macrosynergy.learning.forecasting.nn.regressors#

class MLPRegressor(n_latent, loss_func=MSELoss(), weight_decay=0.0001, reg_turnover=0, batch_size=16, learning_rate=0.0003, use_ts_sampler=True, encoder_activation='tanh', head_activation='identity', fit_encoder_intercept=False, fit_head_intercept=True, epochs=10000, patience=1000, train_pct=0.7, verbose=False, random_state=42, inverse_transform_preds=False)[source]#

Bases: BaseEstimator, RegressorMixin

Scikit-learn compatible multi-layer perceptron (MLP) regressor implemented in PyTorch.

This estimator wraps macrosynergy.learning.forecasting.torch.MultiLayerPerceptron and trains it via macrosynergy.learning.forecasting.torch.MLPTrainer, including optional scaling of inputs and targets using sklearn.preprocessing.StandardScaler.

Parameters:

  • n_latent (int) – Number of hidden units in the latent layer of the MLP.

  • loss_func (torch.nn.Module, optional) – Loss function used during training. Default is nn.MSELoss().

  • weight_decay (float, optional) – L2 regularization strength applied via the optimizer. Default is 1e-4.

  • reg_turnover (float, optional) – Additional turnover regularization penalty applied by the trainer. Default is 0.

  • batch_size (int, optional) – Batch size used during training. Default is 16.

  • learning_rate (float, optional) – Learning rate used by the optimizer. Default is 3e-4.

  • use_ts_sampler (bool, optional) – Whether to use time-series batch sampling during training. Default is True.

  • encoder_activation (str, optional) – Activation function for the encoder (hidden) component of the network. Default is “tanh”.

  • head_activation (str, optional) – Activation function for the head (output) component of the network. Default is “identity”.

  • fit_encoder_intercept (bool, optional) – Whether to include an intercept (bias term) in the encoder layers. Default is False.

  • fit_head_intercept (bool, optional) – Whether to include an intercept (bias term) in the output layer. Default is True.

  • epochs (int, optional) – Maximum number of training epochs. Default is 10000.

  • patience (int, optional) – Number of epochs to wait for improvement before early stopping. Default is 1000.

  • train_pct (float, optional) – Fraction of samples used for training (remainder used for validation). Default is 0.7.

  • verbose (bool, optional) – Whether to print training diagnostics. Default is False.

  • random_state (int, optional) – Random seed used for PyTorch initialization and training. Default is 42.

  • inverse_transform_preds (bool, optional) – Whether to inverse-transform predictions back to the original target scale using the fitted target scaler. Default is False.

fit(X, y)[source]#
predict(X)[source]#
set_score_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → MLPRegressor#

Configure whether metadata should be requested to be passed to the score method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to score.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

New in version 1.3.

Parameters:

sample_weight (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for sample_weight parameter in score.

Returns:

self – The updated object.

Return type:

object