similar to: patch to mva:prcomp to use La.svd instead of svd (PR#2227)

My previous post about prcomp and princomp was done in some haste as I had long ago indicated to Kurt that I would try to have this ready for the June release, and it appeared that I would miss yet another release. I also need to get it out before it becomes hopelessly buried by other work. Brian Ripley kindly pointed out some errors, and also pointed out that I was suggesting replacing some

Dear R-list users, I'm new to principal components and factor analysis. I thought this method can be very useful for me to find relationships between several variables (which I know there is, only don't know which variables exactly and what kind of relation), so as a structure detection method. Now, I'm experimenting with the function prcomp from the mva package. In my source code

Hello, I have a short question about the prcomp function. First I cite the associated help page (help(prcomp)): "Value: ... SDEV the standard deviations of the principal components (i.e., the square roots of the eigenvalues of the covariance/correlation matrix, though the calculation is actually done with the singular values of the data matrix). ROTATION the matrix of variable loadings

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

According to R help: princomp() uses eigenvalues of covariance data. prcomp() uses the SVD method. yet when I run the (eg., USArrests) data example and compare with my own "hand-written" versions of PCA I get what looks like the opposite. Example: comparing the variances I see: Using prcomp(USArrests) ------------------------------------- Standard deviations: [1] 83.732400 14.212402

Martin, I fully agree. This becomes an issue when you have big matrices. (Note that there are awesome methods for actually only computing a small number of PCs (unlike your code which uses svn which gets all of them); these are available in various CRAN packages). Best, Kasper On Thu, Mar 24, 2016 at 1:09 PM, Martin Maechler <maechler at stat.math.ethz.ch > wrote: > Following from

Hi, I am trying to do a PCA on my data but I keep getting the error message svd(x, nu=0) infinite or missing values >From the messages posted on the subject, I understand that the NAs in my data might be the problem, but I thought na.omit would take care of that. Less than 5% of my cells are missing data. However, the NAs are not regularly distributed across my matrix: certain cases and

In the manual page for prcomp(), it says that sdev is "the standard deviations of the principal components (i.e., the square roots of the eigenvalues of the covariance/correlation matrix, though the calculation is actually done with the singular values of the data matrix)." ?However, this is not what I'm finding. ?The values appear to be the standard deviations of a reprojection of

Hi All: I am running prcomp on a very large array, roughly [500000, 3650]. The array itself is 16GB. I am running on a Unix machine and am running ?top? at the same time and am quite surprised to see that the application memory usage is 76GB. I have the ?tol? set very high (.8) so that it should only pull out a few components. I am surprised at this memory usage because prcomp uses the SVD

Hi All: I am running prcomp on a very large array, roughly [500000, 3650]. The array itself is 16GB. I am running on a Unix machine and am running ?top? at the same time and am quite surprised to see that the application memory usage is 76GB. I have the ?tol? set very high (.8) so that it should only pull out a few components. I am surprised at this memory usage because prcomp uses the SVD

The following seems to be an bug in prcomp(): > test <- ts( matrix( c(NA, 2:5, NA, 7:10), 5, 2)) > test Time Series: Start = 1 End = 5 Frequency = 1 Series 1 Series 2 1 NA NA 2 2 7 3 3 8 4 4 9 5 5 10 > prcomp(test, scale.=TRUE, na.action=na.omit) Erro en svd(x, nu = 0) : infinite or missing values in 'x'

As I see it, the display showing the first p << n PCs adding up to 100% of the variance is plainly wrong. I suspect it comes about via a mental short-circuit: If we try to control p using a tolerance, then that amounts to saying that the remaining PCs are effectively zero-variance, but that is (usually) not the intention at all. The common case is that the remainder terms have a roughly

Dear expeRts, I have run some simulations under R 2.15.1 on a Mac, and I have rerun a sample of them under R 3.0.1 on Windows (and also for comparison under R2.14.1 on Windows). For most cases, I get exactly the same results in all three runs. However, for those cases that depend on principal components computed with prcomp, where the particular choice of the orthogonalization is arbitrary

Dear expeRts, I have run some simulations under R 2.15.1 on a Mac, and I have rerun a sample of them under R 3.0.1 on Windows (and also for comparison under R2.14.1 on Windows). For most cases, I get exactly the same results in all three runs. However, for those cases that depend on principal components computed with prcomp, where the particular choice of the orthogonalization is arbitrary

The help for prcomp on R 1.0.0 states that the component sdev of the return value is the eigenvalues of the cov matrix. Am I completely mistaken, or should this be the _square root_ of the eigenvalues? Also, the documentation is not very clear about how tol is used to omit components. (The _code_ is clear, though. :-) -- B/H

> On 25 Mar 2016, at 10:08 , Jari Oksanen <jari.oksanen at oulu.fi> wrote: > >> >> On 25 Mar 2016, at 10:41 am, peter dalgaard <pdalgd at gmail.com> wrote: >> >> As I see it, the display showing the first p << n PCs adding up to 100% of the variance is plainly wrong. >> >> I suspect it comes about via a mental short-circuit: If we

Following from the R-help thread of March 22 on "Memory usage in prcomp", I've started looking into adding an optional 'rank.' argument to prcomp allowing to more efficiently get only a few PCs instead of the full p PCs, say when p = 1000 and you know you only want 5 PCs. (https://stat.ethz.ch/pipermail/r-help/2016-March/437228.html As it was mentioned, we already

Hello, not understanding the output of prcomp, I reduce the number of components and the output continues to show cumulative 100% of the variance explained, which can't be the case dropping from 8 components to 3. How do i get the output in terms of the cumulative % of the total variance, so when i go from total solution of 8 (8 variables in the data set), to a reduced number of

Hi, This may be a `transitional' bug but I am reporting a make check fail with R-devel r70391 in reg-tests-1a.Rout. The tail of reg-tests-1a.Rout.fail is > ## prcomp(tol=1e-6) > x <- matrix(runif(30),ncol=10) > s <- prcomp(x, tol=1e-6) > stopifnot(length(s$sdev) == ncol(s$rotation)) Error: length(s$sdev) == ncol(s$rotation) is not TRUE Execution halted Looking at

Dear R community, I have a data matrix (531X314), and would like to apply the prcomp. However, I got this error Lapack message. I am using R3.2.2. I googled a bit and found that it might be related to converge issue. ?Just wonder if there is a way to get around it? Thank you very much! Ace On Thursday, December 29, 2016 11:44 AM, Ista Zahn <istazahn at gmail.com> wrote: Use