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 nlsr trainPredict arguments - inputs full fmla, 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

#library(nlsr)
nlsr.method <- "none"
hyperParams.nlsr <- function(...) {
    return (list(iter = maxit2ndorder, sdnormstart = 0.1))
}
NNtrain.nlsr <- function(x, y, dataxy, formula, neur, method, hyperParams, NNfullformula, NNparam, ...) {
    
    hyper_params <- do.call(hyperParams, list(...))
    start <- round(rnorm(NNparam, sd = hyper_params$sdnormstart), 4)
    names(start)  <- paste0("b", 1:NNparam)
    
    NNreg <- nlsr::nlxb(NNfullformula, data = dataxy, start = start, control = list(femax = hyper_params$iter))
    return(NNreg)
}
NNpredict.nlsr <- function(object, x, ...)
  as.numeric(predict(object, x))
NNclose.nlsr <- function()
  if("package:nlsr" %in% search())
    detach("package:nlsr", unload=TRUE)
nlsr.prepareZZ <- list(xdmv = "d", ydmv = "v", zdm = "d", scale = TRUE)
if(FALSE)
res <- trainPredict_1data(1, nlsr.method, "NNtrain.nlsr", "hyperParams.nlsr", "NNpredict.nlsr", 
                               NNsummary, "NNclose.nlsr", NA, nlsr.prepareZZ, nrep=5,
                               echo=TRUE, doplot=FALSE, echoreport=0,
                               pkgname="nlsr", pkgfun="nlxb", csvfile=TRUE, rdafile=TRUE, odir=odir)

2 Launch package’s trainPredict

res <- trainPredict_1pkg(1:12, pkgname = "nlsr", pkgfun = "nlxb", nlsr.method,
  prepareZZ.arg = nlsr.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 0.1331 0.0177 0.1069 0.6221 0.39
mFriedman 0.0043 0.0000 0.0035 0.0127 0.62
mIshigami 0.5859 0.3433 0.4563 2.2560 1.17
mRef153 3.2246 10.3983 2.1894 11.5242 0.15
uDmod1 0.0405 0.0016 0.0311 0.1045 0.09
uDmod2 0.0427 0.0018 0.0333 0.1058 0.05
uDreyfus1 0.0000 0.0000 0.0000 0.0001 0.00
uDreyfus2 0.0906 0.0082 0.0723 0.2197 0.02
uGauss1 2.2323 4.9831 1.7377 6.9354 0.07
uGauss2 2.3330 5.4430 1.8305 7.3282 0.04
uGauss3 2.2991 5.2860 1.8377 7.0771 0.03
uNeuroOne 0.2830 0.0801 0.2313 0.5675 0.00 
kable(t(apply(res, c(1,4), median)))%>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed"))
RMSE MSE MAE WAE time
mDette 1.05550 1.17675 0.87970 3.49245 0.410
mFriedman 0.00550 0.00000 0.00435 0.01860 0.645
mIshigami 1.95595 3.82580 1.49170 5.36155 1.220
mRef153 3.62380 13.13395 2.60045 14.91630 0.160
uDmod1 0.04555 0.00205 0.03650 0.11935 0.095
uDmod2 0.06255 0.00395 0.04985 0.14455 0.080
uDreyfus1 0.00000 0.00000 0.00000 0.00010 0.020
uDreyfus2 0.09060 0.00820 0.07230 0.21970 0.060
uGauss1 2.77100 7.88405 2.07335 10.27100 0.150
uGauss2 3.74180 14.05915 2.79805 13.75795 0.110
uGauss3 2.81850 7.94390 2.20780 7.50770 0.080
uNeuroOne 0.28300 0.08010 0.23130 0.56750 0.020