src.dienstleister.ml_training.pytorch_utils.py

class MyDataset(df: DataFrame, prediction_columns: list)

Bases: Dataset

A custom dataset for the pytorch regression service.

Parameters:

  • df (pd.DataFrame) – The dataframe containing the data.

  • prediction_columns (list) – The columns to be used as prediction targets.

__getitem__(idx)

Get an item from the dataset.

Parameters:

idx (int) – The index of the item to get.

Returns:

The input and output data.

Return type:

tuple

__len__()

Return the length of the dataset.

Returns:

The length of the dataset.

Return type:

int

class DemonstratorNeuralNet(input_dim, hidden_dim, output_dim, *args, **kwargs)

Bases: Module

A simple neural network for demonstration purposes.

Parameters:

  • input_dim (int) – Dimension of the input layer.

  • hidden_dim (int) – Dimension of the hidden layers.

  • output_dim (int) – Dimension of the output layer.

  • args – Positional arguments passed to the superclass or internal use.

  • kwargs – Arbitrary keyword arguments, allowing for extensibility or forwarding to the superclass constructor or other components.

forward(x)

Forward pass through the network.

Parameters:

x – The input to the network.

Returns:

The output of the network.

Return type:

torch.Tensor