SensMatPlot | R Documentation |
Function to plot the sensitivities created by HessianMLP
.
SensMatPlot(
hess,
sens = NULL,
output = 1,
metric = c("mean", "std", "meanSensSQ"),
senstype = c("matrix", "interactions"),
...
)
hess |
|
sens |
|
output |
|
metric |
|
senstype |
|
... |
further argument passed similar to |
Most of the code of this function is based on
ggcorrplot()
function from package ggcorrplot
. However, due to the
inhability of changing the limits of the color scale, it keeps giving a warning
if that function is used and the color scale overwritten.
a list of ggplot
s, one for each output neuron.
## 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)
# Try HessianMLP
H <- NeuralSens::HessianMLP(nnetmod, trData = nntrData, plot = FALSE)
NeuralSens::SensMatPlot(H)
S <- NeuralSens::SensAnalysisMLP(nnetmod, trData = nntrData, plot = FALSE)
NeuralSens::SensMatPlot(H, S, senstype = "interactions")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.