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	3.997745	3.749697	198.520618	1
1	-4.900752	-5.197226	289.479124	1
2	2.548804	-1.461503	40.942618	1
3	0.990973	0.813577	113.312578	1
4	2.969121	-4.625220	347.801320	1
5	-2.776850	-3.458532	50.303039	1
6	2.795511	0.765145	18.953735	1
7	-5.385841	1.893729	473.483993	1
8	4.158167	-5.474849	736.817727	1
9	-1.032279	3.286040	51.850215	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,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"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","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"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"prior","context":null,"categories":["mbo","threesix","hvarfner"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"scalekernel","context":null,"categories":["True","False"],"allowed":[true,true]},{"type":"CategoricalInput","key":"ard","context":null,"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","context":null,"unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":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]}}]},"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":{"type":"GreaterThan","lower_bound":0.0001,"initial_value":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","context":null,"unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":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]}}]},"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:2923: 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:2923: 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:2923: 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:2923: 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","context":null,"unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":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]}}]},"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","context":null,"unit":null,"bounds":[-6.0,6.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"x_2","context":null,"unit":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]}}]},"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	2.241933	1024.288818	67.967984	BTMG	tBuXPhos	0.957393	0.346167	1	1
1	1.718134	625.293570	40.728167	DBU	tBuBrettPhos	0.388571	0.280147	1	1
2	2.107285	394.771246	56.135977	BTMG	AlPhos	0.978862	0.511057	1	1
3	1.905663	1740.652499	87.559711	TMG	tBuXPhos	0.719115	0.248309	1	1
4	2.101812	1094.963480	30.942745	DBU	tBuBrettPhos	0.447111	0.280566	1	1
5	1.515187	730.503027	33.084376	BTMG	tBuXPhos	0.865674	0.314423	1	1
6	2.262176	1658.718880	64.474319	BTMG	tBuBrettPhos	1.014585	0.377082	1	1
7	2.072174	958.211837	80.870451	TMG	tBuBrettPhos	0.667135	0.278346	1	1
8	1.716968	125.888744	91.153046	TMG	tBuXPhos	0.521894	0.248302	1	1
9	1.791164	1635.022712	31.790842	TMG	tBuXPhos	0.116899	0.248304	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","context":null,"categories":["rbf","matern_1.5","matern_2.5"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"prior","context":null,"categories":["mbo","threesix","hvarfner"],"allowed":[true,true,true]},{"type":"CategoricalInput","key":"ard","context":null,"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","context":null,"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","context":null,"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","context":null,"unit":null,"bounds":[1.0,2.5],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"temperature","context":null,"unit":null,"bounds":[30.0,100.0],"local_relative_bounds":null,"stepsize":null,"allow_zero":false},{"type":"ContinuousInput","key":"t_res","context":null,"unit":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]}}]},"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":["t_res","base_eq","base","temperature"],"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,"initial_value":null}},"categorical_kernel":{"type":"HammingDistanceKernel","features":["catalyst"],"ard":true,"lengthscale_prior":null,"lengthscale_constraint":{"type":"GreaterThan","lower_bound":1e-6,"initial_value":null}},"noise_prior":{"type":"LogNormalPrior","loc":-4.0,"scale":1.0},"noise_constraint":{"type":"GreaterThan","lower_bound":0.0001,"initial_value":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