Botorch with cardinality constraint via sampling

CHANGELOG.md

@@ -9,6 +9,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `BCUT2D` encoding for `SubstanceParameter`
 - Stored benchmarking results now include the Python environment and version
 - `qPSTD` acquisition function
+- `ContinuousCardinalityConstraint` is now compatible with `BotorchRecommender`
+- A `MinimumCardinalityViolatedWarning` is triggered when minimum cardinality
+  constraints are violated
+- Attribute `max_n_subspaces` to `BotorchRecommender`, allowing to control
+  optimization behavior in the presence of cardinality constraints
+- Utilities `inactive_parameter_combinations` and`n_inactive_parameter_combinations` 
+  in both `ContinuousCardinalityConstraint`and `SubspaceContinuous`
+- Attribute `relative_threshold` and method `get_absolute_thresholds` to 
+  `ContinuousCardinalityConstraint`
+- Utilities `activate_parameter`, `is_between` and `is_cardinality_fulfilled`
 
 ### Changed
 - Acquisition function indicator `is_mc` has been removed in favor of new indicators 

README.md

@@ -42,6 +42,7 @@ The following provides a non-comprehensive overview:
 - 🎭 Hybrid (mixed continuous and discrete) spaces
 - 🚀 Transfer learning: Mix data from multiple campaigns and accelerate optimization
 - 🎰 Bandit models: Efficiently find the best among many options in noisy environments (e.g. A/B Testing)
+- 🔢 Cardinality constraints: Control the number of active factors in your design
 - 🌎 Distributed workflows: Run campaigns asynchronously with pending experiments
 - 🎓 Active learning: Perform smart data acquisition campaigns
 - ⚙️ Custom surrogate models: Enhance your predictions through mechanistic understanding

baybe/constraints/continuous.py

@@ -4,11 +4,13 @@
 
 import gc
 import math
-from collections.abc import Collection, Sequence
+from collections.abc import Collection, Iterator, Sequence
+from itertools import combinations
+from math import comb
 from typing import TYPE_CHECKING, Any
 
 import numpy as np
-from attr.validators import in_
+from attr.validators import gt, in_, lt
 from attrs import define, field
 
 from baybe.constraints.base import (
@@ -17,6 +19,7 @@
     ContinuousNonlinearConstraint,
 )
 from baybe.parameters import NumericalContinuousParameter
+from baybe.utils.interval import Interval
 from baybe.utils.numerical import DTypeFloatNumpy
 from baybe.utils.validation import finite_float
 
@@ -138,6 +141,40 @@ class ContinuousCardinalityConstraint(
 ):
     """Class for continuous cardinality constraints."""
 
+    relative_threshold: float = field(
+        default=1e-2, converter=float, validator=[gt(0.0), lt(1.0)]
+    )
+    """A relative threshold for determining if a value is considered zero.
+
+    The threshold is translated into an asymmetric open interval around zero via
+    :meth:`get_absolute_thresholds`.
+
+    **Note:** The interval induced by the threshold is considered **open** because
+    numerical routines that optimize parameter values on the complementary set (i.e. the
+    value range considered "nonzero") may push the numerical value exactly to the
+    interval boundary, which should therefore also be considered "nonzero".
+    """
+
+    @property
+    def n_inactive_parameter_combinations(self) -> int:
+        """The number of possible inactive parameter combinations."""
+        return sum(
+            comb(len(self.parameters), n_inactive_parameters)
+            for n_inactive_parameters in self._inactive_set_sizes()
+        )
+
+    def _inactive_set_sizes(self) -> range:
+        """Get all possible sizes of inactive parameter sets."""
+        return range(
+            len(self.parameters) - self.max_cardinality,
+            len(self.parameters) - self.min_cardinality + 1,
+        )
+
+    def inactive_parameter_combinations(self) -> Iterator[frozenset[str]]:
+        """Get an iterator over all possible combinations of inactive parameters."""
+        for n_inactive_parameters in self._inactive_set_sizes():
+            yield from combinations(self.parameters, n_inactive_parameters)
+
     def sample_inactive_parameters(self, batch_size: int = 1) -> list[set[str]]:
         """Sample sets of inactive parameters according to the cardinality constraints.
 
@@ -176,6 +213,34 @@ def sample_inactive_parameters(self, batch_size: int = 1) -> list[set[str]]:
 
         return inactive_params
 
+    def get_absolute_thresholds(self, bounds: Interval, /) -> Interval:
+        """Get the absolute thresholds for a given interval.
+
+        Turns the relative threshold of the constraint into absolute thresholds
+        for the considered interval. That is, for a given interval ``(a, b)`` with
+        ``a <= 0`` and ``b >= 0``, the method returns the interval ``(r*a, r*b)``,
+        where ``r`` is the relative threshold defined by the constraint.
+
+        Args:
+            bounds: The specified interval.
+
+        Returns:
+            The absolute thresholds represented as an interval.
+
+        Raises:
+            ValueError: When the specified interval does not contain zero.
+        """
+        if not bounds.contains(0.0):
+            raise ValueError(
+                f"The specified interval must contain zero. "
+                f"Given: {bounds.to_tuple()}."
+            )
+
+        return Interval(
+            lower=self.relative_threshold * bounds.lower,
+            upper=self.relative_threshold * bounds.upper,
+        )
+
 
 # Collect leftover original slotted classes processed by `attrs.define`
 gc.collect()

baybe/constraints/utils.py

@@ -0,0 +1,50 @@
+"""Constraint utilities."""
+
+import numpy as np
+import pandas as pd
+
+from baybe.searchspace import SubspaceContinuous
+from baybe.utils.dataframe import is_between
+
+
+def is_cardinality_fulfilled(
+    df: pd.DataFrame,
+    subspace_continuous: SubspaceContinuous,
+    *,
+    check_minimum: bool = True,
+    check_maximum: bool = True,
+) -> bool:
+    """Validate cardinality constraints in a dataframe of parameter configurations.
+
+    Args:
+        df: The dataframe to be checked.
+        subspace_continuous: The subspace spanned by the considered parameters.
+        check_minimum: If ``True``, minimum cardinality constraints are validated.
+        check_maximum: If ``True``, maximum cardinality constraints are validated.
+
+    Returns:
+        ``True`` if all cardinality constraints are fulfilled, ``False`` otherwise.
+    """
+    if len(subspace_continuous.constraints_cardinality) == 0:
+        return True
+
+    for c in subspace_continuous.constraints_cardinality:
+        # Get the activity thresholds for all parameters
+        thresholds = {
+            p.name: c.get_absolute_thresholds(p.bounds)
+            for p in subspace_continuous.get_parameters_by_name(c.parameters)
+        }
+
+        # Count the number of active values per dataframe row
+        cols = df[c.parameters]
+        is_inactive = is_between(cols, thresholds) | (cols == 0.0)
+        n_zeros = is_inactive.sum(axis=1)
+        n_active = len(c.parameters) - n_zeros
+
+        # Check if cardinality is violated
+        if check_minimum and np.any(n_active < c.min_cardinality):
+            return False
+        if check_maximum and np.any(n_active > c.max_cardinality):
+            return False
+
+    return True

baybe/constraints/validation.py

@@ -8,8 +8,14 @@
 from baybe.constraints.discrete import (
     DiscreteDependenciesConstraint,
 )
+from baybe.parameters import NumericalContinuousParameter
 from baybe.parameters.base import Parameter
 
+try:  # For python < 3.11, use the exceptiongroup backport
+    ExceptionGroup
+except NameError:
+    from exceptiongroup import ExceptionGroup
+
 
 def validate_constraints(  # noqa: DOC101, DOC103
     constraints: Collection[Constraint], parameters: Collection[Parameter]
@@ -26,6 +32,8 @@ def validate_constraints(  # noqa: DOC101, DOC103
         ValueError: If any discrete constraint includes a continuous parameter.
         ValueError: If any discrete constraint that is valid only for numerical
             discrete parameters includes non-numerical discrete parameters.
+        ValueError: If any parameter affected by a cardinality constraint does
+            not include zero.
     """
     if sum(isinstance(itm, DiscreteDependenciesConstraint) for itm in constraints) > 1:
         raise ValueError(
@@ -41,6 +49,9 @@ def validate_constraints(  # noqa: DOC101, DOC103
     param_names_discrete = [p.name for p in parameters if p.is_discrete]
     param_names_continuous = [p.name for p in parameters if p.is_continuous]
     param_names_non_numerical = [p.name for p in parameters if not p.is_numerical]
+    params_continuous: list[NumericalContinuousParameter] = [
+        p for p in parameters if isinstance(p, NumericalContinuousParameter)
+    ]
 
     for constraint in constraints:
         if not all(p in param_names_all for p in constraint.parameters):
@@ -78,6 +89,11 @@ def validate_constraints(  # noqa: DOC101, DOC103
                 f"Parameter list of the affected constraint: {constraint.parameters}."
             )
 
+        if isinstance(constraint, ContinuousCardinalityConstraint):
+            validate_cardinality_constraint_parameter_bounds(
+                constraint, params_continuous
+            )
+
 
 def validate_cardinality_constraints_are_nonoverlapping(
     constraints: Collection[ContinuousCardinalityConstraint],
@@ -98,3 +114,50 @@ def validate_cardinality_constraints_are_nonoverlapping(
                 f"cannot share the same parameters. Found the following overlapping "
                 f"parameter sets: {s1}, {s2}."
             )
+
+
+def validate_cardinality_constraint_parameter_bounds(
+    constraint: ContinuousCardinalityConstraint,
+    parameters: Collection[NumericalContinuousParameter],
+) -> None:
+    """Validate that all parameters of a continuous cardinality constraint include zero.
+
+    Args:
+        constraint: A continuous cardinality constraint.
+        parameters: A collection of parameters, including those affected by the
+            constraint.
+
+    Raises:
+        ValueError: If one of the affected parameters does not include zero.
+        ExceptionGroup: If several of the affected parameters do not include zero.
+    """
+    exceptions = []
+    for name in constraint.parameters:
+        try:
+            parameter = next(p for p in parameters if p.name == name)
+        except StopIteration as ex:
+            raise ValueError(
+                f"The parameter '{name}' referenced by the constraint is not contained "
+                f"in the given collection of parameters."
+            ) from ex
+
+        if not parameter.is_in_range(0.0):
+            exceptions.append(
+                ValueError(
+                    f"The bounds of all parameters affected by a constraint of type "
+                    f"'{ContinuousCardinalityConstraint.__name__}' must include zero, "
+                    f"but the bounds of parameter '{name}' are: "
+                    f"{parameter.bounds.to_tuple()}, which may indicate unintended "
+                    f"settings in your parameter definition. "
+                    f"A parameter whose value range includes zero trivially "
+                    f"increases the cardinality of the resulting configuration by one. "
+                    f"Therefore, if your parameter definitions are all correct, "
+                    f"consider excluding the parameter from the constraint and "
+                    f"reducing the cardinality limits by one accordingly."
+                )
+            )
+
+    if exceptions:
+        if len(exceptions) == 1:
+            raise exceptions[0]
+        raise ExceptionGroup("Invalid parameter bounds", exceptions)

baybe/exceptions.py

@@ -11,6 +11,10 @@ class UnusedObjectWarning(UserWarning):
     """
 
 
+class MinimumCardinalityViolatedWarning(UserWarning):
+    """Minimum cardinality constraints are violated."""
+
+
 ##### Exceptions #####
 
 
@@ -37,6 +41,10 @@ class IncompatibleArgumentError(IncompatibilityError):
     """An incompatible argument was passed to a callable."""
 
 
+class InfeasibilityError(Exception):
+    """An optimization problem has no feasible solution."""
+
+
 class NotEnoughPointsLeftError(Exception):
     """
     More recommendations are requested than there are viable parameter configurations

baybe/parameters/numerical.py

@@ -136,7 +136,7 @@ def is_in_range(self, item: float) -> bool:
 
     @override
     @property
-    def comp_rep_columns(self) -> tuple[str, ...]:
+    def comp_rep_columns(self) -> tuple[str]:
         return (self.name,)
 
     @override
@@ -150,5 +150,38 @@ def summary(self) -> dict:
         return param_dict
 
 
+@define(frozen=True, slots=False)
+class _FixedNumericalContinuousParameter(ContinuousParameter):
+    """Parameter class for fixed numerical parameters."""
+
+    is_numeric: ClassVar[bool] = True
+    # See base class.
+
+    value: float = field(converter=float)
+    """The fixed value of the parameter."""
+
+    @property
+    def bounds(self) -> Interval:
+        """The value of the parameter as a degenerate interval."""
+        return Interval(self.value, self.value)
+
+    @override
+    def is_in_range(self, item: float) -> bool:
+        return item == self.value
+
+    @override
+    @property
+    def comp_rep_columns(self) -> tuple[str]:
+        return (self.name,)
+
+    @override
+    def summary(self) -> dict:
+        return dict(
+            Name=self.name,
+            Type=self.__class__.__name__,
+            Value=self.value,
+        )
+
+
 # Collect leftover original slotted classes processed by `attrs.define`
 gc.collect()