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.enum import CategoricalEncodingEnum
from bofire.data_models.surrogates.api import (
    AnySurrogate,
    EmpiricalSurrogate,
    MixedSingleTaskGPSurrogate,
    RandomForestSurrogate,
    RegressionMLPEnsemble,
    SingleTaskGPSurrogate,
)

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	5.395001	0.987122	364.946366	1
1	-2.750879	5.570551	457.415901	1
2	0.259184	-1.496116	174.750620	1
3	-5.732269	-1.040251	569.142195	1
4	-5.007695	-0.777188	306.928958	1
5	-4.021406	0.014618	148.364694	1
6	-1.792976	-1.684513	125.142887	1
7	3.902579	-2.772682	23.195385	1
8	1.409463	4.505500	236.675707	1
9	-4.828057	0.716342	297.716172	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","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","unit":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","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","categories":["rbf","matern_1.5","matern_2.5"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"prior","categories":["mbo","threesix","hvarfner"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"scalekernel","categories":["True","False"],"allowed":[true,true]},{"type":"CategoricalInput","key":"ard","categories":["True","False"],"allowed":[true,true]}]},"n_iterations":null,"target_metric":"MAE","lengthscale_constraint":null,"outputscale_constraint":null},"engineered_features":{"type":"EngineeredFeatures","features":[]},"type":"SingleTaskGPSurrogate","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"input_preprocessing_specs":{},"dump":null,"categorical_encodings":{},"scaler":{"type":"Normalize","features":[]},"output_scaler":"STANDARDIZE","kernel":{"type":"RBFKernel","features":null,"ard":true,"lengthscale_prior":{"type":"DimensionalityScaledLogNormalPrior","loc":1.4142135623730951,"loc_scaling":0.5,"scale":1.7320508075688772,"scale_scaling":0.0},"lengthscale_constraint":null},"noise_prior":{"type":"LogNormalPrior","loc":-4.0,"scale":1.0},"noise_constraint":null}'

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/3.12.13/x64/lib/python3.12/site-packages/bofire/surrogates/botorch.py:181: 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 /pytorch/torch/csrc/utils/tensor_numpy.cpp:213.)
  torch.from_numpy(Y.values).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,"engineered_features":{"type":"EngineeredFeatures","features":[]},"type":"RandomForestSurrogate","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"input_preprocessing_specs":{},"dump":null,"categorical_encodings":{},"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/3.12.13/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/3.12.13/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2924: 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/3.12.13/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/3.12.13/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2924: 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/3.12.13/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/3.12.13/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2924: 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/3.12.13/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/3.12.13/x64/lib/python3.12/site-packages/torch/nn/modules/module.py:2924: 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,"engineered_features":{"type":"EngineeredFeatures","features":[]},"type":"RegressionMLPEnsemble","inputs":{"type":"Inputs","features":[{"type":"ContinuousInput","key":"x_1","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"input_preprocessing_specs":{},"dump":null,"categorical_encodings":{},"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","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"y","unit":null,"objective":{"type":"MinimizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"input_preprocessing_specs":{},"dump":null,"categorical_encodings":{}}'

# 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	1.893222	561.691023	77.563836	TMG	AlPhos	0.561364	0.419080	1	1
1	1.589289	1131.232671	84.546013	TEA	tBuBrettPhos	0.042195	0.278849	1	1
2	1.040624	642.650489	30.820642	BTMG	AlPhos	0.978809	0.464465	1	1
3	2.029936	771.445061	93.414156	DBU	tBuBrettPhos	1.089295	0.280487	1	1
4	2.455796	60.197432	67.675870	DBU	tBuXPhos	0.831368	0.250921	1	1
5	2.261352	1525.620059	46.840793	DBU	AlPhos	0.838302	0.421480	1	1
6	1.666928	726.588464	82.837658	TMG	AlPhos	0.733730	0.419072	1	1
7	2.043017	637.638942	90.115412	TMG	AlPhos	0.873184	0.419085	1	1
8	2.338512	1585.581632	97.852021	BTMG	tBuXPhos	1.004653	0.350385	1	1
9	1.606380	1673.897472	52.989406	TEA	AlPhos	0.103417	0.419596	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": CategoricalEncodingEnum.ORDINAL},
)

# 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","categories":["rbf","matern_1.5","matern_2.5"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"prior","categories":["mbo","threesix","hvarfner"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"ard","categories":["True","False"],"allowed":[true,true]}]},"n_iterations":null,"target_metric":"MAE"},"engineered_features":{"type":"EngineeredFeatures","features":[]},"type":"MixedSingleTaskGPSurrogate","inputs":{"type":"Inputs","features":[{"type":"CategoricalDescriptorInput","key":"catalyst","categories":["tBuXPhos","tBuBrettPhos","AlPhos"],"allowed":[true,true,true],"descriptors":["area_cat","M2_cat"],"values":[[460.7543,67.2057],[518.8408,89.8738],[819.933,129.0808]]},{"type":"CategoricalDescriptorInput","key":"base","categories":["TEA","TMG","BTMG","DBU"],"allowed":[true,true,true,true],"descriptors":["area","M2"],"values":[[162.2992,25.8165],[165.5447,81.4847],[227.3523,30.554],[192.4693,59.8367]]},{"type":"ContinuousInput","key":"base_eq","unit":null,"bounds":[1.0,2.5],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"temperature","unit":null,"bounds":[30.0,100.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"t_res","unit":null,"bounds":[60.0,1800.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false}]},"outputs":{"type":"Outputs","features":[{"type":"ContinuousOutput","key":"yield","unit":null,"objective":{"type":"MaximizeObjective","w":1.0,"bounds":[0.0,1.0]}}]},"input_preprocessing_specs":{"base":"ORDINAL","catalyst":"ORDINAL"},"dump":null,"categorical_encodings":{"catalyst":"ORDINAL","base":"DESCRIPTOR"},"scaler":{"type":"Normalize","features":[]},"output_scaler":"STANDARDIZE","continuous_kernel":{"type":"RBFKernel","features":["temperature","t_res","base_eq","base"],"ard":true,"lengthscale_prior":{"type":"DimensionalityScaledLogNormalPrior","loc":1.4142135623730951,"loc_scaling":0.5,"scale":1.7320508075688772,"scale_scaling":0.0},"lengthscale_constraint":{"type":"GreaterThan","lower_bound":0.025}},"categorical_kernel":{"type":"HammingDistanceKernel","features":["catalyst"],"ard":true,"lengthscale_prior":null,"lengthscale_constraint":{"type":"GreaterThan","lower_bound":1e-6}},"noise_prior":{"type":"LogNormalPrior","loc":-4.0,"scale":1.0},"noise_constraint":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)

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