Hi Naomi, The colorspace dependency will be removed in the next version of hexbin. Most of the functionality I needed is now in grDevices. This should be in the development version in the next couple days. Also, I just committed some code last night to mix hexbin with lattice so that now one can do hexploms and conditional plots. Thanks to Deepayan for that. Nicholas > > Message: 4 > Date: Wed, 19 Oct 2005 14:26:42 -0400 > From: Naomi Altman <naomi at="" stat.psu.edu=""> > Subject: [BioC] ANCOVA in limma > To: bioconductor at stat.math.ethz.ch > Message-ID: <6.2.5.6.2.20051019142403.033e61e8 at stat.psu.edu> > Content-Type: text/plain; charset="us-ascii"; format=flowed > > We would like to adjust our ANOVA-type analysis by using the > covariate "age". Because limma is based on contrast, rather than > "type III SS", it seems to me that the only way to proceed with an > ANCOVA-type analysis is to orthogonalize the design matrix against > the covariate. Is there a more straight-forward method? > > Naomi S. Altman 814-865-3791 (voice) > Associate Professor > Dept. of Statistics 814-863-7114 (fax) > Penn State University 814-865-1348 (Statistics) > University Park, PA 16802-2111 > > > > ------------------------------ > > Message: 5 > Date: Wed, 19 Oct 2005 14:58:43 -0400 > From: Naomi Altman <naomi at="" stat.psu.edu=""> > Subject: [BioC] hexbin in R 2.2.0 - installation problem > To: bioconductor at stat.math.ethz.ch > Message-ID: <6.2.5.6.2.20051019145353.03423508 at stat.psu.edu> > Content-Type: text/plain; charset="us-ascii"; format=flowed > > I just downloaded R 2.2.0 for Windows, after which I installed > several Bioconductor packages using the packages menu. > > I downloaded hexbin and graph apparently without incident, except > that "colorspace" was not found. > > However, I cannot run hexbin: > > >library(hexbin) > > Loading required package: colorspace > Error: package 'colorspace' could not be loaded > In addition: Warning message: > there is no package called 'colorspace' in: library(pkg, > character.only = TRUE, logical = TRUE, lib.loc = lib.loc) > > > hexbin > Error: object "hexbin" not found > > > "graph" apparently installed "Ruuid". I got the following message > when installing hexbin > > dependency ''colorspace'' is not available > > trying URL > 'http://www.bioconductor.org/bin/windows/contrib/2.2/hexbin_1.4.0.zip' > Content type 'application/zip' length 1135841 bytes > opened URL > downloaded 1109Kb > > package 'hexbin' successfully unpacked and MD5 sums checked > > The downloaded packages are in > C:\temp\Rtmp18070\downloaded_packages > updating HTML package descriptions > > > > Naomi S. Altman 814-865-3791 (voice) > Associate Professor > Dept. of Statistics 814-863-7114 (fax) > Penn State University 814-865-1348 (Statistics) > University Park, PA 16802-2111 > > > > ------------------------------ > > Message: 8 > Date: Wed, 19 Oct 2005 13:53:04 -0700 > From: Seth Falcon <sfalcon at="" fhcrc.org=""> > Subject: Re: [BioC] hexbin in R 2.2.0 - installation problem > To: bioconductor at stat.math.ethz.ch > Message-ID: <m2ek6hns9b.fsf at="" macaroni.local=""> > Content-Type: text/plain; charset=us-ascii > > Hi Naomi, > > On 19 Oct 2005, naomi at stat.psu.edu wrote: > > > I just downloaded R 2.2.0 for Windows, after which I installed > > several Bioconductor packages using the packages menu. > > > > I downloaded hexbin and graph apparently without incident, except > > that "colorspace" was not found. > > I'm guessing: > 1. you did the installation using the menus > 2. you had selected only the bioconductor repository to select > packages from. > > Unfortunately, this doesn't allow the tools to install dependencies > from other package repositories, namely CRAN, where colorspace is > hosted. > > This isn't your fault and it is something we will try to address for > the future. > > I think you can resolve your issue with hexbin by installing the > colorspace package from CRAN. > > You might also try select both bioconductor and CRAN repositories form > the menu and then reinstalling hexbin (note: I haven't tried this, but > I think it has a good chance of working). > > Best, > > + seth > >