search for: scaling

Hi, Given the following, a <- rnorm(5) b <- rnorm(5) c <- rnorm(5) a.1g.scale <- scale(c(a,b,c))[1:5] b.1g.scale <- scale(c(a,b,c))[6:10] c.1g.scale <- scale(c(a,b,c))[11:15] a.2g.scale <- scale(c(a,b))[1:5] b.2g.scale <- scale(c(a,b))[6:10] c.2g.scale <- scale(c) a.3g.scale <- scale(a) b.3g.scale <- scale(b) c.3g.scale <- scale(c) I am puzzled why the

...original units, see lines 2832-2838) 3. fitted response is now scaled BACK to the original units of "y" at lines 839,840. So, when assigning "error(ret) <-" at line 844, fitted(ret) is in the original units but y is in standardized units: 828 829 if(any(scaled)) 830 scaling(ret) <- list(scaled = scaled, x.scale = x.scale, y.scale = y.scale) 831 832 if (fit){ ... 837 if(type(ret)=="eps-svr"||type(ret)=="nu-svr"||type(ret)=="eps-bsvr"){ 838 if (!is.null(scaling(ret)$y.scale)){ 839 scal <- scaling(ret)$y.scale$&quo...

Hello folks, it may be regarded as a user error to scale() your data prior to prcomp() instead of using its 'scale.' argument. However, it is a user thing that may happen and sounds a legitimate thing to do, but in that case predict() with 'newdata' can give wrong results: x <- scale(USArrests) sol <- prcomp(x) all.equal(predict(sol), predict(sol, newdata=x)) ## [1]

Hi all, I have been previously been using scatterplot3d package to create some graphs but unfortunately it does not allow me to rotate the plot on all three axis. The cloud() function in the lattice package does allow me to do so. When I was using scatterplot3d I was using a script (Shown Below) to calculate the mean, quartiles and range limits for all three axis and I was representing that on the

Why does: (shape/scale) * (1:365/scale)^(shape - 1) return a vector of numbers but calling a function hasard(1:365,shape,scale) defined like: hazard <- function(x,shape,scale) { return (shape/scale) * (x/scale)^(shape - 1) } Only return a single value? It is like x becomes a single value passed as an argument. Thank you. Kevin

Hi Everyone, I would like to scale a data frame and then using the same scaling parameters scale on another data frame. This will be helpful in scaling the test dataset based on train dataset's scaling parameters. I couldn't find any utility functions that do this. Any suggestions on how to approach this problem? x = data.frame(a=1:10,b=11:20) y = data.frame(a=2:11,b=...

...d funded by CANCER RESEARCH UK. http://bioinformatics.picr.man.ac.uk/simpleaffy mailto: microarray at picr.man.ac.uk Background correcting Retrieving data from AffyBatch...done. Computing expression calls... .........................done. scaling to a TGT of 100 ... Scale factor for: 0203_YH10_H_MCF7_r1.CEL 0.291660289301555 Scale factor for: 0203_YH11_H_MCF10A_r1.CEL 0.42025300545212 Scale factor for: 0203_YH12_H_a100MCF7_r1.CEL 0.287589038746987 Scale factor for: 0203_YH13_H_a100MCF10A_r1.CEL 0.451200408584071 Scale factor for: 0203_YH14_...

Full_Name: Ryszard Czerminski Version: 1.8.1 OS: GNU/Linux Submission from: (NULL) (205.181.102.120) prcomp(..., scale = TRUE) does not work correctly: $ uname -a Linux 2.4.20-28.9bigmem #1 SMP Thu Dec 18 13:27:33 EST 2003 i686 i686 i386 GNU/Linux $ gcc --version gcc (GCC) 3.2.2 20030222 (Red Hat Linux 3.2.2-5) > a <- matrix(rnorm(6), nrow = 3) > sum((scale(a %*% svd(cov(a))$u, scale

Full_Name: Maria Rizzo Version: 2.10.1 (2009-12-14) OS: Windows XP SP3 Submission from: (NULL) (72.241.75.222) platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor

Hi all, I'm running a monte carlo test of a neural network tool I've developed, and it looks like it's going to take a very long time if I run it in R so I'm interested in translating my code (included below) into something faster like Fortran (which I'll have to learn from scratch). However, as you'll see my code loads the nnet library and uses it quite a bit, and I

Hi, The documentation for scale() states:"If center is TRUE then centering is done by subtracting the column means (omitting NAs) of x from their corresponding columns". But it seems that R is subtracting something else instead of the column mean: > x=c(2,4,3,4,5) > mean(x) [1] 3.6 > x-mean(x) [1] -1.6 0.4 -0.6 0.4 1.4 > scale(x) [,1] [1,] -1.4032928 [2,]

Hi, I'm trying to follow the suggestions given by Deepayan Sarkar in this message: http://tolstoy.newcastle.edu.au/R/help/05/11/16135.html to plot 3-D points on a wireframe plot. The problem is that I keep getting a partly formed plot- with the colored lattice visible but no axis labels or additional points- with the error message "error using packet 1, 'x' and 'units'

I am attempting to use the lars package with a sparse input feature matrix, but the following fails: library(Matrix) library(lars) data(diabetes) attach(diabetes) x = as(as.matrix(as.data.frame(x)), 'dgCMatrix') lars(x, y, intercept = FALSE) Error in scale.default(x, FALSE, normx) : > > length of 'scale' must equal the number of columns of 'x' > > More

...SVM module from the library ''e1071'' for training. Problem formulation: a classification has been performed using SVM module (linear kernel). Later, a new data set (test set) comparable to the training data shall be scaled in the same way as the training set (using the same scaling parameter set, but without using the SVM again to save time). We found the scaling matrices, but we do not know, how to apply them. How must the scaling parameter matrices (scaled:center and scaled:scale) be applied to the test data set to receive the same scaling as it would have been done b...

Hi, I am using function wireframe from package lattice to draw a 3D surface. I would like to add a few points on the surface. I read in a post from Deepayan Sarkar that "To do this in a wireframe plot you would probably use the panel function panel.3dscatter". Does someone have an example? When calling panel.3dscatter with only x, y and z arguments I get "argument

Hello all, I’m trying to add some data points to a wireframe. X an Y axis are independent variables, Z axis is predicted probability. I’d like to add the original data points on which the predicted probabilities are based to the wireframe. I’ve followed some of the previous post on this but get stuck : ## first part yields the wireframe## setwd("C:/Temp") rnp <-

Moi! A student here has been getting a bit irritated with some side effects of scale() (OS is Windows XP, the behaviour occurs in R 2.0.0, but not 1.7.1). The problem is that she scales a variable in a data frame, then does a regression, and tries to get some predictions for some new data. However, at this point she gets an error (see the example below). This seems to be because the

I've been working on a revised version of prcomp and princomp. Below is my current draft of prcomp, which is marginally different from V&R. I've added center and scale as optional arguments. However, scale causes the following: > zi _ prcomp(iris[,,2]) Warning: ignored non function "scale" because scale is both a variable and a function. Is there any way to avoid this

I have a list of vectors, all forced to be the same length: testlist <- list( shape=c(0, 0, 2), cell.fill=c("red","blue","green"), back.fill=rep("white",3), scale.max=rep(100,3) ) > str(testlist) List of 4 $ shape : num [1:3] 0 0 2 $ cell.fill: chr [1:3] "red" "blue" "green" $ back.fill: chr [1:3]

I have a problem with lattice log scales that I could use some help with. I'm trying to print log y-axis scales without exponents in the labels. A similar thread with Deepayan' recommendation is here: http://tolstoy.newcastle.edu.au/R/e11/help/10/09/9865.html. For example, this code using xyplot produces a logged y-axis but the labels (e.g. "10^1.2") are not very