for name, value in self.fixed_features.items():
            columns += [self.model_input_names.index(name)]
            values += [value]

        acq = FixedFeatureAcquisitionFunction(
            acq_function=acq, d=dim, columns=columns, values=values
        )

    acq = acq.to(**self.tkwargs)
    return acq

get_input_data(data)

Convert input data to a torch tensor.

Parameters:

Name	Type	Description	Default
data	DataFrame	The input data in the form of a pandas DataFrame.	required

Returns:

Type	Description
Tensor	A torch tensor containing the input data.

Notes

This method takes a pandas DataFrame as input data and converts it into a torch tensor. It specifically selects columns corresponding to the model's input names (variables), and the resulting tensor is configured with the data type and device settings from the generator.

Source code in xopt/generators/bayesian/bayesian_generator.py

def get_input_data(self, data: pd.DataFrame) -> torch.Tensor:
    """
    Convert input data to a torch tensor.

    Parameters
    ----------
    data : pd.DataFrame
        The input data in the form of a pandas DataFrame.

    Returns
    -------
    torch.Tensor
        A torch tensor containing the input data.

    Notes
    -----
    This method takes a pandas DataFrame as input data and converts it into a
    torch tensor. It specifically selects columns corresponding to the model's
    input names (variables), and the resulting tensor is configured with the data
    type and device settings from the generator.
    """
    return torch.tensor(
        data[self.model_input_names].to_numpy().copy(), **self.tkwargs
    )

get_optimum()

select the best point(s) given by the model using the Posterior mean

Source code in xopt/generators/bayesian/bayesian_generator.py

def get_optimum(self):
    """select the best point(s) given by the
    model using the Posterior mean"""
    acq = qUpperConfidenceBound(
        model=self.model, beta=0.0, objective=self._get_objective()
    )
    if len(self.vocs.constraints):
        acq = ConstrainedMCAcquisitionFunction(
            self.model,
            acq,
            self._get_constraint_callables(),
            sampler=self._get_sampler(self.model),
        )
    bounds = self._get_bounds()

    if self.fixed_features is not None:
        acq = self._apply_fixed_features(acq)

        indices = []
        for idx, name in enumerate(self.vocs.variable_names):
            if name not in self.fixed_features:
                indices += [idx]

        bounds = bounds[:, indices]

    bounds = bounds.to(**self.tkwargs)
    acq = acq.to(**self.tkwargs)

    # use default initial conditions for a global search
    result = self.numerical_optimizer.optimize(acq, bounds, 1)

    return self._process_candidates(result)

get_training_data(data)

Get training data used to train the GP model.

If a turbo controller is specified with the flag restrict_model_data this will return a subset of data that is inside the trust region.

Parameters:

Name	Type	Description	Default
data	DataFrame	The data in the form of a pandas DataFrame.	required

Returns:

Name	Type	Description
data	DataFrame	A subset of data used to train the model form of a pandas DataFrame.

Source code in xopt/generators/bayesian/bayesian_generator.py

def get_training_data(self, data: pd.DataFrame) -> pd.DataFrame:
    """
    Get training data used to train the GP model.

    If a turbo controller is specified with the flag `restrict_model_data` this
    will return a subset of data that is inside the trust region.

    Parameters
    ----------
    data : pd.DataFrame
        The data in the form of a pandas DataFrame.

    Returns
    -------
    data : pd.DataFrame
        A subset of data used to train the model form of a pandas DataFrame.

    """
    if self.turbo_controller is not None:
        if self.turbo_controller.restrict_model_data:
            data = self.turbo_controller.get_data_in_trust_region(data, self)
            if data.empty:
                raise FeasibilityError(
                    "No training data available to build model, because ",
                    "no points in the dataset are within the TuRBO trust region. ",
                )
    return data

model_dump(*args, **kwargs)

overwrite model dump to remove faux class attrs

Source code in xopt/generator.py

def model_dump(self, *args: Any, **kwargs: Any) -> dict[str, Any]:
    """overwrite model dump to remove faux class attrs"""

    res = super().model_dump(*args, **kwargs)

    res.pop("supports_batch_generation", None)
    res.pop("supports_multi_objective", None)

    return res

propose_candidates(model, n_candidates=1)

Propose candidates using Bayesian Optimization.

Parameters:

Name	Type	Description	Default
model	Module	The trained Bayesian model.	required
n_candidates	int	The number of candidates to propose (default is 1).	1

Returns:

Type	Description
Tensor	A tensor containing the proposed candidates.

Notes

This method proposes candidates for Bayesian Optimization by numerically optimizing the acquisition function using the trained model. It updates the state of the Turbo controller if used and calculates the optimization bounds.

Source code in xopt/generators/bayesian/bayesian_generator.py

def propose_candidates(self, model: Module, n_candidates: int = 1) -> Tensor:
    """
    Propose candidates using Bayesian Optimization.

    Parameters
    ----------
    model : Module
        The trained Bayesian model.
    n_candidates : int, optional
        The number of candidates to propose (default is 1).

    Returns
    -------
    Tensor
        A tensor containing the proposed candidates.

    Notes
    -----
    This method proposes candidates for Bayesian Optimization by numerically
    optimizing the acquisition function using the trained model. It updates the
    state of the Turbo controller if used and calculates the optimization bounds.
    """
    # update TurBO state if used with the last `n_candidates` points
    if self.turbo_controller is not None:
        self.turbo_controller.update_state(self, n_candidates)

    # calculate optimization bounds
    bounds = self._get_optimization_bounds()

    # get acquisition function
    acq_funct = self.get_acquisition(model)

    # get initial candidates to start acquisition function optimization
    initial_points = self._get_initial_conditions(n_candidates)

    # get candidates -- grid optimizer does not support batch_initial_conditions
    if isinstance(self.numerical_optimizer, GridOptimizer):
        candidates = self.numerical_optimizer.optimize(
            acq_funct, bounds, n_candidates
        )
    else:
        candidates = self.numerical_optimizer.optimize(
            acq_funct, bounds, n_candidates, batch_initial_conditions=initial_points
        )
    return candidates

train_model(data=None, update_internal=True)

Train a Bayesian model for Bayesian Optimization.

Parameters:

Name	Type	Description	Default
data	DataFrame	The data to be used for training the model. If not provided, the internal data of the generator is used.	None
update_internal	bool	Flag to indicate whether to update the internal model of the generator with the trained model (default is True).	True

Returns:

Type	Description
Module	The trained Bayesian model.

Raises:

Type	Description
ValueError	If no data is available to build the model.

Notes

This method trains a Bayesian model using the provided data or the internal data of the generator. It updates the internal model with the trained model if the 'update_internal' flag is set to True.

Source code in xopt/generators/bayesian/bayesian_generator.py

def train_model(
    self, data: pd.DataFrame | None = None, update_internal: bool = True
) -> Module:
    """
    Train a Bayesian model for Bayesian Optimization.

    Parameters
    ----------
    data : pd.DataFrame, optional
        The data to be used for training the model. If not provided, the internal
        data of the generator is used.
    update_internal : bool, optional
        Flag to indicate whether to update the internal model of the generator
        with the trained model (default is True).

    Returns
    -------
    Module
        The trained Bayesian model.

    Raises
    ------
    ValueError
        If no data is available to build the model.

    Notes
    -----
    This method trains a Bayesian model using the provided data or the internal
    data of the generator. It updates the internal model with the trained model
    if the 'update_internal' flag is set to True.
    """
    if data is None:
        data = self.get_training_data(self.data)
        if data is None:
            raise ValueError("no data available to build model")

    if data.empty:
        raise ValueError("no data available to build model")

    # get input bounds
    variable_bounds = {
        name: ele.domain for name, ele in self.vocs.variables.items()
    }

    # if turbo restrict points is true then set the bounds to the trust region
    # bounds
    if self.turbo_controller is not None:
        if self.turbo_controller.restrict_model_data:
            variable_bounds = dict(
                zip(
                    self.vocs.variable_names,
                    self.turbo_controller.get_trust_region(self).numpy().T,
                )
            )

    # add fixed feature bounds if requested
    if self.fixed_features is not None:
        # get bounds for each fixed_feature (vocs bounds take precedent)
        for key in self.fixed_features:
            if key not in variable_bounds:
                if key not in data:
                    raise KeyError(
                        "generator data needs to contain fixed feature "
                        f"column name `{key}`"
                    )
                f_data = data[key]
                bounds = [f_data.min(), f_data.max()]
                if bounds[1] - bounds[0] < 1e-8:
                    bounds[1] = bounds[0] + 1e-8
                variable_bounds[key] = bounds

    _model = self.gp_constructor.build_model(
        self.model_input_names,
        self.vocs.output_names,
        data,
        {name: variable_bounds[name] for name in self.model_input_names},
        **self.tkwargs,
    )

    if update_internal:
        self.model = _model

    return _model

validate_turbo_controller(value, info) classmethod

note default behavior is no use of turbo

Source code in xopt/generators/bayesian/bayesian_generator.py

@field_validator("turbo_controller", mode="before")
@classmethod
def validate_turbo_controller(cls, value: Any, info: ValidationInfo):
    """note default behavior is no use of turbo"""
    if value is None:
        return value

    compatible_turbo_controllers = [
        turbo_controller
        for turbo_controller in cls.get_compatible_turbo_controllers()
        if turbo_controller is not None
    ]

    if len(compatible_turbo_controllers) == 0:
        raise ValueError("no turbo controllers are compatible with this generator")
    else:
        return validate_turbo_controller_base(
            value, compatible_turbo_controllers, info
        )

visualize_model(**kwargs)

Display GP model predictions for the selected output(s).

The GP models are displayed with respect to the named variables. If None are given, the list of variables in vocs is used. Feasible samples are indicated with a filled orange "o", infeasible samples with a hollow red "o". Feasibility is calculated with respect to all constraints unless the selected output is a constraint itself, in which case only that one is considered.

Parameters:

Name	Type	Description	Default
**kwargs		Supported keyword arguments: - output_names : List[str] Outputs for which the GP models are displayed. Defaults to all outputs in vocs. - variable_names : List[str] The variables with respect to which the GP models are displayed (maximum of 2). Defaults to vocs.variable_names. - idx : int Index of the last sample to use. This also selects the point of reference in higher dimensions unless an explicit reference_point is given. - reference_point : dict Reference point determining the value of variables in vocs.variable_names, but not in variable_names (slice plots in higher dimensions). Defaults to last used sample. - show_samples : bool, optional Whether samples are shown. - show_prior_mean : bool, optional Whether the prior mean is shown. - show_feasibility : bool, optional Whether the feasibility region is shown. - show_acquisition : bool, optional Whether the acquisition function is computed and shown (only if acquisition function is not None). - n_grid : int, optional Number of grid points per dimension used to display the model predictions. - axes : Axes, optional Axes object used for plotting. - exponentiate : bool, optional Flag to exponentiate acquisition function before plotting.	{}

Returns:

Name	Type	Description
result	tuple	The matplotlib figure and axes objects.

Source code in xopt/generators/bayesian/bayesian_generator.py

def visualize_model(self, **kwargs):
    """Display GP model predictions for the selected output(s).

    The GP models are displayed with respect to the named variables. If None are given, the list of variables in
    vocs is used. Feasible samples are indicated with a filled orange "o", infeasible samples with a hollow
    red "o". Feasibility is calculated with respect to all constraints unless the selected output is a
    constraint itself, in which case only that one is considered.

    Parameters
    ----------
    **kwargs: dict, optional
        Supported keyword arguments:
        - output_names : List[str]
            Outputs for which the GP models are displayed. Defaults to all outputs in vocs.
        - variable_names : List[str]
            The variables with respect to which the GP models are displayed (maximum of 2).
            Defaults to vocs.variable_names.
        - idx : int
            Index of the last sample to use. This also selects the point of reference in
            higher dimensions unless an explicit reference_point is given.
        - reference_point : dict
            Reference point determining the value of variables in vocs.variable_names, but not in variable_names
            (slice plots in higher dimensions). Defaults to last used sample.
        - show_samples : bool, optional
            Whether samples are shown.
        - show_prior_mean : bool, optional
            Whether the prior mean is shown.
        - show_feasibility : bool, optional
            Whether the feasibility region is shown.
        - show_acquisition : bool, optional
            Whether the acquisition function is computed and shown (only if acquisition function is not None).
        - n_grid : int, optional
            Number of grid points per dimension used to display the model predictions.
        - axes : Axes, optional
            Axes object used for plotting.
        - exponentiate : bool, optional
            Flag to exponentiate acquisition function before plotting.

    Returns
    -------
    result : tuple
        The matplotlib figure and axes objects.
    """
    return visualize_generator_model(self, **kwargs)

yaml(**kwargs)

serialize first then dump to yaml string

Source code in xopt/pydantic.py

def yaml(self, **kwargs):
    """serialize first then dump to yaml string"""
    output = json.loads(
        self.to_json(
            **kwargs,
        )
    )
    return yaml.dump(output)