on.aic: AIC from model built with KnowGRRF
In guanxin1121/Know_GRRF: Knowledge-based Guided Regularized Random Forest

Description Usage Arguments Value Author(s) References Examples

User can directly get model performance (AIC: Akaike information criterion) by providing weights and regularization term. Feature selection will be done by RRF and RF model will be built using feature returned by RRF.

1	on.aic(par, wt, num = 1, iter = 1)

`par`	A scaler or a vector of parameters to adjust proportion of weights. The length of parameters is equal to the number of domain.
`wt`	A vector or a matrix of weights corresponding to each of predictors from one or multiple domains.
`num`	The number of domains the weights come from
`iter`	The number of RF model built to evaluate AIC (Akaike information criterion)

mean of AIC from a number of RF model using feature selected by RRF

Li Liu, Xin Guan

Guan, X., & Liu, L. (2018). Know-GRRF: Domain-Knowledge Informed Biomarker Discovery with Random Forests.

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (par, wt, num = 1, iter = 1) 
{
    if (num == 1) {
        return(rrf.opt.1(par, wt, iter)[1])
    }
    else {
        return(rrf.opt.m(par, wt, iter)[1])
    }
  }