Skip to main content

MLPRegression

Model
DashAI.back.models.scikit_learn.MLPRegression

Single hidden-layer MLP regressor implemented in PyTorch.

A Multi-layer Perceptron (MLP) is a feedforward neural network composed of an input layer, one hidden layer of configurable width, and a single linear output neuron. The hidden layer uses a configurable activation function (ReLU, tanh, sigmoid, or identity). The network is trained by minimising the mean squared error using the Adam optimiser and mini-batch gradient descent via backpropagation.

Key hyperparameters include hidden_size (number of neurons in the hidden layer), activation, learning_rate, epochs, batch_size, and device (CPU or GPU). The model also supports per-epoch and per-step metric logging. The implementation uses PyTorch (torch.nn).

References​

Parameters​

hidden_size : integer, default=5
Number of neurons in the hidden layer.
activation : string, default=relu
Activation function.
learning_rate : number, default=0.001
Initial learning rate for the optimizer.
epochs : integer, default=5
Total number of training passes over the dataset.
batch_size, default=32
Number of samples per gradient update during training. If greater than dataset size or None, uses full dataset.
device : string, default=CPU
Hardware device (CPU/GPU).
log_train_every_n_epochs, default=1
Log metrics for train split every n epochs during training. If None, it won't log per epoch.
log_train_every_n_steps, default=None
Log metrics for train split every n steps during training. If None, it won't log per step.
log_validation_every_n_epochs, default=1
Log metrics for validation split every n epochs during training. If None, it won't log per epoch.
log_validation_every_n_steps, default=None
Log metrics for validation split every n steps during training. If None, it won't log per step.

Methods​

load(filename: str) -> 'MLPRegression'

Defined on MLPRegression

Restore an MLPRegression instance from a saved checkpoint.

Parameters

filename : str
Path to the checkpoint file saved by save.

Returns

MLPRegression
The restored model instance with loaded weights.

predict(self, x: 'DashAIDataset') -> 'ndarray'

Defined on MLPRegression

Generate regression predictions for the input dataset.

Parameters

x : DashAIDataset
The input features to predict on.

Returns

ndarray
Predicted continuous values as a 1-D NumPy array.

save(self, filename: str) -> None

Defined on MLPRegression

Save the trained model weights and configuration to disk.

Parameters

filename : str
Path where the model checkpoint will be saved.

train(self, x_train: 'DashAIDataset', y_train: 'DashAIDataset', x_validation: 'DashAIDataset' = None, y_validation: 'DashAIDataset' = None) -> 'MLPRegression'

Defined on MLPRegression

Train the MLP regressor using Adam optimiser and MSE loss.

Parameters

x_train : DashAIDataset
The input features for training.
y_train : DashAIDataset
The regression targets for training.
x_validation : DashAIDataset, optional
Input features for validation metric logging. Defaults to None.
y_validation : DashAIDataset, optional
Target values for validation metric logging. Defaults to None.

Returns

MLPRegression
The trained model instance (self).

calculate_metrics(self, split: DashAI.back.core.enums.metrics.SplitEnum = <SplitEnum.VALIDATION: 'validation'>, level: DashAI.back.core.enums.metrics.LevelEnum = <LevelEnum.LAST: 'last'>, log_index: int = None, x_data: 'DashAIDataset' = None, y_data: 'DashAIDataset' = None)

Defined on BaseModel

Calculate and save metrics for a given data split and level.

Parameters

split : SplitEnum
The data split to evaluate (TRAIN, VALIDATION, or TEST). Defaults to SplitEnum.VALIDATION.
level : LevelEnum
The metric granularity level (LAST, TRIAL, STEP, or BATCH). Defaults to LevelEnum.LAST.
log_index : int, optional
Explicit step index for the metric entry. If None, the next step index is computed automatically. Defaults to None.
x_data : DashAIDataset, optional
Input features. If None, the dataset stored in the model for the given split is used. Defaults to None.
y_data : DashAIDataset, optional
Target labels. If None, the labels stored in the model for the given split are used. Defaults to None.

get_metadata(cls) -> Dict[str, Any]

Defined on BaseModel

Get metadata values for the current model.

Returns

Dict[str, Any]
Dictionary containing UI metadata such as the model icon used in the DashAI frontend.

get_schema(cls) -> dict

Defined on ConfigObject

Generates the component related Json Schema.

Returns

dict
Dictionary representing the Json Schema of the component.

prepare_dataset(self, dataset: 'DashAIDataset', is_fit: bool = False) -> 'DashAIDataset'

Defined on BaseModel

Hook for model-specific preprocessing of input features.

Parameters

dataset : DashAIDataset
The input dataset to preprocess.
is_fit : bool
Whether the call is part of a fitting phase. Defaults to False.

Returns

DashAIDataset
The preprocessed dataset ready to be fed into the model.

prepare_output(self, dataset: 'DashAIDataset', is_fit: bool = False) -> 'DashAIDataset'

Defined on BaseModel

Hook for model-specific preprocessing of output targets.

Parameters

dataset : DashAIDataset
The output dataset (target labels) to preprocess.
is_fit : bool
Whether the call is part of a fitting phase. Defaults to False.

Returns

DashAIDataset
The preprocessed output dataset.

validate_and_transform(self, raw_data: dict) -> dict

Defined on ConfigObject

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Parameters

raw_data : dict
A dictionary with the data provided by the user to initialize the model.

Returns

dict
A validated dictionary with the necessary objects.

Compatible with​