Trainer Class An S4 class representing a learning method.

The object consists of 4 slots

Constructor for the S4 Trainer object.

Usage

Trainer(id, trainer, parameters, logger = Logger())

Arguments

id

the learning method name associated to this Trainer. If learning method is one of the supported by renoir, the constructor will automatically select a trainer. See supported_learning_methods() for the supported methods.

trainer

(optional) function to train a model. Used if id is not one of the supported by renoir. If trainer is provided it must conform to the renoir common interface, and must have the following formal arguments:

x: the input matrix, where rows are observations and columns are variables.
y: the response variable. Its number of rows must match the number of rows of x.
weights: priors of the observations
offset: used only for GLM methods, it is an a priori known component to be included in the linear predictor during fitting
resp.type: the response type
observations: indices of observations to keep
features: indices of predictors to keep
...: additional arguments

parameters

list containing the parameters for the chosen learning method

logger

a Logger

Value

An object of class Trainer.

Slots

id

the learning method name

trainer

trainer function. It must have the following formal arguments:

x: the input matrix, where rows are observations and columns are variables.
y: the response variable. Its number of rows must match the number of rows of x.
weights: priors of the observations
offset: used only for GLM methods, it is an a priori known component to be included in the linear predictor during fitting
resp.type: the response type
observations: indices of observations to keep
features: indices of predictors to keep
...: additional arguments

parameters

list containing the parameters for the chosen learning method

logger

a Logger

Author

Alessandro Barberis