BaseLearner.FitObj-class: Classes '"BaseLearner.FitObj"' and '"Regression.FitObj"'

In EnsembleBase: Extensible Package for Parallel, Batch Training of Base Learners for Ensemble Modeling

Description

Base class templates for containing base learner training output.

Objects from the Class

"BaseLearner.FitObj" is a virtual class: No objects may be created from it. "Regression.FitObj" is a base class for objects representing trained models for individual base learners.

Slots

config:

Object of class "BaseLearner.Config"; often one of the derived configuration classes belonging to a particular base learner.

For Regression.FitObj, we have the following additional fields:

est:

Object of class "RegressionEstObj", typically containing the low-level list coming out of the training algorithm. If filemethod=TRUE during the fit, this object will be of class "character", containing the filepath to where the estimation object is stored.

pred:

Object of class "OptionalNumeric", fitted values of the model for the training data. It is allowed to be "NULL" in order to reduce memory footrpint during cross-validated ensemble methods.

Methods

No methods defined with these classes in their signature.

Author(s)

Alireza S. Mahani, Mansour T.A. Sharabiani

See Also

"KNN.Regression.FitObj", "RF.Regression.FitObj", "SVM.Regression.FitObj", "GBM.Regression.FitObj", "NNET.Regression.FitObj"

EnsembleBase documentation built on May 2, 2019, 2:10 p.m.