return (invisible(NULL))
}
V <- length(private$pmodels)
- if (length(private$pmodels[[1]]$model(X[1,])) >= 2)
+ oneLineX <- t(as.matrix(X[1,]))
+ if (length(private$pmodels[[1]]$model(oneLineX)) >= 2)
# Soft classification:
return (Reduce("+", lapply(private$pmodels, function(m) m$model(X))) / V)
n <- nrow(X)
all_predictions[,v] <- private$pmodels[[v]]$model(X)
if (private$task == "regression")
# Easy case: just average each row
- rowSums(all_predictions)
+ return (rowMeans(all_predictions))
# "Hard" classification:
apply(all_predictions, 1, function(row) {
t <- table(row)