if (FALSE) {
## simulate data
set.seed(23432)
## training set
n <- 500
p <- 50
X <- matrix(rnorm(n*p), nrow = n, ncol = p)
colnames(X) <- paste("X", 1:p, sep="")
X <- data.frame(X)
Y <- X[, 1] + sqrt(abs(X[, 2] * X[, 3])) + X[, 2] - X[, 3] + rnorm(n)
## test set
m <- 1000
newX <- matrix(rnorm(m*p), nrow = m, ncol = p)
colnames(newX) <- paste("X", 1:p, sep="")
newX <- data.frame(newX)
newY <- newX[, 1] + sqrt(abs(newX[, 2] * newX[, 3])) + newX[, 2] -
newX[, 3] + rnorm(m)
# generate Library and run Super Learner
SL.library <- c("SL.glm", "SL.randomForest", "SL.gam",
"SL.polymars", "SL.mean")
test <- SampleSplitSuperLearner(Y = Y, X = X, newX = newX, SL.library = SL.library,
verbose = TRUE, method = "method.NNLS")
test
# library with screening
SL.library <- list(c("SL.glmnet", "All"), c("SL.glm", "screen.randomForest",
"All", "screen.SIS"), "SL.randomForest", c("SL.polymars", "All"), "SL.mean")
test <- SuperLearner(Y = Y, X = X, newX = newX, SL.library = SL.library,
verbose = TRUE, method = "method.NNLS")
test
# binary outcome
set.seed(1)
N <- 200
X <- matrix(rnorm(N*10), N, 10)
X <- as.data.frame(X)
Y <- rbinom(N, 1, plogis(.2*X[, 1] + .1*X[, 2] - .2*X[, 3] +
.1*X[, 3]*X[, 4] - .2*abs(X[, 4])))
SL.library <- c("SL.glmnet", "SL.glm", "SL.knn", "SL.gam", "SL.mean")
# least squares loss function
test.NNLS <- SampleSplitSuperLearner(Y = Y, X = X, SL.library = SL.library,
verbose = TRUE, method = "method.NNLS", family = binomial())
test.NNLS
}
Run the code above in your browser using DataLab