src.model.decorated_model

Classes

class src.model.decorated_model.DecoratedModel(**kwargs)

Abstract decorator for machine learning models that provides the common logic for different types of model decorators.

Variables:

decorated_model_spec (dict) – The specification of the decorated model.
decorated_model (Model) – The decorated model object.
undecorated_predictions (bool) – Whether to use the decorated model without decoration when computing the predictions (true) or not (false).

static extract_model_args(spec)

Extract the arguments to initialize/instantiate a DecoratedModel from a key-word specification.

Parameters:: spec – The key-word specification containing the arguments.
Returns:: The arguments to initialize/instantiate a DecoratedModel.

predict(pcloud, X=None)

Decorate the main predictive logic to work on the representation generated by the decorator.

prepare_model(): Prepare the decorated model. See Model and Model.prepare_model().

overwrite_pretrained_model(spec): Overwrite the decorated pretrained model. See Model and Model.overwrite_pretrained_model().

get_input_from_pcloud(pcloud): Get input from the decorated pretrained model. See Model and Model.get_input_from_pcloud().

is_deep_learning_model(): Check whether the decorated model is a deep learning model. See Model and Model.is_deep_learning_model().

training(X, y, info=True): Use the training logic of the decorated model. See Model and Model.training().

autoval(y, yhat, info=True): Auto validation during training through decorated model. See Model and Model.autoval().

train_base(pcloud): Straightforward training through decorated model. See Model and Model.train_base().

train_autoval(pcloud): Use autovalidation training strategy from decorated model. See Model and Model.train_autoval().

train_stratified_kfold(pcloud): Use stratified k-fold training strategy from decorated model. See Model and Model.train_stratified_kfold().

on_training_finished(X, y): Use on training finished callback from decorated model. See Model and Model.on_training_finished().

abstractmethod decorate_pcloud(pcloud)

Obtain the representation of the input point cloud generated by the decorator.

Parameters:: pcloud (PointCloud) – The input point cloud whose decorated representation must be computed.
Returns:: The decorated representation of the input point cloud.
Return type:: PointCloud

abstractmethod propagate(rf_yhat)

Propagate the values (typically predictions) from the receptive field back to the original point cloud.

Parameters:: rf_yhat (np.ndarray) – The values (typically predictions) in the receptive field representation generated by the decorator.
Returns:: The values (typically predictions) propagated back to the original point cloud.
Return type:: np.ndarray

get_fnames_recursively()

Find through any potential decoration graph until the deepest model is found, then consider its feature names.

Returns:: The feature names of the deepest model in the decoration hierarchy.
Return type:: list of str

property fnames: Getter for feature names to get them from the decorated model. :return: The feature names from the decorated model. :rtype: None or list of str