[R] reconstruction of data after PCA and interpolation
Dear all, I have a matrix of size N x M. I purchase a PCA analysis through prcomp function. Then I keep the H eigenvectors which explain 90% of the total variance and interpolate each vectors of the matrix H x M, to obtain a new matrix of size H x K (K M). My question is : from this last matrix (H x K), how to (re)construct a matrix of size N x K which have the same units of the inital matrix (N x M). Regards -- Cordialement Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch 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.
Re: [R] Linux configuration (Ubuntu)
Brian Edward a écrit : Hello all, I have been a R user for about a year now, running on a MS Windows machine. I am in the process of making a complete switch to open-source. Linux is a new world to me. Ubuntu was my selection of the various distributions. Please pardon this very basic question (I was unable to locate an answer on R or Ubuntu). I used Synaptic to download the necessary files to run. However, I was unable to locate the program using the Add/Remove feature. So, I created a Launcher for R on the desktop and identified the executable file. The path I entered into the Command Line was: /usr/bin/R I can run R in the Terminal, but not as a separate desktop location. So, the short question is, what is the specific command line or configuration I should be using to run R? Or, am I supposed to be running R in the Terminal? Thanks in advance, Brian [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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. Dear Edward, R under linux (Ubuntu or other distributions) is not exactly as it is under windows. Under linux, you have to use a shell (or a terminal) to launch R and use it. The main difference between windows and linux version of R, is that R under linux, does not provide the graphical facilities to load and install libraries. To do so under linux, you have to download the tar.gz version of the library from CRAN and use as a root user the command R CMD INSTALL thelibrarytoinstall.tar.gz. You have to install, of course, before, the needed compilers gcc and/or fortran, depend the library you are about to install. Hope it 'll help. Regards -- Cordialement Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch 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.
[R] Negative value on ternaryplot
Dear all, I found a wonderful package (vcd) able to plot ternary diagrams, i.e. ternaryplot (thanks D. Meyer). The problem is that one of three variable has negative values. If I use the ternaryplot function but some points are outside the triangle, as value en negative. Is it possible to make the ternary diagram fit exactly the cloud points ? Regards Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] autocorrelation test
Hi all, I would like to test the relevance of a vector field (i.e. if the vectors are organized or not). To do so, I would like to use an autocorrelation test, so that I have two questions: - is the Watson test applicable to that perpuse ? - is the kuiper test applicable to that purpuse ? Regards Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] One sample test
Hi all, I would like to test the uniformity (or no uniformity) of a vector field. To do so, I would like to use a ks.test (Kolmogorov-Smirnov) but don't know what value to give for the second parameter in case of a one sample test, as it is my case here. An other question is, does any body know if there is a R function to perform a Kuiper test ? Regards -- Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Compilationerror at installation of packages
Dear all, I did post a message about problems on installing a package (gstat) which ends with a compilation error: ** libs gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c block.c -o block.o gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c chfactor.c -o chfactor.o gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c copy.c -o copy.o gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c data.c -o data.o /tmp/ccB5viRU.s: Messages de l'assembleur: /tmp/ccB5viRU.s:8032: ERREUR: Opérande de relocalisation inconnue: !lituse_jsrdirect make: *** [data.o] Erreur 1 ERROR: compilation failed for package 'gstat' I tried an other package and have the same result. The R installation is new so tha I have all the basic packages installed I used gcc compiler : Using built-in specs. Target: alpha-linux-gnu Configured with: ../src/configure -v --enable-languages=c,c++,java,f95,objc,treelang --prefix=/usr --enable-shared --with-system-zlib --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --enable-nls --program-suffix=-4.0 --enable-__cxa_atexit --enable-libstdcxx-allocator=mt --enable-clocale=gnu --enable-libstdcxx-debug --enable-java-gc=boehm --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.4.2-gcj-4.0-1.4.2.0/jre --enable-mpfr --disable-werror --enable-checking=release alpha-linux-gnu Thread model: posix gcc version 4.0.2 (Debian 4.0.2-2) Regards -- Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Compilation package error
Dear all, I tried to install gstat package and add the following compilation error : * Installing *source* package 'gstat' ... creating cache ./config.cache checking for gcc... gcc checking whether the C compiler (gcc ) works... yes checking whether the C compiler (gcc ) is a cross-compiler... no checking whether we are using GNU C... yes checking whether gcc accepts -g... yes checking how to run the C preprocessor... gcc -E checking for AIX... no checking for minix/config.h... no checking for POSIXized ISC... no checking for ANSI C header files... yes checking for working const... yes checking whether time.h and sys/time.h may both be included... yes checking for 8-bit clean memcmp... yes checking for vprintf... yes checking for strstr... yes checking for strtod... yes checking for strtol... yes checking for drand48... yes checking for gettimeofday... yes checking whether byte ordering is bigendian... no checking for memory.h... yes checking for ANSI C header files... (cached) yes checking for gcc option to accept ANSI C... checking for function prototypes... yes checking for working const... (cached) yes checking for complex.h... yes checking for malloc.h... yes checking for varargs.h... no checking for size_t... yes checking for working const... (cached) yes checking whether byte ordering is bigendian... (cached) no checking for u_int computing machine epsilon(s) gcc -o macheps ./src/meschach/dmacheps.c gcc -o macheps ./src/meschach/fmacheps.c computing M_MAX_INT gcc -o maxint maxint.c ./src/meschach/maxint.c: In function 'main': ./src/meschach/maxint.c:37: warning: incompatible implicit declaration of built-in function 'printf' checking char \\0 vs. float zeros checking for bcopy... yes checking for bzero... yes checking for function prototypes checking for function prototypes in structures updating cache ./config.cache creating ./config.status creating makefile creating src/config.h creating src/machine.h ** libs gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c block.c -o block.o gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c chfactor.c -o chfactor.o gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c copy.c -o copy.o gcc -I/usr/lib/R/include -mieee-with-inexact -fPIC -g -O2 -c data.c -o data.o /tmp/ccXDZili.s: Messages de l'assembleur: /tmp/ccXDZili.s:8032: ERREUR: Opérande de relocalisation inconnue: !lituse_jsrdirect make: *** [data.o] Erreur 1 ERROR: compilation failed for package 'gstat' ** Removing '/usr/local/lib/R/site-library/gstat' ** Restoring previous '/usr/local/lib/R/site-library/gstat' --- R run on a dec alpha station under Debian Sarge 64 bits (alpha version of course). Compiler version is gcc 4.0.2. Regards Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] geometric mean regression
Hi, is it possible to perform a geometric mean regression with R ? Thanks. Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Phone (Direct) : (00 33)(0)233887342 Fax : (00 33)(0)233887339 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Classification of an image
Dear all, I need to do a automatic classification of a raster file (image) using training samples. I would like to know if there is a library able to do such a work. Thanks Emmanuel Poizot __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] array construction
Hi all, I've got a file of the following format: X Y Z u v w 0 0 0 x x x 0 0 1 x x x 0 0 2 x x x .. .. .. .. .. .. 0 1 0 x x x 0 1 1 x x x 0 1 2 x x x .. .. .. .. .. .. 1 0 0 x x x 1 0 1 x x x 1 0 2 x x x etc x stand for decimal values X coordinate is 3h, Y and Z are h length. I read that file with: data - read.table(filename, fill=T) I extract coordinates with: coord - data[1:length,1:3]with length the number of lines of the file I get the x values with: values-data[1:length,4:6] I would like now to create an 3D array storing the values on the correct order: uvw - array(data[1:length],dim=c(3h,h,h)) with h predifened of course Is that command correct ? -- Cordialement ~~~ Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Tél: (33)(0)233887342 Fax: (33)(0)233887339 ~~~ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] R from outside program
Hi all, I'm writing a program in C++ in witch there should be some graphical outputs. To do so, I would like to use R with the command : R --no-save cmdfile.R , where I put the R graphic commands in the cmdfile.R file. I call R from my C++ code but as R seems to run in batch mode, there are no graphical outputs! How can I do to get the graphics outputs ? -- Sincerely ~~~ Emmanuel Poizot Cnam/Intechmer B.P. 324 50103 Cherbourg Cedex Tél: (33)(0)233887342 Fax: (33)(0)233887339 ~~~ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Alpha
Hello, I just install red-hat 7.2 for alpha station. I downloaded R-1.8.1-1.alpha.rpm, but unable to install it. I need the libblas.so.3 library. I did have a look around and did not find where to get that library for linux alpha version. -- regards Emmanuel POIZOT Cnam/Intechmer Digue de Collignon 50110 Tourlaville Tél : (33)(0)2 33 88 73 42 Fax : (33)(0)2 33 88 73 39 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Postscript PBs
Hi, I use R 1.6.2 under Mandrake9.0. I've got a problem with the postscript files I try to creat. When I look to the file with ghostview it's ok. When I want to print it, I've got a blank page or a black page (fill of black encre) I changed the printer (guessing it was my driver printer), it was the same. Does anyone had the same problem and resolved it ? -- Cordialy Emmanuel POIZOT Cnam/Intechmer Digue de Collignon 50110 Tourlaville Tél : (33)(0)2 33 88 73 42 Fax : (33)(0)2 33 88 73 39 - __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Correlation test
Hi, I need to test multiple correlation coefficient in a same time, what's the best test for that and are should I do under R ? Thanks -- Cordialement Emmanuel POIZOT Cnam/Intechmer Digue de Collignon 50110 Tourlaville Tél : (33)(0)2 33 88 73 42 Fax : (33)(0)2 33 88 73 39 - __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Wavelets correlation test
Hello, I use wavethresh packages to perform wavelet analysis. In particular, I would like to compare 2 signals (vectors) after a wavelet decomposition. I would like to use cor.test function, but this function acts on the entire vector values. I plan to perform a cor.test on each level of the wavelet decomposition, say N. So I will have at the end of a first step N results of cor.test. How can I deal with this N results to have an answer globaly ? -- Cordialy Emmanuel POIZOT Cnam/Intechmer Digue de Collignon 50110 Tourlaville Tél : (33)(0)2 33 88 73 42 Fax : (33)(0)2 33 88 73 39 - __ [EMAIL PROTECTED] mailing list http://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Wavelets analysis
Hello, I would like to compare 2 vectors representing 2 signals. To do so, I use a wavelet decomposition (wavethresh package). I then try to find if the such transformed vectors are equivalent or not. I can do for example a simple a correlation test on wavelets coefficents, but it seems to me that in this case, it's no more better than a FFT analysis. What I wanted to do (and that's my question), is to compare coefficients values, but also compare the relative positions of coefficients on each levels. Does anybody did such a stuff under R ? -- Cordialy Emmanuel POIZOT Cnam/Intechmer Digue de Collignon 50110 Tourlaville Tél : (33)(0)2 33 88 73 42 Fax : (33)(0)2 33 88 73 39 - __ [EMAIL PROTECTED] mailing list http://www.stat.math.ethz.ch/mailman/listinfo/r-help