1 Setup

1.1 Packages and options

library(NNbenchmark)
library(kableExtra)
options(scipen = 999)

1.2 Datasets to test

NNdataSummary(NNdatasets)
##      Dataset n_rows n_inputs n_neurons n_parameters
## 1     mDette    500        3         5           26
## 2  mFriedman    500        5         5           36
## 3  mIshigami    500        3        10           51
## 4    mRef153    153        5         3           22
## 5     uDmod1     51        1         6           19
## 6     uDmod2     51        1         5           16
## 7  uDreyfus1     51        1         3           10
## 8  uDreyfus2     51        1         3           10
## 9    uGauss1    250        1         5           16
## 10   uGauss2    250        1         4           13
## 11   uGauss3    250        1         4           13
## 12 uNeuroOne     51        1         2            7

1.3 ELMR Train Function - arguments formula, data

if(dir.exists("D:/GSoC2020/Results/2020run03/"))
{  
  odir <- "D:/GSoC2020/Results/2020run03/"
}else if(dir.exists("~/Documents/recherche-enseignement/code/R/NNbenchmark-project/NNtempresult/"))
{  
  odir <- "~/Documents/recherche-enseignement/code/R/NNbenchmark-project/NNtempresult/"
}else
  odir <- "~"

nrep <- 10
maxit2ndorder  <-    200
maxit1storderA <-   1000
maxit1storderB <-  10000
maxit1storderC <- 100000

ELMR.method <- "extremeML"
hyperParams.ELMR <- function(optim_method, ...) {

    hidden_activation <- "sig"
    size_first_block <- 50
    size_each_chunk <- 50
    
    out <- list(hidden_activation = hidden_activation,
                size_first_block=size_first_block, size_each_chunk=size_each_chunk)
    return (out)
}
NNtrain.ELMR <- function(x, y, dataxy, formula, hidden_neur, optim_method, hyperParams, ...) {
    
    hyper_params <- do.call(hyperParams, list(optim_method, ...))
    
    hidden_activation <- hyper_params$hidden_activation
    size_each_chunk <- hyper_params$size_each_chunk
    size_first_block <- hyper_params$size_first_block
    
    #OSelm_train.formula() call OSelm_training()
    NNreg <- ELMR::OSelm_train.formula(formula = formula,
                                       data = dataxy,
                                       Elm_type = "regression",
                                       nHiddenNeurons = hidden_neur,
                                       ActivationFunction = hidden_activation,
                                       N0 = size_first_block, Block = size_each_chunk)

    return (NNreg)
}
NNpredict.ELMR <- function(object, x, xy)
    ELMR::predict_elm(model = object, test = xy)$predicted
NNclose.ELMR <- function()
  if("package:ELMR" %in% search())
    detach("package:ELMR", unload=TRUE)
ELMR.prepareZZ <- list(xdmv = "m", ydmv = "m", zdm = "d", scale = TRUE)
if(FALSE)
res <- train_and_predict_1data(1, ELMR.method, "NNtrain.ELMR", "hyperParams.ELMR", "NNpredict.ELMR", 
                               NNsummary, "NNclose.ELMR", NA, ELMR.prepareZZ, nrep=2, echo=TRUE, doplot=FALSE,
                               pkgname="ELMR", pkgfun="OSelm_train", rdafile=TRUE, odir=odir)

2 Launch package’s trainPredict

res <- trainPredict_1pkg(1:12, pkgname = "ELMR", pkgfun = "OSelm_train.formula", ELMR.method,
  prepareZZ.arg = ELMR.prepareZZ, nrep = nrep, doplot = TRUE,
  csvfile = TRUE, rdafile = TRUE, odir = odir, echo = FALSE)

3 Results

#print(res)
kable(t(apply(res, c(1,4), min)))%>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed"))
RMSE MSE MAE WAE time
mDette 6.8979 47.5806 5.6315 27.3255 0.01
mFriedman 0.1481 0.0219 0.1160 0.4587 0.00
mIshigami 3.0365 9.2201 2.5408 9.8415 0.00
mRef153 13.3990 179.5343 10.8774 34.5165 0.00
uDmod1 0.3024 0.0914 0.2476 0.8167 0.00
uDmod2 0.2547 0.0648 0.2272 0.4618 0.00
uDreyfus1 0.4198 0.1763 0.2751 1.0798 0.00
uDreyfus2 0.4255 0.1811 0.2921 1.1807 0.00
uGauss1 264.7452 70090.0432 220.2319 778.6982 0.00
uGauss2 24.8924 619.6336 21.4221 52.3001 0.00
uGauss3 26.5430 704.5322 22.7605 54.2973 0.00
uNeuroOne 0.9856 0.9714 0.8251 2.2928 0.00 
kable(t(apply(res, c(1,4), median)))%>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed"))
RMSE MSE MAE WAE time
mDette 7.36045 54.17690 5.86395 31.06885 0.015
mFriedman 0.16980 0.02880 0.13480 0.52295 0.020
mIshigami 3.26795 10.67975 2.64755 11.60160 0.010
mRef153 17.87730 319.60330 14.11365 49.46080 0.005
uDmod1 0.31340 0.09825 0.26215 0.85120 0.000
uDmod2 0.27525 0.07575 0.23940 0.54245 0.000
uDreyfus1 0.44615 0.19900 0.29940 1.15540 0.000
uDreyfus2 0.44995 0.20250 0.30180 1.29725 0.000
uGauss1 1494.00805 2391350.56325 1300.09800 3880.74920 0.010
uGauss2 72.79175 5351.86480 61.48805 194.53205 0.000
uGauss3 42.16685 1801.73205 34.10520 114.33340 0.000
uNeuroOne 1.03080 1.06260 0.84910 2.45055 0.000