FitModels: Fit regression model to performance data

In fcampelo/MetaTuner: MetaTuner: Metaheuristics Tuner

Description

Fits regression models to the performance data gathered by MetaTuner. Returns the model fitted to the data, plus a number of models obtained by perturbing the regression coefficients within certain error bounds.

Usage

FitModels(X, Nmodels, model.order = 3, model.type = c("linear", "quantile",
  "lasso", "ridge"), Yij.norm, ...)

Arguments

X	data frame containing the performance data
Nmodels	number of models to generate (1 original plus Nmodels - 1 perturbations)
model.order	order to use for the regression model. Defaults to 2
model.type	type of model to fit. See metatuner() for details.
Yij.norm	matrix of normalized performance values, returned by EvaluateConfigurations().
...	other parameters to be passed down to specific fitting functions

Value

list containing information about all models fitted

Author(s)

Felipe Campelo ([e-mail]), Athila Trindade ([e-mail])

fcampelo/MetaTuner documentation built on May 29, 2019, 9:14 a.m.