Merge pull request #205 from ChristopherMayes/select_best_improvements

add returning best param set to vocs method,

tests/generators/test_neldermead.py

@@ -138,7 +138,7 @@ def wrap(x):
         data = X.vocs.variable_data(X.data).to_numpy()
         assert np.array_equal(data, scipy_data)
 
-        idx, best = X.vocs.select_best(X.data)
+        idx, best, _ = X.vocs.select_best(X.data)
         xbest = X.vocs.variable_data(X.data.loc[idx, :]).to_numpy().flatten()
         assert np.array_equal(
             xbest, result.x
@@ -216,7 +216,7 @@ def wrap(x):
         assert data.shape == scipy_data.shape
         assert np.allclose(data, scipy_data, rtol=0, atol=1e-10)
 
-        idx, best = X.vocs.select_best(X.data)
+        idx, best, _ = X.vocs.select_best(X.data)
         xbest = X.vocs.variable_data(X.data.loc[idx, :]).to_numpy().flatten()
         assert np.array_equal(
             xbest, result.x

tests/test_vocs.py

@@ -208,29 +208,29 @@ def test_select_best(self):
 
         # test maximization
         vocs.objectives[vocs.objective_names[0]] = "MAXIMIZE"
-        idx, val = vocs.select_best(test_data)
+        idx, val, _ = vocs.select_best(test_data)
         assert idx == [2]
         assert val == [1.0]
 
         vocs.constraints = {}
-        idx, val = vocs.select_best(test_data)
+        idx, val, _ = vocs.select_best(test_data)
         assert idx == [3]
         assert val == [1.5]
 
         # test returning multiple best values -- sorted by best value
-        idx, val = vocs.select_best(test_data, 2)
+        idx, val, _ = vocs.select_best(test_data, 2)
         assert np.allclose(idx, np.array([3, 2]))
         assert np.allclose(val, np.array([1.5, 1.0]))
 
         # test minimization
         vocs.objectives[vocs.objective_names[0]] = "MINIMIZE"
         vocs.constraints = {"c1": ["GREATER_THAN", 0.5]}
-        idx, val = vocs.select_best(test_data)
+        idx, val, _ = vocs.select_best(test_data)
         assert idx == [0]
         assert val == [0.5]
 
         vocs.constraints = {}
-        idx, val = vocs.select_best(test_data)
+        idx, val, _ = vocs.select_best(test_data)
         assert idx == 1
         assert val == 0.1
 

xopt/asynchronous.py

@@ -31,7 +31,8 @@ def submit_data(
         """
         Submit data to evaluator and return futures indexed to internal futures list.
 
-        Args:
+        Parameters
+        ----------
             input_data: dataframe containing input data
 
         """

xopt/generators/bayesian/bax/acquisition.py

@@ -20,7 +20,8 @@ class ModelListExpectedInformationGain(MultiObjectiveAnalyticAcquisitionFunction
         >>> EIG = ExpectedInformationGain(model, algo)
         >>> eig = EIG(test_X)
 
-        Args:
+        Parameters
+        ----------
             model: A fitted independent multi-output (ModelList) model.
     """
 
@@ -62,13 +63,15 @@ def __init__(self, model: Model, algorithm: Algorithm, bounds: Tensor) -> None:
     def forward(self, X: Tensor) -> Tensor:
         r"""Evaluate Expected Information Gain on the candidate set X.
 
-        Args:
+        Parameters
+        ----------
             X: A `(b1 x ... bk) x 1 x d`-dim batched tensor of `d`-dim design points.
                 Expected Information Gain is computed for each point individually,
                 i.e., what is considered are the marginal posteriors, not the
                 joint.
 
-        Returns:
+        Returns
+        -------
             A `(b1 x ... bk)`-dim tensor of Expected Information Gain values at the
             given design points `X`.
         """

xopt/generators/bayesian/bayesian_exploration.py

@@ -55,7 +55,8 @@ def __init__(
         X_pending: Optional[Tensor] = None,
     ) -> None:
         r"""q-Upper Confidence Bound.
-        Args:
+        Parameters
+        ----------
             model: A fitted model.
             sampler: The sampler used to draw base samples. Defaults to
                 `SobolQMCNormalSampler(num_samples=512, collapse_batch_dims=True)`
@@ -79,10 +80,13 @@ def __init__(
     @t_batch_mode_transform()
     def forward(self, X: Tensor) -> Tensor:
         r"""Evaluate qUpperConfidenceBound on the candidate set `X`.
-        Args:
+        Parameters
+        ----------
             X: A `batch_sahpe x q x d`-dim Tensor of t-batches with `q` `d`-dim design
                 points each.
-        Returns:
+
+        Returns
+        -------
             A `batch_shape'`-dim Tensor of Upper Confidence Bound values at the given
             design points `X`, where `batch_shape'` is the broadcasted batch shape of
             model and input `X`.

xopt/generators/bayesian/custom_botorch/constrained_acquisition.py

@@ -29,7 +29,8 @@ def ones_callable(Z, X=None):
     def forward(self, samples: Tensor, X: Optional[Tensor] = None) -> Tensor:
         r"""Evaluate the feasibility-weighted objective on the samples.
 
-        Args:
+        Parameters
+        ----------
             samples: A `sample_shape x batch_shape x q x m`-dim Tensors of
                 samples from a model posterior.
             X: A `batch_shape x q x d`-dim tensor of inputs. Relevant only if

xopt/generators/bayesian/custom_botorch/heteroskedastic.py

@@ -38,7 +38,8 @@ def __init__(
         to specify mean and covariance modules.
 
 
-        Args:
+        Parameters
+        ----------
             train_X: A `batch_shape x n x d` tensor of training features.
             train_Y: A `batch_shape x n x m` tensor of training observations.
             train_Yvar: A `batch_shape x n x m` tensor of observed measurement

xopt/generators/bayesian/custom_botorch/identity.py

@@ -11,10 +11,13 @@ def __init__(self, model) -> None:
     @t_batch_mode_transform()
     def forward(self, X: Tensor) -> Tensor:
         r"""Evaluate qUpperConfidenceBound on the candidate set `X`.
-        Args:
+        Parameters
+        ----------
             X: A `batch_sahpe x q x d`-dim Tensor of t-batches with `q` `d`-dim design
                 points each.
-        Returns:
+
+        Returns
+        -------
             A `batch_shape'`-dim Tensor of Upper Confidence Bound values at the given
             design points `X`, where `batch_shape'` is the broadcasted batch shape of
             model and input `X`.

xopt/generators/bayesian/custom_botorch/proximal.py

@@ -55,7 +55,8 @@ def __init__(
         r"""Derived Acquisition Function weighted by proximity to recently
         observed point.
 
-        Args:
+        Parameters
+        ----------
             acq_function: The base acquisition function, operating on input tensors
                 of feature dimension `d`.
             proximal_weights: A `d` dim tensor used to bias locality
@@ -89,10 +90,12 @@ def __init__(
     def forward(self, X: Tensor) -> Tensor:
         r"""Evaluate base acquisition function with proximal weighting.
 
-        Args:
+        Parameters
+        ----------
             X: Input tensor of feature dimension `d` .
 
-        Returns:
+        Returns
+        -------
             Base acquisition function evaluated on tensor `X` multiplied by proximal
             weighting.
         """
@@ -143,7 +146,8 @@ def _validate_model(model: Model, proximal_weights: Tensor) -> None:
     Perform vaidation checks on model used in base acquisition function to make sure
     it is compatible with proximal weighting.
 
-    Args:
+    Parameters
+    ----------
         model: Model associated with base acquisition function to be validated.
         proximal_weights: A `d` dim tensor used to bias locality
                 along each axis.

xopt/generators/bayesian/models/prior_mean.py

@@ -14,7 +14,8 @@ def __init__(
     ):
         """Custom prior mean for a GP based on an arbitrary model.
 
-        Args:
+        Parameters
+        ----------
             model: Representation of the model.
             input_transformer: Module used to transform inputs in the GP.
             outcome_transformer: Module used to transform outcomes in the GP.

xopt/generators/bayesian/visualize.py

@@ -22,22 +22,36 @@ def visualize_generator_model(
     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.
 
-    Args:
-        generator: Bayesian generator object.
-        output_names: Outputs for which the GP models are displayed. Defaults to all outputs in generator.vocs.
-        variable_names: The variables with respect to which the GP models are displayed (maximum of 2).
-          Defaults to generator.vocs.variable_names.
-        idx: 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: Reference point determining the value of variables in generator.vocs.variable_names,
-          but not in variable_names (slice plots in higher dimensions). Defaults to last used sample.
-        show_samples: Whether samples are shown.
-        show_prior_mean: Whether the prior mean is shown.
-        show_feasibility: Whether the feasibility region is shown.
-        show_acquisition: Whether the acquisition function is computed and shown.
-        n_grid: Number of grid points per dimension used to display the model predictions.
+    Parameters
+    ----------
+        generator : Generator
+            Bayesian generator object.
+        output_names : List[str]
+            Outputs for which the GP models are displayed. Defaults to all outputs in
+            generator.vocs.
+        variable_names : List[str]
+            The variables with respect to which the GP models are displayed (maximum
+            of 2). Defaults to generator.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
+            generator.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.
+        n_grid : int, optional
+        Number of grid points per dimension used to display the model predictions.
 
     Returns:
+    --------
         The matplotlib figure and axes objects.
     """
 

xopt/pydantic.py

@@ -600,12 +600,14 @@ def get_callable_from_string(callable: str, bind: Any = None) -> Callable:
     """Get callable from a string. In the case that the callable points to a bound method,
     the function returns a callable taking the bind instance as the first arg.
 
-    Args:
+        Parameters
+        ----------
         callable: String representation of callable abiding convention
              __module__:callable
         bind: Class to bind as self
 
-    Returns:
+    Returns
+    -------
         Callable
     """
     callable_split = callable.rsplit(".", 1)