ML.H2O: ML.H2O

In frbl/OnlineSuperLearner: Online SuperLearner package

Description

Base class for any h2o machine learning model. Extend this class if you want to create a new machine learning model.

Usage

ML.H2O

Format

An object of class R6ClassGenerator of length 24.

Methods

initialize()

Creates a new ML.H2o base model. Note that this also initializes a new H2O interactor for storing and retrieving data.

get_checkpoint(m.fit)

In order to perform an update on an existing H2O model, H2O uses checkpoints. In order to use this system together with our other implementations, we have this function to retrieve a checkpoint if one is available. The function returns NULL if no checkpoint is available, and it returns the model ID if there is a checkpoint.

@param m.fit h2o model (not an h2o base model class, but a plain h2o model) a fitted h2o model from which one wants to retrieve a checkpoint.

frbl/OnlineSuperLearner documentation built on Feb. 9, 2020, 9:28 p.m.