SEMdeep (version 0.1.0)

predict.DNN: SEM-based out-of-sample prediction using layer-wise DNN

Description

Predict method for DNN objects.

Usage

# S3 method for DNN
predict(object, newdata, verbose = FALSE, ...)

Value

A list of 2 objects:

1. "PE", vector of the prediction error equal to the Mean Squared Error (MSE) for each out-of-bag prediction. The first value of PE is the AMSE, where we average over all (sink and mediators) graph nodes.

2. "Yhat", the matrix of continuous predicted values of graph nodes (excluding source nodes) based on out-of-bag samples.

Arguments

object

A model fitting object from SEMdnn() function.

newdata

A matrix containing new data with rows corresponding to subjects, and columns to variables.

verbose

Print predicted out-of-sample MSE values (default = FALSE).

...

Currently ignored.

Author

Mario Grassi

Examples

# \donttest{
if (torch::torch_is_installed()){

# Load Amyotrophic Lateral Sclerosis (ALS)
data<- alsData$exprs; dim(data)
data<- transformData(data)$data
ig<- alsData$graph; gplot(ig)
group<- alsData$group 

#...with train-test (0.5-0.5) samples
set.seed(123)
train<- sample(1:nrow(data), 0.5*nrow(data))

start<- Sys.time()
dnn0 <- SEMdnn(ig, data, train, cowt = FALSE, thr = NULL,
			#loss = "mse", hidden = 5*K, link = "selu",
			loss = "mse", hidden = c(10, 10, 10), link = "selu",
			validation = 0, bias = TRUE, lr = 0.01,
			epochs = 32, device = "cpu", verbose = TRUE)
end<- Sys.time()
print(end-start)
mse0 <- predict(dnn0, data[-train, ], verbose=TRUE)

# SEMrun vs. SEMdnn MSE comparison
sem0 <- SEMrun(ig, data[train, ], SE="none", limit=1000)
mse0 <- predict(sem0, data[-train,], verbose=TRUE)

#...with a binary outcome (1=case, 0=control)

ig1<- mapGraph(ig, type="outcome"); gplot(ig1)
outcome<- ifelse(group == 0, -1, 1); table(outcome)
data1<- cbind(outcome, data); data1[1:5,1:5]

start<- Sys.time()
dnn1 <- SEMdnn(ig1, data1, train, cowt = TRUE, thr = NULL,
			#loss = "mse", hidden = 5*K, link = "selu",
			loss = "mse", hidden = c(10, 10, 10), link = "selu",
			validation = 0, bias = TRUE, lr = 0.01,
			epochs = 32, device = "cpu", verbose = TRUE)
end<- Sys.time()
print(end-start)

mse1 <- predict(dnn1, data1[-train, ])
yobs <- group[-train]
yhat <- mse1$Yhat[ ,"outcome"]
benchmark(yobs, yhat, thr=0, F1=FALSE)
}
# }