On Sep 2, 2011, at 3:05 PM, Eduardo M. A. M.Mendes wrote: > Hello > > > > Please see the example below > > > >> class(testX) > > [1] "matrix" > >> class(testX[1,]) > > [1] "numeric" > > > > Why not matrix? What am I missing here? Is there a way to keep the same > class? > > > > The reason for the question is that I want to implement a k-step ahead > prediction for my own routines and R wrecks does not seem to like [1,] as > shown below. > > > >> predict(fit10,testX[1,]) > Error in knnregTrain(train = c(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, : > dims of 'test' and 'train differ >> predict(fit10,testX[1:2,]) > [1] 81.00 76.36 > > > > Many thanks > > > > Ed
Ed, See: http://cran.r-project.org/doc/FAQ/R-FAQ.html#Why-do-my-matrices-lose-dimensions_003f and then use: predict(fit10, testX[1, , drop = FALSE]) HTH, Marc Schwartz ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
