autoprognosis.plugins.prediction.regression.plugin_neural_nets_regression module

class BasicNet(*args: Any, **kwargs: Any)

Bases: torch.nn.Module

Basic neural net.

Parameters

  • n_unit_in (int) – Number of features

  • n_layers_hidden (int) – Number of hypothesis layers (n_layers_hidden x n_units_hidden + 1 x Linear layer)

  • n_units_hidden (int) – Number of hidden units in each hypothesis layer

  • nonlin (string, default 'elu') – Nonlinearity to use in NN. Can be ‘elu’, ‘relu’, ‘selu’ or ‘leaky_relu’.

  • lr (float) – learning rate for optimizer. step_size equivalent in the JAX version.

  • weight_decay (float) – l2 (ridge) penalty for the weights.

  • n_iter (int) – Maximum number of iterations.

  • batch_size (int) – Batch size

  • n_iter_print (int) – Number of iterations after which to print updates and check the validation loss.

  • val_split_prop (float) – Proportion of samples used for validation split (can be 0)

  • patience (int) – Number of iterations to wait before early stopping after decrease in validation loss

  • n_iter_min (int) – Minimum number of iterations to go through before starting early stopping

  • clipping_value (int, default 1) – Gradients clipping value

forward(X: torch.Tensor) → torch.Tensor
train(X: torch.Tensor, y: torch.Tensor) → autoprognosis.plugins.prediction.regression.plugin_neural_nets_regression.BasicNet
class NeuralNetsRegressionPlugin(n_layers_hidden: int = 1, n_units_hidden: int = 100, nonlin: str = 'relu', lr: float = 0.001, weight_decay: float = 0.001, n_iter: int = 1000, batch_size: int = 512, n_iter_print: int = 10, patience: int = 10, n_iter_min: int = 100, dropout: float = 0.1, clipping_value: int = 1, batch_norm: bool = True, early_stopping: bool = True, random_state: int = 0, hyperparam_search_iterations: Optional[int] = None, **kwargs: Any)

Bases: autoprognosis.plugins.prediction.regression.base.RegressionPlugin

Regression plugin based on Neural networks.

Parameters

  • n_layers_hidden (int) – Number of hypothesis layers (n_layers_hidden x n_units_hidden + 1 x Linear layer)

  • n_units_hidden (int) – Number of hidden units in each hypothesis layer

  • nonlin (string, default 'elu') – Nonlinearity to use in NN. Can be ‘elu’, ‘relu’, ‘selu’ or ‘leaky_relu’.

  • lr (float) – learning rate for optimizer. step_size equivalent in the JAX version.

  • weight_decay (float) – l2 (ridge) penalty for the weights.

  • n_iter (int) – Maximum number of iterations.

  • batch_size (int) – Batch size

  • n_iter_print (int) – Number of iterations after which to print updates and check the validation loss.

  • val_split_prop (float) – Proportion of samples used for validation split (can be 0)

  • patience (int) – Number of iterations to wait before early stopping after decrease in validation loss

  • n_iter_min (int) – Minimum number of iterations to go through before starting early stopping

  • clipping_value (int, default 1) – Gradients clipping value

  • random_state (int) – Random seed

  • Example – 

    >>> from autoprognosis.plugins.prediction import Predictions
>>> plugin = Predictions(category="regression").get("neural_nets_regression", n_iter = 100)
>>> from sklearn.datasets import load_iris
>>> X, y = load_iris(return_X_y=True)
>>> plugin.fit_predict(X, y) # returns the probabilities for each class

change_output(output: str) → None
explain(X: pandas.core.frame.DataFrame, *args: Any, **kwargs: Any) → pandas.core.frame.DataFrame
fit(X: pandas.core.frame.DataFrame, *args: Any, **kwargs: Any) → autoprognosis.plugins.prediction.regression.base.RegressionPlugin

Train the plugin

Parameters

X – pd.DataFrame

fit_predict(X: pandas.core.frame.DataFrame, *args: Any, **kwargs: Any) → pandas.core.frame.DataFrame

Fit the model and predict the training data. Used by predictors.

fit_transform(X: pandas.core.frame.DataFrame, *args: Any, **kwargs: Any) → pandas.core.frame.DataFrame

Fit the model and transform the training data. Used by imputers and preprocessors.

classmethod fqdn() → str

The fully-qualified name of the plugin: type->subtype->name

get_args() → dict
static hyperparameter_space(*args: Any, **kwargs: Any) → List[autoprognosis.plugins.core.params.Params]

The hyperparameter search domain, used for tuning.

classmethod hyperparameter_space_fqdn(*args: Any, **kwargs: Any) → List[autoprognosis.plugins.core.params.Params]

The hyperparameter domain using they fully-qualified name.

is_fitted() → bool

Check if the model was trained

classmethod load(buff: bytes) → autoprognosis.plugins.prediction.regression.plugin_neural_nets_regression.NeuralNetsRegressionPlugin

Load the plugin from bytes

static name() → str

The name of the plugin, e.g.: xgboost

predict(X: pandas.core.frame.DataFrame, *args: Any, **kwargs: Any) → pandas.core.frame.DataFrame

Run predictions for the input. Used by predictors.

Parameters

X – pd.DataFrame

predict_proba(X: pandas.core.frame.DataFrame, *args: Any, **kwargs: Any) → pandas.core.frame.DataFrame
classmethod sample_hyperparameters(trial: optuna.trial.Trial, *args: Any, **kwargs: Any) → Dict[str, Any]

Sample hyperparameters for Optuna.

classmethod sample_hyperparameters_fqdn(trial: optuna.trial.Trial, *args: Any, **kwargs: Any) → Dict[str, Any]

Sample hyperparameters using they fully-qualified name.

classmethod sample_hyperparameters_np(random_state: int = 0, *args: Any, **kwargs: Any) → Dict[str, Any]

Sample hyperparameters as a dict.

save() → bytes

Save the plugin to bytes

score(X: pandas.core.frame.DataFrame, y: pandas.core.frame.DataFrame, metric: str = 'aucroc') → float
static subtype() → str

The type of the plugin, e.g.: classifier

transform(X: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame

Transform the input. Used by imputers and preprocessors.

Parameters

X – pd.DataFrame

static type() → str

The type of the plugin, e.g.: prediction

plugin

alias of autoprognosis.plugins.prediction.regression.plugin_neural_nets_regression.NeuralNetsRegressionPlugin