Model Building with BoFire

This notebooks shows how to setup and analyze models trained with BoFire. It is still WIP.

Imports

from pydantic import TypeAdapter

import bofire.surrogates.api as surrogates
from bofire.benchmarks.multi import CrossCoupling
from bofire.benchmarks.single import Himmelblau
from bofire.data_models.domain.api import Outputs
from bofire.data_models.encodings.api import OrdinalEncoding
from bofire.data_models.surrogates.api import (
    AnySurrogate,
    EmpiricalSurrogate,
    MixedSingleTaskGPSurrogate,
    RandomForestSurrogate,
    RegressionMLPEnsemble,
    SingleTaskGPSurrogate,
)
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/torch/jit/_script.py:1491: FutureWarning: `torch.jit.script` is deprecated. Please switch to `torch.compile` or `torch.export`.
  warnings.warn(
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/torch/jit/_script.py:1491: FutureWarning: `torch.jit.script` is deprecated. Please switch to `torch.compile` or `torch.export`.
  warnings.warn(

Problem Setup

For didactic purposes, we sample data from a Himmelblau benchmark function and use them to train a SingleTaskGP.

benchmark = Himmelblau()
samples = benchmark.domain.inputs.sample(n=50)
experiments = benchmark.f(samples, return_complete=True)

experiments.head(10)
x_1 x_2 y valid_y
0 -0.059360 -4.087916 320.694187 1
1 1.918462 -4.190780 288.264542 1
2 3.451916 -1.849742 0.888401 1
3 -3.466299 0.596358 104.822570 1
4 -4.248998 4.057608 150.665579 1
5 0.371828 5.035361 384.635748 1
6 -4.661100 -5.131463 246.529997 1
7 3.775708 -5.890923 997.850668 1
8 3.804614 2.818457 62.155210 1
9 3.147430 -4.997512 483.265238 1

Model Fitting

input_features = benchmark.domain.inputs
output_features = benchmark.domain.outputs
input_features.model_dump_json()
'{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]}'
output_features.model_dump_json()
'{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","context":null,"unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]}'

Single Task GP

Generate the json spec

# we setup the data model, here a Single Task GP
surrogate_data = SingleTaskGPSurrogate(inputs=input_features, outputs=output_features)

# we generate the json spec
jspec = surrogate_data.model_dump_json()

jspec
'{"hyperconfig":{"type":"SingleTaskGPHyperconfig","hyperstrategy":"FractionalFactorialStrategy","inputs":{"type":"Inputs","features":[{"type":"CategoricalInput","key":"kernel","context":null,"categories":["rbf","matern_1.5","matern_2.5"],"descriptors":null,"allowed":[true,true,true]},{"type":"CategoricalInput","key":"prior","context":null,"categories":["mbo","threesix","hvarfner"],"descriptors":null,"allowed":[true,true,true]},{"type":"CategoricalInput","key":"scalekernel","context":null,"categories":["True","False"],"descriptors":null,"allowed":[true,true]},{"type":"CategoricalInput","key":"ard","context":null,"categories":["True","False"],"descriptors":null,"allowed":[true,true]}]},"n_iterations":null,"target_metric":"MAE","lengthscale_constraint":null,"outputscale_constraint":null},"type":"SingleTaskGPSurrogate","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","context":null,"unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"dump":null,"categorical_encodings":{},"engineered_features":{"type":"EngineeredFeatures","features":[]},"scaler":{"type":"Normalize","features":[]},"output_scaler":"STANDARDIZE","kernel":{"type":"RBFKernel","features":null,"lengthscale_prior":{"type":"DimensionalityScaledLogNormalPrior","loc":1.4142135623730951,"loc_scaling":0.5,"scale":1.7320508075688772,"scale_scaling":0.0},"lengthscale_constraint":null,"ard":true},"noise_prior":{"type":"LogNormalPrior","loc":-4.0,"scale":1.0},"noise_constraint":{"type":"GreaterThan","initial_value":null,"lower_bound":0.0001}}'

Load it from the spec

surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)

Map it

surrogate = surrogates.map(surrogate_data)

Fit it. This is not 100% finished. In the future we will call here hyperfit which will return the CV results etc. This has to be finished. So ignore this for now and just call fit.

surrogate.fit(experiments=experiments)
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/bofire/utils/torch_tools.py:51: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /__w/pytorch/pytorch/torch/csrc/utils/tensor_numpy.cpp:213.)
  return torch.from_numpy(np.ascontiguousarray(df.to_numpy())).to(**tkwargs)

Dump it.

# dump it
dump = surrogate.dumps()

Make predictions.

# predict with it
df_predictions = surrogate.predict(experiments)
# transform to spec
predictions = surrogate.to_predictions(predictions=df_predictions)

Load again from spec and dump and make predictions.

surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
surrogate = surrogates.map(surrogate_data)
surrogate.loads(dump)

# predict with it
df_predictions2 = surrogate.predict(experiments)
# transform to spec
predictions2 = surrogate.to_predictions(predictions=df_predictions2)

# check for equality
predictions == predictions2
True

Random Forest

Generate the json spec

# we setup the data model, here a Single Task GP
surrogate_data = RandomForestSurrogate(
    inputs=input_features,
    outputs=output_features,
    random_state=42,
)

# we generate the json spec
jspec = surrogate_data.model_dump_json()

jspec
'{"hyperconfig":null,"type":"RandomForestSurrogate","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","context":null,"unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"dump":null,"categorical_encodings":{},"engineered_features":{"type":"EngineeredFeatures","features":[]},"scaler":{"type":"Normalize","features":[]},"output_scaler":"STANDARDIZE","n_estimators":100,"criterion":"squared_error","max_depth":null,"min_samples_split":2,"min_samples_leaf":1,"min_weight_fraction_leaf":0.0,"max_features":1.0,"max_leaf_nodes":null,"min_impurity_decrease":0.0,"bootstrap":true,"oob_score":false,"random_state":42,"ccp_alpha":0.0,"max_samples":null}'
# Load it from the spec
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
# Map it
surrogate = surrogates.map(surrogate_data)
# Fit it
surrogate.fit(experiments=experiments)
# dump it
dump = surrogate.dumps()
# predict with it
df_predictions = surrogate.predict(experiments)
# transform to spec
predictions = surrogate.to_predictions(predictions=df_predictions)
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/botorch/models/ensemble.py:82: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  self.eval()
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2932: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  return self.train(False)
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/botorch/models/ensemble.py:82: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  self.eval()
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2932: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  return self.train(False)
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
surrogate = surrogates.map(surrogate_data)
surrogate.loads(dump)

# predict with it
df_predictions2 = surrogate.predict(experiments)
# transform to spec
predictions2 = surrogate.to_predictions(predictions=df_predictions2)

# check for equality
predictions == predictions2
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/botorch/models/ensemble.py:82: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  self.eval()
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2932: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  return self.train(False)
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/botorch/models/ensemble.py:82: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  self.eval()
/opt/hostedtoolcache/Python/3.12.14/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2932: RuntimeWarning: Could not update `train_inputs` with transformed inputs since _RandomForest does not have a `train_inputs` attribute. Make sure that the `input_transform` is applied to both the train inputs and test inputs.
  return self.train(False)
True

MLP Ensemble

Generate the json spec

# we setup the data model, here a Single Task GP
surrogate_data = RegressionMLPEnsemble(
    inputs=input_features,
    outputs=output_features,
    n_estimators=2,
)

# we generate the json spec
jspec = surrogate_data.model_dump_json()

jspec
'{"hyperconfig":null,"type":"RegressionMLPEnsemble","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","context":null,"unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"dump":null,"categorical_encodings":{},"engineered_features":{"type":"EngineeredFeatures","features":[]},"scaler":null,"output_scaler":"IDENTITY","n_estimators":2,"hidden_layer_sizes":[100],"activation":"relu","dropout":0.0,"batch_size":10,"n_epochs":200,"lr":0.0001,"weight_decay":0.0,"subsample_fraction":1.0,"shuffle":true,"final_activation":"identity"}'
# Load it from the spec
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
# Map it
surrogate = surrogates.map(surrogate_data)
# Fit it
surrogate.fit(experiments=experiments)
# dump it
dump = surrogate.dumps()
# predict with it
df_predictions = surrogate.predict(experiments)
# transform to spec
predictions = surrogate.to_predictions(predictions=df_predictions)
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
surrogate = surrogates.map(surrogate_data)
surrogate.loads(dump)

# predict with it
df_predictions2 = surrogate.predict(experiments)
# transform to spec
predictions2 = surrogate.to_predictions(predictions=df_predictions2)

# check for equality
predictions == predictions2
True

Empirical Surrogate

The empirical model is special as it has per default no fit and you need cloudpickle. There can be empirical models which implement a fit, but for this they also have to inherit from Trainable. The current example is the default without any fit functionality.

from botorch.models.deterministic import DeterministicModel
from torch import Tensor


class HimmelblauModel(DeterministicModel):
    def __init__(self):
        super().__init__()
        self._num_outputs = 1

    def forward(self, X: Tensor) -> Tensor:
        return (
            (X[..., 0] ** 2 + X[..., 1] - 11.0) ** 2
            + (X[..., 0] + X[..., 1] ** 2 - 7.0) ** 2
        ).unsqueeze(-1)
surrogate_data = EmpiricalSurrogate(

    inputs=input_features,
    outputs=output_features,
)

# we generate the json spec
jspec = surrogate_data.model_dump_json()

jspec
'{"type":"EmpiricalSurrogate","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":null,"descriptors":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","context":null,"unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"dump":null,"categorical_encodings":{},"engineered_features":{"type":"EngineeredFeatures","features":[]}}'
# Load it from the spec
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
# Map it
surrogate = surrogates.map(surrogate_data)
# attach the actual model to it
surrogate.model = HimmelblauModel()
# dump it
dump = surrogate.dumps()
# predict with it
df_predictions = surrogate.predict(experiments)
# transform to spec
predictions = surrogate.to_predictions(predictions=df_predictions)
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
surrogate = surrogates.map(surrogate_data)
surrogate.loads(dump)

# predict with it
df_predictions2 = surrogate.predict(experiments)
# transform to spec
predictions2 = surrogate.to_predictions(predictions=df_predictions2)

# check for equality
predictions == predictions2
True

Mixed GP

Generate data for a mixed problem.

benchmark = CrossCoupling()
samples = benchmark.domain.inputs.sample(n=50)
experiments = benchmark.f(samples, return_complete=True)

experiments.head(10)
base_eq t_res temperature base catalyst yield cost valid_cost valid_yield
0 1.380899 1300.180055 30.920790 DBU AlPhos 0.881413 0.420519 1 1
1 2.414180 1216.814754 53.022409 BTMG tBuXPhos 0.929141 0.353691 1 1
2 2.083958 728.907820 38.387974 BTMG tBuXPhos 0.886130 0.339267 1 1
3 2.401124 715.264312 51.193121 BTMG tBuBrettPhos 1.011520 0.383151 1 1
4 2.073627 61.367798 41.703372 TMG tBuBrettPhos -0.028579 0.278346 1 1
5 1.241610 1271.528190 57.280329 TMG AlPhos 0.272633 0.419056 1 1
6 1.803938 1377.525561 63.222641 TMG tBuBrettPhos 0.350060 0.278336 1 1
7 1.083250 715.802019 97.267700 DBU tBuBrettPhos 1.026979 0.279453 1 1
8 2.345248 1689.414162 33.429635 BTMG tBuXPhos 0.885450 0.350680 1 1
9 1.282102 1197.841517 34.159671 TMG tBuXPhos 0.115657 0.248286 1 1 
# we setup the data model, here a Single Task GP
surrogate_data = MixedSingleTaskGPSurrogate(
    inputs=benchmark.domain.inputs,
    outputs=Outputs(features=[benchmark.domain.outputs.features[0]]),
    categorical_encodings={"catalyst": OrdinalEncoding()},
)

# we generate the json spec
jspec = surrogate_data.model_dump_json()

jspec
'{"hyperconfig":{"type":"MixedSingleTaskGPHyperconfig","hyperstrategy":"FractionalFactorialStrategy","inputs":{"type":"Inputs","features":[{"type":"CategoricalInput","key":"continuous_kernel","context":null,"categories":["rbf","matern_1.5","matern_2.5"],"descriptors":null,"allowed":[true,true,true]},{"type":"CategoricalInput","key":"prior","context":null,"categories":["mbo","threesix","hvarfner"],"descriptors":null,"allowed":[true,true,true]},{"type":"CategoricalInput","key":"ard","context":null,"categories":["True","False"],"descriptors":null,"allowed":[true,true]}]},"n_iterations":null,"target_metric":"MAE"},"type":"MixedSingleTaskGPSurrogate","inputs":{"type":"Inputs","features":[{"type":"CategoricalInput","key":"catalyst","context":null,"categories":["tBuXPhos","tBuBrettPhos","AlPhos"],"descriptors":{"columns":{"area_cat":[460.7543,518.8408,819.933],"M2_cat":[67.2057,89.8738,129.0808]},"structure":null},"allowed":[true,true,true]},{"type":"CategoricalInput","key":"base","context":null,"categories":["TEA","TMG","BTMG","DBU"],"descriptors":{"columns":{"area":[162.2992,165.5447,227.3523,192.4693],"M2":[25.8165,81.4847,30.554,59.8367]},"structure":null},"allowed":[true,true,true,true]},{"type":"ContinuousInput","key":"base_eq","context":null,"unit":null,"descriptors":null,"bounds":[1.0,2.5],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"temperature","context":null,"unit":null,"descriptors":null,"bounds":[30.0,100.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"t_res","context":null,"unit":null,"descriptors":null,"bounds":[60.0,1800.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"yield","context":null,"unit":null,"objective":{"type":"MaximizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"dump":null,"categorical_encodings":{"catalyst":{"type":"OrdinalEncoding"},"base":{"columns":null,"generators":[],"filter_descriptors":false,"correlation_cutoff":0.95,"type":"DescriptorEncoding"}},"engineered_features":{"type":"EngineeredFeatures","features":[]},"scaler":{"type":"Normalize","features":[]},"output_scaler":"STANDARDIZE","continuous_kernel":{"type":"RBFKernel","features":["t_res","base","base_eq","temperature"],"lengthscale_prior":{"type":"DimensionalityScaledLogNormalPrior","loc":1.4142135623730951,"loc_scaling":0.5,"scale":1.7320508075688772,"scale_scaling":0.0},"lengthscale_constraint":{"type":"GreaterThan","initial_value":null,"lower_bound":0.025},"ard":true},"categorical_kernel":{"type":"HammingDistanceKernel","features":["catalyst"],"lengthscale_prior":null,"lengthscale_constraint":{"type":"GreaterThan","initial_value":null,"lower_bound":1e-6},"ard":true},"noise_prior":{"type":"LogNormalPrior","loc":-4.0,"scale":1.0},"noise_constraint":{"type":"GreaterThan","initial_value":null,"lower_bound":0.0001}}'
# Load it from the spec
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
# Map it
surrogate = surrogates.map(surrogate_data)
# Fit it
surrogate.fit(experiments=experiments)
# dump it
dump = surrogate.dumps()
# predict with it
df_predictions = surrogate.predict(experiments)
# transform to spec
predictions = surrogate.to_predictions(predictions=df_predictions)
surrogate_data = TypeAdapter(AnySurrogate).validate_json(jspec)
surrogate = surrogates.map(surrogate_data)
surrogate.loads(dump)

# predict with it
df_predictions2 = surrogate.predict(experiments)
# transform to spec
predictions2 = surrogate.to_predictions(predictions=df_predictions2)

# check for equality
predictions == predictions2
True