Last chance! 50% off unlimited learning
Sale ends in
$k$-nearest neighbour classification with an interface compatible to
bagging
and errorest
.
ipredknn(formula, data, subset, na.action, k=5, ...)
An object of class ipredknn
. See predict.ipredknn
.
a formula of the form lhs ~ rhs
where lhs
is the response variable and rhs
a set of
predictors.
optional data frame containing the variables in the model formula.
optional vector specifying a subset of observations to be used.
function which indicates what should happen when
the data contain NA
s.
number of neighbours considered, defaults to 5.
additional parameters.
This is a wrapper to knn
in order to be able to
use k-NN in bagging
and errorest
.
library("mlbench")
learn <- as.data.frame(mlbench.twonorm(300))
mypredict.knn <- function(object, newdata)
predict.ipredknn(object, newdata, type="class")
errorest(classes ~., data=learn, model=ipredknn,
predict=mypredict.knn)
Run the code above in your browser using DataLab