ForeTiS.model.mlpbayes

Module Contents

Classes

Mlpbayes

Implementation of a class for a bayesian feedforward Multilayer Perceptron (MLP).
class ForeTiS.model.mlpbayes.Mlpbayes(optuna_trial, datasets, featureset_name, optimize_featureset, pca_transform=None, current_model_name=None, batch_size=None, n_epochs=None, target_column=None)

Bases: ForeTiS.model._torch_model.TorchModel

Implementation of a class for a bayesian feedforward Multilayer Perceptron (MLP).

See BaseModel and TorchModel for more information on the attributes.

Parameters:

  • optuna_trial (optuna.trial.Trial) –

  • datasets (list) –

  • featureset_name (str) –

  • optimize_featureset (bool) –

  • pca_transform (bool) –

  • current_model_name (str) –

  • batch_size (int) –

  • n_epochs (int) –

  • target_column (str) –

define_model()

Definition of an MLP network.

Architecture:

  • N_LAYERS of (bayesian Linear (+ ActivationFunction) (+ BatchNorm) + Dropout)

  • Bayesian Linear output layer

  • Dropout layer

Number of units in the first bayesian linear layer and percentage decrease after each may be fixed or optimized.

Return type:

torch.nn.Sequential

define_hyperparams_to_tune()

See BaseModel for more information on the format.

See TorchModel for more information on hyperparameters common for all torch models.

Return type:

dict

predict(X_in)

Implementation of a prediction based on input features for PyTorch models. See BaseModel for more information

Parameters:

X_in (pandas.DataFrame) –

Return type:

numpy.array