practice_sdoml.modeling package

Submodules

practice_sdoml.modeling.evaluate module

Model evaluation module with test set diagnostic figures export.

practice_sdoml.modeling.evaluate.evaluate_and_generate_figures()

practice_sdoml.modeling.model module

class practice_sdoml.modeling.model.SimpleNet(input_dim: int, num_classes: int)

Bases: Module

Feedfordward neural network for tabular classification.

This architecture is created of intermediate lineal layers combined with non-linear activation functions (ReLU) to process input characteristics and predict class probability.

Parameters:

• input_dim (int) – Feature number.

• num_classes (int) – Total number of classes to predict.

forward(x)

Executes fordwars pass of the neural network.

It takes an input tensor batch and spread it over the sequential layers in order to generate non-normalized logits.

Parameters:

x (torch.Tensor) – Input tensor with dimensions (batch_size, input_dim)

Returns:

Output logits with dimensions (batch_size, num_classes)

Return type:

torch.Sensor

practice_sdoml.modeling.predict module

practice_sdoml.modeling.predict.main(features_path: Path = PosixPath('/home/runner/work/practice_sdoml_jn/practice_sdoml_jn/data/processed/test_features.csv'), model_path: Path = PosixPath('/home/runner/work/practice_sdoml_jn/practice_sdoml_jn/models/model.pkl'), predictions_path: Path = PosixPath('/home/runner/work/practice_sdoml_jn/practice_sdoml_jn/data/processed/test_predictions.csv'))

practice_sdoml.modeling.train module

Training module for SimpleNet.

practice_sdoml.modeling.train.train(epochs: int = 3, lr: float = 0.001)

Trains SimpleNet model using provided data by DiabetesDataset

Module contents

Subpaquete de modelado: arquitectura de redes neuronales, entrenamiento y evaluación.