Neural network structure sensitivity plot

Plot a neural interpretation diagram colored by sensitivities of the model

Usage

PlotSensMLP(
  MLP.fit,
  metric = "mean",
  sens_neg_col = "red",
  sens_pos_col = "blue",
  ...
)

Arguments

MLP.fit

fitted neural network model

metric

metric to plot in the NID. It can be "mean" (default), "median or "sqmean". It can be any metric to combine the raw sensitivities

sens_neg_col

character string indicating color of negative sensitivity measure, default 'red'. The same is passed to argument neg_col of plotnet

sens_pos_col

character string indicating color of positive sensitivity measure, default 'blue'. The same is passed to argument pos_col of plotnet

...

additional arguments passed to plotnet and/or SensAnalysisMLP

Value

A graphics object

Examples

## Load data -------------------------------------------------------------------
data("DAILY_DEMAND_TR")
fdata <- DAILY_DEMAND_TR
## Parameters of the NNET ------------------------------------------------------
hidden_neurons <- 5
iters <- 100
decay <- 0.1

################################################################################
#########################  REGRESSION NNET #####################################
################################################################################
## Regression dataframe --------------------------------------------------------
# Scale the data
fdata.Reg.tr <- fdata[,2:ncol(fdata)]
fdata.Reg.tr[,3] <- fdata.Reg.tr[,3]/10
fdata.Reg.tr[,1] <- fdata.Reg.tr[,1]/1000

# Normalize the data for some models
preProc <- caret::preProcess(fdata.Reg.tr, method = c("center","scale"))
nntrData <- predict(preProc, fdata.Reg.tr)

#' ## TRAIN nnet NNET --------------------------------------------------------
# Create a formula to train NNET
form <- paste(names(fdata.Reg.tr)[2:ncol(fdata.Reg.tr)], collapse = " + ")
form <- formula(paste(names(fdata.Reg.tr)[1], form, sep = " ~ "))

set.seed(150)
nnetmod <- nnet::nnet(form,
                      data = nntrData,
                      linear.output = TRUE,
                      size = hidden_neurons,
                      decay = decay,
                      maxit = iters)
#> # weights:  21
#> initial  value 2487.870002 
#> iter  10 value 1587.516208
#> iter  20 value 1349.706741
#> iter  30 value 1333.940734
#> iter  40 value 1329.097060
#> iter  50 value 1326.518168
#> iter  60 value 1323.148574
#> iter  70 value 1322.378769
#> iter  80 value 1322.018091
#> final  value 1321.996301 
#> converged
# Try SensAnalysisMLP
NeuralSens::PlotSensMLP(nnetmod, trData = nntrData)