Re: [R] fitdistr question
The ML estimate of lambda is the mean, so no need for (iterative) optimization. See eg: http://mathworld.wolfram.com/MaximumLikelihood.html hth, Ingmar On Fri, Feb 11, 2011 at 8:52 AM, Antje Niederlein niederlein-rs...@yahoo.de wrote: Hello, I tried to fit a poisson distribution but looking at the function fitdistr() it does not optimize lambda but simply estimates the mean of the data and returns it as lambda. I'm a bit confused because I was expecting an optimization of this parameter to gain a good fit... If I would use mle() of stats4 package or mle2() of bbmle package, I would have to write the function by myself which should be optimized. But what shall I return? -sum((y_observed - y_fitted)^2) ? Any other suggestions or comments on my solution? Antje __ 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. [[alternative HTML version deleted]] __ 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.
Re: [R] extracting characters from string
Well, I believe, given the original statement of the problem, that it
is philosophically wrong to use the gsub approach. What if there are
50 underscores instead of 5, and you want to extract the characters
after the 23rd underscore? By using gsub, you are trying to fight
against the pattern of underscores. By using strsplit, we are using
that pattern to our advantage. Kind of. :)
Besides, breaking it up using strsplit will also give us the option to
iterate through it, though it is not relevant it here.
--
Soumendra Prasad Dhanee
Quantitative Analyst, Neural Technologies and Software Pvt. Ltd.
soumen...@neuraltechsoft.com, soumen...@maths.org.in, soumen...@gmail.com
+91-7498076111, +91-8100428686
--
When you understand why you dismiss all the other possible gods, you
will understand why I dismiss yours. - Stephen Roberts
On 11 February 2011 05:55, jim holtman jholt...@gmail.com wrote:
A safer way to make sure you don't match the underscore:
gsub([^_]*_[^_]*_([^_]*).*, \\1, abcd_efgh_X_12ab3_dfsfd)
[1] X
On Thu, Feb 10, 2011 at 2:06 PM, Henrique Dallazuanna www...@gmail.com
wrote:
So, a way could be:
gsub((.*)_(.*)_(.*)_.*, \\3, abcd_efgh_X_12ab3_dfsfd)
On Thu, Feb 10, 2011 at 3:47 PM, Soumendra soumen...@gmail.com wrote:
Hi Henrique,
I believe your solution is wrong as it is fitted to find 12ab3,
whereas Yan seems to be asking for the characters after the second
underscore and before the third underscore.
For example, gsub(.*_.*_(.*)_.*, \\1,
abcd_efgh_X_12ab3_dfsfd) would still yield 12ab3 even though, as
I understand it, it should have output X.
I think a straightforward solution would do the job:
strsplit(abcd_efgh_12ab3_dfsfd, _)[[1]][3]
strsplit(abcd_efgh_X_12ab3_dfsfd, _)[[1]][3] has the output
X, for example.
Of course, I would be wrong if Yan specifically wanted to find the
string 12ab3. But in that case, he would have been asking for matching
(and locating) that substring instead of extracting it.
Regards,
Soumendra
--
Soumendra Prasad Dhanee
Quantitative Analyst, Neural Technologies and Software Pvt. Ltd.
soumen...@neuraltechsoft.com, soumen...@maths.org.in, soumen...@gmail.com
+91-7498076111, +91-8100428686
--
When you understand why you dismiss all the other possible gods, you
will understand why I dismiss yours. - Stephen Roberts
On 10 February 2011 11:52, Henrique Dallazuanna www...@gmail.com wrote:
Try this:
gsub(.*_.*_(.*)_.*, \\1, abcd_efgh_12ab3_dfsfd)
On Thu, Feb 10, 2011 at 9:42 AM, Yan Jiao y.j...@ucl.ac.uk wrote:
Dear R gurus,
If I got a vector with string characters like abcd_efgh_12ab3_dfsfd,
how could I extract 12ab3, which is the characters after second
underscore and before the third underscore?
Tons of thanks
yan
**
This email and any files transmitted with it are
confide...{{dropped:10}}
__
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.
--
Henrique Dallazuanna
Curitiba-Paraná-Brasil
25° 25' 40 S 49° 16' 22 O
[[alternative HTML version deleted]]
__
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.
--
Henrique Dallazuanna
Curitiba-Paraná-Brasil
25° 25' 40 S 49° 16' 22 O
[[alternative HTML version deleted]]
__
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.
--
Jim Holtman
Data Munger Guru
What is the problem that you are trying to solve?
__
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.
Re: [R] Revolution Analytics reading SAS datasets
On 02/10/2011 07:44 PM, David Smith wrote: The SAS import/export feature of Revolution R Enterprise 4.2 isn't open-source, so we can't release it in open-source Revolution R Community, or to CRAN as we do with the ParallelR packages (foreach, doMC, etc.). It is, though, available for download free of charge to members of the academic community (as is all of Revolution Analytics' software) from http://www.revolutionanalytics.com/downloads/ timeo Danaos et dona ferentes On Wed, Feb 9, 2011 at 5:46 PM, Daniel Nordlunddjnordl...@frontier.com wrote: Has anyone heard whether Revolution Analytics is going to release this capability to the R community? http://www.businesswire.com/news/home/20110201005852/en/Revolution-Analytics-Unlocks-SAS-Data Dan Daniel Nordlund Bothell, WA USA VP of Marketing, Revolution Analytics http://blog.revolutionanalytics.com __ 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.
Re: [R] fitdistr question
Hi Ingmar, hi Dennis, okay, you're right. I was expecting that the result would give the best fit to my data even if it's not a real poisson distribution. It looks somehow similar... But how to judge the goodness of fit? I was using the residual sum of squares. I'm not a statistician, so I'm not sure whether this method is the one to choose... If I estimate lambda with mle2() and use the RSS as criteria to minimize, my lambda is much smaller that with fitdistr(). I'm happy about any suggestion! Antje On 11 February 2011 09:16, Ingmar Visser i.vis...@uva.nl wrote: The ML estimate of lambda is the mean, so no need for (iterative) optimization. See eg: http://mathworld.wolfram.com/MaximumLikelihood.html hth, Ingmar On Fri, Feb 11, 2011 at 8:52 AM, Antje Niederlein niederlein-rs...@yahoo.de wrote: Hello, I tried to fit a poisson distribution but looking at the function fitdistr() it does not optimize lambda but simply estimates the mean of the data and returns it as lambda. I'm a bit confused because I was expecting an optimization of this parameter to gain a good fit... If I would use mle() of stats4 package or mle2() of bbmle package, I would have to write the function by myself which should be optimized. But what shall I return? -sum((y_observed - y_fitted)^2) ? Any other suggestions or comments on my solution? Antje __ 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. __ 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.
Re: [R] Optimal choice of the threshold u in Peak Over Threshold (POT)Approach
Dear Fir,
for instance, have a look at the package 'ismev' and the function mrl.plot().
The CRAN task view 'Finance' lists many more packages that address EVT under
the topic 'Risk management'.
Best,
Bernhard
-Ursprüngliche Nachricht-
Von: r-help-boun...@r-project.org
[mailto:r-help-boun...@r-project.org] Im Auftrag von FMH
Gesendet: Donnerstag, 10. Februar 2011 19:28
An: r-help@r-project.org
Betreff: [R] Optimal choice of the threshold u in Peak Over
Threshold (POT)Approach
Dear All,
Could someone please suggest me the way to calculate the
optimal threshold in POT method via any available packages in R?
Thanks,
Fir
__
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.
*
Confidentiality Note: The information contained in this ...{{dropped:10}}
__
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.
Re: [R] fitdistr question
Yes, I understand. If I have a distribution which is not listed in fitdistr() but I still would like to you compute the ML estimate. Would it be correct to maximize the following function? sum( log( dens_mydistr(x, my_distr_param))) As I said, I try to step into this field by reading and trying things and I'm not sure whether I got it right how to find the ML-function of a more complex distribution... Antje On 11 February 2011 10:14, Ingmar Visser i.vis...@uva.nl wrote: Antje, On Fri, Feb 11, 2011 at 9:58 AM, Antje Niederlein niederlein-rs...@yahoo.de wrote: Hi Ingmar, hi Dennis, okay, you're right. I was expecting that the result would give the best fit to my data even if it's not a real poisson distribution. It looks somehow similar... The ML estimate is of course made under the assumption that the data stems from a Poisson distribution, and under that assumption, the ML estimate is most efficient and unbiased compared with other estimates. Best, Ingmar But how to judge the goodness of fit? I was using the residual sum of squares. I'm not a statistician, so I'm not sure whether this method is the one to choose... If I estimate lambda with mle2() and use the RSS as criteria to minimize, my lambda is much smaller that with fitdistr(). I'm happy about any suggestion! Antje On 11 February 2011 09:16, Ingmar Visser i.vis...@uva.nl wrote: The ML estimate of lambda is the mean, so no need for (iterative) optimization. See eg: http://mathworld.wolfram.com/MaximumLikelihood.html hth, Ingmar On Fri, Feb 11, 2011 at 8:52 AM, Antje Niederlein niederlein-rs...@yahoo.de wrote: Hello, I tried to fit a poisson distribution but looking at the function fitdistr() it does not optimize lambda but simply estimates the mean of the data and returns it as lambda. I'm a bit confused because I was expecting an optimization of this parameter to gain a good fit... If I would use mle() of stats4 package or mle2() of bbmle package, I would have to write the function by myself which should be optimized. But what shall I return? -sum((y_observed - y_fitted)^2) ? Any other suggestions or comments on my solution? Antje __ 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. __ 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.
[R] directed MST
Hi every body, Is there any function in R to find the Directed Minimum Spanning tree? There are some for undirected but I am looking for a directed Minimum spannin tree. Regards, Amir __ 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.
Re: [R] Ggplot: free x-scales in a facet-grid
Hello, hereby the code with example data, as an attach to my question (see mail below). Thank you! Ann library(ggplot2) library(grid) library(RColorBrewer) library(car) library(reshape) #make dataframe ID=c(a,b,c,d,e,f,g,h,i,j) type=c(type1,type2,type3,type2,type2,type1,type2,type1,type1,type3) dat_feit_lo=c(13229222400,13510803600,13463193600,13491619200,13502732400,13514315400,13463193600,13514718600,13514497200,13515031800) dat_feit_hi=c(13502591940,13510803600,13464798000,13508697600,13514036100,13514315400,13507862400,13514719380,13514432400,13515036600) dat_pol=c(13512488400,13510877580,13468415940,13508697600,13514036100,13514315400,13513528800,13514719380,13514809800,13515037260) dat_avv_start=c(13512502320,13510936200,13513705980,13514227440,13514217300,13514396280,13514636520,13514810580,13514909640,13515099060) feiten-data.frame(ID,type,dat_feit_lo,dat_feit_hi,dat_pol,dat_avv_start) #make POSIX of date variables feiten$dat_feit_lo-as.POSIXct(feiten$dat_feit_lo, origin=1582-10-14,tz=GMT) feiten$dat_feit_hi-as.POSIXct(feiten$dat_feit_hi, origin=1582-10-14,tz=GMT) feiten$dat_pol-as.POSIXct(feiten$dat_pol, origin=1582-10-14,tz=GMT) feiten$dat_avv_start-as.POSIXct(feiten$dat_avv_start, origin=1582-10-14,tz=GMT) #sort melt data# feiten$ID-with(feiten,reorder(reorder(reorder(ID,1/as.numeric(dat_pol)),1/as.numeric(dat_avv_start)),as.numeric(type))) sortframe=function(df,...)df[do.call(order,list(...)),] data_sort-with(feiten,sortframe(feiten,as.numeric(type),1/as.numeric(dat_avv_start),1/as.numeric(dat_pol))) data.melt-melt.data.frame(data_sort, id=c(ID,type), variable_name = time) levels(data.melt$time)-c(fact low,fact high,complaint,hearing) #make plot# data.melt$pos-data.melt$valueas.POSIXlt(2010-12-01 00:00:00) data.melt$pos[is.na(data.melt$pos)]-'FALSE' plot- ggplot(data.melt,aes(value,ID)) + geom_point(aes(groups=time,colour=time,shape=time)) + facet_grid(type~pos,scales=free,space=free) + opts(strip.text.y=theme_text())+ xlab(NULL) + ylab(NULL)+ opts(axis.text.x = theme_text(angle = 90, hjust = 1, size = 8)) + opts(legend.text = theme_text(hjust=1, size = 8))+ opts(legend.position=top,legend.direction=horizontal)+ scale_shape_manual(values = c(1,3,0,2),name=) + scale_colour_manual(values = c(red,red,royalblue4,mediumvioletred),name=) - Original Message - From: Strategische Analyse CSD Hasselt csd...@fedpolhasselt.be To: r-help@R-project.org Sent: Thursday, February 10, 2011 2:40 PM Subject: Ggplot: free x-scales in a facet-grid Hello, I have a ggplot that has the looks of the plot that I want, but it doesn't have the right layout. The data is an ordered melted dataframe: - ID - type (to use for a faced grid) - time - type - time - value (POSIXct) - pos (to use for a faced grid, this is an index to split the plot) The goal of the plot is to create a time line for each ID (different points of time). The ID's are split in facets according to their type. The plot will look like this (the numbers refer to the ID, the letters to the time values): 1 xosTYPE1 2xo s 3 xosTYPE2 4xos TYPE3 The data are ordered within each type, according to date 's'. Now here's the problem. The most data are between the periode 01/12/2010 and 31/01/2011. But there are some outliers, going back to 2003. Now I would like to split the plot in 2 (based on the index 'pos', split date = 01/12/2010), so the left part of the plot are the time values before this date (scale_x_datetime major = 1 year), and the right part of the plot are the time values after this date (scale_x_datetime major=1 day). Hereby also the R-code (simplified): ggplot(data_plot.melt,aes(timevalue,ID)) + geom_point(aes(groups=timetype,colour=timetype,shape=timetype)) + facet_grid(type ~pos,scales=free,space=free) + xlab(NULL) + ylab(NULL) The scales of y has to be free, because the number of ID's per type differ. The scales of x has to be free, so the scales differ in the left and right part of the plot. This code succeeds in my goal, but the left part of the plot is very big, and the right part very very small. However, the most important part of the plot is the right part. The left part is only to mention the outliers, to read the plot correctly. I don't know if it's possible to get a plot like I want? Before I added the following code to make the plot, but then I loose the information of every time value before 01/12/2010: + scale_x_datetime (major = 1 days,limits=c(as.numeric(as.POSIXlt(2010-12-01 00:00:00)),as.numeric(as.POSIXlt(2011-01-31 22:00:00))),format = %b-%d,expand=c(0,0)) Thank you very much in advance! Ann Frederix __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide
[R] How to compute yaxp and usr without plotting ?
Dear all, I'd like to know how I could compute the parameters yaxp and (the y components of) usr without having to plot the data first. Note that ylim is /a priori/ fixed. The aim is to automatically adjust the parameter mgp without having to make the plot twice. Then, with yaxp and usr known, it should be easy to calculate a suitable mgp with the axTicks and strwidth functions. Many thanks in advance, Yves [[alternative HTML version deleted]] __ 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.
Re: [R] Simulation of Multivariate Fractional Gaussian Noise and Fractional Brownian Motion
Dear Kjetil, Thank you so much for your advice on my question. Best Regards, Wonsang 2011/2/10 Kjetil Halvorsen kjetilbrinchmannhalvor...@gmail.com What you can do to find out is to type into your R session RSiteSearch(multivariate fractional gaussian) That seems to give some usefull results. Kjetil On Tue, Feb 8, 2011 at 1:51 PM, Wonsang You y...@ifn-magdeburg.de wrote: Dear R Helpers, I have searched for any R package or code for simulating multivariate fractional Brownian motion (mFBM) or multivariate fractional Gaussian noise (mFGN) when a covariance matrix are given. Unfortunately, I could not find such a package or code. Can you suggest any solution for multivariate FBM and FGN simulation? Thank you for your help. Best Regards, Ryan - Wonsang You Leibniz Institute for Neurobiology -- View this message in context: http://r.789695.n4.nabble.com/Simulation-of-Multivariate-Fractional-Gaussian-Noise-and-Fractional-Brownian-Motion-tp3276296p3276296.html Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]] __ 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. [[alternative HTML version deleted]] __ 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.
Re: [R] Writing R packages in an easier way?
On Fri, Feb 11, 2011 at 7:52 AM, Dr. Michael Wolf m-w...@muenster.de wrote:
Dear R colleagues,
is there an easier way to write R packages for the own use - without RTools
and TeX?
There are simpler ways of maintaining R source code than building
packages. I bashed out a quick way of keeping code in directories as
source and reading in on demand. All you need is two functions:
import - function(dir){
e = attach(NULL,name=dir)
assign(__path__,dir,envir=e)
reload(e)
invisible(e)
}
reload - function(e){
path = get(__path__,e)
files = list.files(path,.R$,full.names=TRUE,recursive=TRUE,ignore.case=TRUE)
for(f in files){
sys.source(f,envir=e)
}
}
Now put the source code in some folder/directory somewhere. You can
even make subdirs if you wish to organise it that way.
I've got some .R files in lib1. I do;
import(lib1)
and that runs 'source' on all the .R files in there and loads them
into position 2 on the search list. ls(pos=2) shows them.
If you edit the source code, just do reload(2) (assuming it hasn't
moved because you've loaded another package) and your stuff will be
updated. It just sources everything again. Do detach(2) to get rid of
it.
If you want to distribute your code in source format, just make a
zip or tar of the folder with the code in, and make sure your users
have the import and reload functions (I should probably put them in a
package one day...).
To distribute in 'binary' format, do an import, and then save as .RData:
save(list=ls(pos=2),file=lib1.RData, envir=as.environment(2)) #
not well tested
Then your users just need to attach(lib1.RData) to get your functions.
Now this scheme could get more complex - for example it doesn't deal
with C or Fortran code, or documentation, or tests, or examples, or
version numbering. Adding any of those would be pointless - if you
want any of that either use packages and learn to write R docs
(roxygen helps) or add it to my code yourself. You'll end up
rebuilding the R package system anyway.
Hope this helps. Doubtless someone else will come up with a simple
way to build proper packages without all the bondage and discipline
that annoys you.
Barry
__
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.
Re: [R] Ggplot: free x-scales in a facet-grid
Dear Ann, The easiest way is to seperate both plots into two subplots. And then use viewport to paste them together. Best regards, Thierry p1 - ggplot(subset(data.melt, pos = FALSE),aes(value,ID)) + geom_point(aes(groups=time,colour=time,shape=time)) + facet_grid(type~.,scales=free,space=free) + opts(strip.text.y=theme_text())+ xlab(NULL) + ylab(NULL)+ opts(axis.text.x = theme_text(angle = 90, hjust = 1, size = 8)) + opts(legend.text = theme_text(hjust=1, size = 8))+ opts(legend.position=top,legend.direction=horizontal)+ scale_shape_manual(values = c(1,3,0,2),name=) + scale_colour_manual(values = c(red,red,royalblue4,mediumvioletred),name=) p2 - ggplot(subset(data.melt, pos = TRUE),aes(value,ID)) + geom_point(aes(groups=time,colour=time,shape=time)) + facet_grid(type~.,scales=free,space=free) + opts(strip.text.y=theme_text())+ xlab(NULL) + ylab(NULL)+ opts(axis.text.x = theme_text(angle = 90, hjust = 1, size = 8)) + opts(legend.text = theme_text(hjust=1, size = 8))+ opts(legend.position=top,legend.direction=horizontal)+ scale_shape_manual(values = c(1,3,0,2),name=) + scale_colour_manual(values = c(red,red,royalblue4,mediumvioletred),name=) vp1 - viewport(width = 1/3, height = 1, x = 1/6, y = 0.5) vp2 - viewport(width = 2/3, height = 1, x = 4/6, y = 0.5) print(p1, vp = vp1) print(p1, vp = vp2) ir. Thierry Onkelinx Instituut voor natuur- en bosonderzoek team Biometrie Kwaliteitszorg Gaverstraat 4 9500 Geraardsbergen Belgium Research Institute for Nature and Forest team Biometrics Quality Assurance Gaverstraat 4 9500 Geraardsbergen Belgium tel. + 32 54/436 185 thierry.onkel...@inbo.be www.inbo.be To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of. ~ Sir Ronald Aylmer Fisher The plural of anecdote is not data. ~ Roger Brinner The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data. ~ John Tukey -Oorspronkelijk bericht- Van: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] Namens Strategische Analyse CSD Hasselt Verzonden: vrijdag 11 februari 2011 10:09 Aan: r-help@r-project.org Onderwerp: Re: [R] Ggplot: free x-scales in a facet-grid Hello, hereby the code with example data, as an attach to my question (see mail below). Thank you! Ann library(ggplot2) library(grid) library(RColorBrewer) library(car) library(reshape) #make dataframe ID=c(a,b,c,d,e,f,g,h,i,j) type=c(type1,type2,type3,type2,type2,type1,type2 ,type1,type1,type3) dat_feit_lo=c(13229222400,13510803600,13463193600,13491619200, 13502732400,13514315400,13463193600,13514718600,13514497200,13 515031800) dat_feit_hi=c(13502591940,13510803600,13464798000,13508697600, 13514036100,13514315400,13507862400,13514719380,13514432400,13 515036600) dat_pol=c(13512488400,13510877580,13468415940,13508697600,1351 4036100,13514315400,13513528800,13514719380,13514809800,13515037260) dat_avv_start=c(13512502320,13510936200,13513705980,1351422744 0,13514217300,13514396280,13514636520,13514810580,13514909640, 13515099060) feiten-data.frame(ID,type,dat_feit_lo,dat_feit_hi,dat_pol,dat _avv_start) #make POSIX of date variables feiten$dat_feit_lo-as.POSIXct(feiten$dat_feit_lo, origin=1582-10-14,tz=GMT) feiten$dat_feit_hi-as.POSIXct(feiten$dat_feit_hi, origin=1582-10-14,tz=GMT) feiten$dat_pol-as.POSIXct(feiten$dat_pol, origin=1582-10-14,tz=GMT) feiten$dat_avv_start-as.POSIXct(feiten$dat_avv_start, origin=1582-10-14,tz=GMT) #sort melt data# feiten$ID-with(feiten,reorder(reorder(reorder(ID,1/as.numeric (dat_pol)),1/as.numeric(dat_avv_start)),as.numeric(type))) sortframe=function(df,...)df[do.call(order,list(...)),] data_sort-with(feiten,sortframe(feiten,as.numeric(type),1/as. numeric(dat_avv_start),1/as.numeric(dat_pol))) data.melt-melt.data.frame(data_sort, id=c(ID,type), variable_name = time) levels(data.melt$time)-c(fact low,fact high,complaint,hearing) #make plot# data.melt$pos-data.melt$valueas.POSIXlt(2010-12-01 00:00:00) data.melt$pos[is.na(data.melt$pos)]-'FALSE' plot- ggplot(data.melt,aes(value,ID)) + geom_point(aes(groups=time,colour=time,shape=time)) + facet_grid(type~pos,scales=free,space=free) + opts(strip.text.y=theme_text())+ xlab(NULL) + ylab(NULL)+ opts(axis.text.x = theme_text(angle = 90, hjust = 1, size = 8)) + opts(legend.text = theme_text(hjust=1, size = 8))+ opts(legend.position=top,legend.direction=horizontal)+ scale_shape_manual(values = c(1,3,0,2),name=) + scale_colour_manual(values = c(red,red,royalblue4,mediumvioletred),name=) - Original Message - From: Strategische Analyse CSD Hasselt csd...@fedpolhasselt.be To: r-help@R-project.org Sent: Thursday, February 10, 2011 2:40 PM
Re: [R] Matrix of Matrices?
On Thu, Feb 10, 2011 at 11:54:50PM -0800, Alaios wrote:
Dear all I have a few matrices that I would like to store alltogether under a
bigger object.
My matrixes with the same name were calculated inside a loop like
for (few times){
estimatedsr- this is my matrix
savematrixasimagefile();
}
which means that I was losing all that instances.
What can I do to keep all these matrices? ( I do not know in advance their
number, so I can not preallocate space).
How can I store them and adress them back again?
I would like to thank you in advance in your help
Hello.
A possible approach is to use list (see ?list).
lst - list()
lst[[1]] - rbind(c(1, 2), c(1, 2))
lst[[2]] - rbind(c(3, 3), c(4, 4))
lst
[[1]]
[,1] [,2]
[1,]12
[2,]12
[[2]]
[,1] [,2]
[1,]33
[2,]44
If you know in advance an upper bound on the number of matrices,
then it is possible to use an array (see ?array). For example
storing two matrices 2 x 2 may be done as follows
a - array(dim=c(2, 2, 2))
a[,,1] - rbind(c(1, 2), c(1, 2))
a[,,2] - rbind(c(3, 3), c(4, 4))
a
, , 1
[,1] [,2]
[1,]12
[2,]12
, , 2
[,1] [,2]
[1,]33
[2,]44
Hope this helps.
Petr Savicky.
__
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.
Re: [R] Writing R packages in an easier way?
Dear Dr. Wolf:
I understand your concern that the mechanics of writing an R
package can be difficult. It was hard for me when I started.
I came to embrace it, because I actually got more done in less
time doing so. In my previous experience, as code I wrote got more
complicated, it became more difficult to find bugs. Then I started
writing R packages, beginning by writing the documentation including
examples that became unit tests
(http://en.wikipedia.org/wiki/Unit_testing). Then I wrote code to the
test. For example, I would first write function A. Then I write B that
calls A. Then I write C that also uses A. In the process of writing C,
I modify A. When I run R CMD check, I learn that my change to A broke
B. I learn that instantly. Without the R package discipline, it could
be 6 months before I learned that I had a bug. Then finding and fixing
it was very difficult and time consuming. Now, whenever I stumble over
a new bug, I add it to my tests in the examples on the help page.
People tell me I shouldn't put too much in the examples, because the
complicated examples can confuse users. Fortunately, with \dontshow,
not all examples need to be shown to the users of the help page.
By using the R package development process, I get more
trustworthy software -- fewer bugs -- with less time, work, blood, sweat
and tears. The savings comes from less time spent debugging. Moreover,
the resulting software is generally better designed, because the process
of writing the standard help page with the standard parts helps me think
through what each function should do and how they all should work
together. I save so much debugging time that I essentially get the
documentation for free. This makes it much easier to share my code with
others -- and to revisit code I wrote previously but had forgotten many
details.
I started writing Fortran in 1963, and I had many bad software
development habits. I had read a lot about software productivity and
the virtues various software productivity practices. It was only when I
started writing R packages that I began to actually use those
recommended practices productively.
I've never read the entire Writing R Extensions manual, though
I have used it repeatedly as a reference. Fortunately, there are
simpler introductions to R package development. Have you checked the
contributed page on CRAN for the word package? I just found 9
matches, including 4 documents on creating R packages, two in English,
one in French, and one in Italian. Leider, kein Deutsch.
Hope this helps.
Spencer
On 2/11/2011 3:03 AM, Barry Rowlingson wrote:
On Fri, Feb 11, 2011 at 7:52 AM, Dr. Michael Wolfm-w...@muenster.de wrote:
Dear R colleagues,
is there an easier way to write R packages for the own use - without RTools
and TeX?
There are simpler ways of maintaining R source code than building
packages. I bashed out a quick way of keeping code in directories as
source and reading in on demand. All you need is two functions:
import- function(dir){
e = attach(NULL,name=dir)
assign(__path__,dir,envir=e)
reload(e)
invisible(e)
}
reload- function(e){
path = get(__path__,e)
files =
list.files(path,.R$,full.names=TRUE,recursive=TRUE,ignore.case=TRUE)
for(f in files){
sys.source(f,envir=e)
}
}
Now put the source code in some folder/directory somewhere. You can
even make subdirs if you wish to organise it that way.
I've got some .R files in lib1. I do;
import(lib1)
and that runs 'source' on all the .R files in there and loads them
into position 2 on the search list. ls(pos=2) shows them.
If you edit the source code, just do reload(2) (assuming it hasn't
moved because you've loaded another package) and your stuff will be
updated. It just sources everything again. Do detach(2) to get rid of
it.
If you want to distribute your code in source format, just make a
zip or tar of the folder with the code in, and make sure your users
have the import and reload functions (I should probably put them in a
package one day...).
To distribute in 'binary' format, do an import, and then save as .RData:
save(list=ls(pos=2),file=lib1.RData, envir=as.environment(2)) #
not well tested
Then your users just need to attach(lib1.RData) to get your functions.
Now this scheme could get more complex - for example it doesn't deal
with C or Fortran code, or documentation, or tests, or examples, or
version numbering. Adding any of those would be pointless - if you
want any of that either use packages and learn to write R docs
(roxygen helps) or add it to my code yourself. You'll end up
rebuilding the R package system anyway.
Hope this helps. Doubtless someone else will come up with a simple
way to build proper packages without all the bondage and discipline
that annoys you.
Barry
__
R-help@r-project.org mailing list
Re: [R] Writing R packages in an easier way?
Dr. Michael Wolf m-w...@muenster.de 11/02/2011 07:52
is there an easier way to write R packages for the own use - without
RTools and TeX?
Installing Rtools is not hard, and doesn't have to happen often; the
hardest bit in Windows is making sure that the requisite executables are
on the path, and that just involves adding the directory names to the
path environment variable. If I understand you, the problem is the time
spent hacking about in the .Rd help files. That can certainly be
simplified - eliminated, in fact.
Use package.skeleton() once you have a good starting set of functions
and data in R. That creates all the necessary directories, creates
skeleton (but valid) .Rd files, and exports your functions and data
objects for you. You can then edit the code directly, use RCMD check to
check the package (useful anyway) and use RCMD build to build it. (In
fact if all you want is the zip, you can - or at least could - zip the
package directory created by RCMD check).
S Ellison
***
This email and any attachments are confidential. Any use...{{dropped:8}}
__
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.
Re: [R] Writing R packages in an easier way?
On Fri, Feb 11, 2011 at 12:33 PM, Spencer Graves spencer.gra...@structuremonitoring.com wrote: Dear Dr. Wolf: I understand your concern that the mechanics of writing an R package can be difficult. It was hard for me when I started. I should add that although I did write that import/reload code for simple development of R code in folders - I don't actually use it. It's one of those things I wrote because someone on R-help asked a similar question to Dr Wolf's. I write proper packages with examples and tests. Of course I do. Barry __ 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.
[R] Large Datasets
I have recently been using R - more speciifcally the GUI packages Rattle and Rcmdr. I like these products a lot and want to use them for some projects - the problem that I run into is when I start to try and run large datasets through them. The data sets are 10-15 million in record quantity and usually have 15-30 fields (both numerical and categorical). I saw that there were some packages that could deal with large datasets in R - bigmemory, ff, ffdf, biganalytics. My problem is that I am not much of a coder (and the reason I use the above mentioned GUIs). These GUIs do show the executable R code in the background - my thought was to run a small sample through the GUI, copy the code, and then incorporate some of the large data packages mentioned above - have anyone every tried to do this and would you have working examples. In terms of what I am trying to do to the data - really simple stuff - desriptive statistics, k-means clustering, and possibly some decision trees. Any help would be greatly appreciated. Thank you - John John Filben Cell Phone - 773.401.2822 Email - johnfil...@yahoo.com [[alternative HTML version deleted]] __ 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.
[R] Ordinal logistic regression (lrm)- checking model assumptions
Dear all, I have been using the lrm function in R to run an ordinal logistic regression and I am a bit confused about the methods for checking the model assumptions. I have produced residual plots in R of the score.binary type which I think look ok. However, the partial type plots show bell shaped patterns and have crossing lines, indicating violation of parallelism. However, I noticed on the help page that for ordinal models, simulations where proportional odds are satisfied have also produced similar patterns. I have also run the regression in SPSS and found that the test of parallel lines shows that the assumption of parallelism has not been violated. However, I have read that this is not a reliable method. I am finding it very confusing to determine if my model meets the necessary assumptions. Does anybody know the best way to do this? Any advice would be much appreciated, Thank you, Anna __ 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.
Re: [R] How can we make a vector call a function element-wise efficiently?
Hi,
you compute the same results for logx many times. So it is easier and
time saving tabulating all intermediate results.
smth. like
n-10
CT=6000#assignment to CT
NT=29535210#assignment to NT
i - 0:(n-1)
lookup- lchoose(NT-n, CT-i) + lchoose(n, i)
lgmax-cummax(lookup)
calsta2-function(c) lgmax[c] + log(sum(exp(lookup[1:c] - lgmax[c])))
should help for a start, but I think, you are running into numerical
troubles, since you are dealing with very high and low (on log scale)
numbers and calsta constantly returns 57003.6 for c38 (the summands in
sum(exp(logx - logmax)) will become 0 for c38).
#check
sapply(1:50,calsta2)
sapply(1:50,calsta)
hth
Am 11.02.2011 06:12, schrieb zhaoxing731:
Hello
I have a time-comsuming program which need to simplify, I have tested
the annotated program as follow:
#define function which will be call
calsta - function(c, n=10)
+ {
+ i - seq(from=0, length=c)
+ logx - lchoose(NT-n, CT-i) + lchoose(n, i)
+ logmax - max(logx)
+ logmax + log(sum(exp(logx - logmax)))
+ }
CT=6000 #assignment to CT
NT=29535210 #assignment to NT
vec-c(2331,524,918,218,1100,547,289,1167,450,1723)
vec
[1] 2331 524 918 218 1100 547 289 1167 450 1723
vec-rep(vec,1000)#replicate the vec 1000 times
length(vec)
[1] 1
#then I'd like to make vector vec call function calsta element-wise
#and save the output to vector result
system.time(result-sapply(vec,calsta))
user system elapsed
26.450.03 26.70
system.time(for (i in 1:1) result[i]=calsta(vec[i]))
user system elapsed
27.740.14 28.94
I have about 300,000 such 26.70/ 28.94 seconds, so the approximate
computation time is 100 days
What a terrible thing to do!!!
Any modification, nomatter how subtle, will be a big help for me
Thank you in advance
Yours sincerely
ZhaoXing
Department of Health Statistics
West China School of Public Health
Sichuan University
No.17 Section 3, South Renmin Road
Chengdu, Sichuan 610041
P.R.China
__
¸Ï¿ì×¢²áÑÅ»¢³¬´óÈÝÁ¿Ãâ·ÑÓÊÏä?
__
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.
--
Eik Vettorazzi
Institut für Medizinische Biometrie und Epidemiologie
Universitätsklinikum Hamburg-Eppendorf
Martinistr. 52
20246 Hamburg
T ++49/40/7410-58243
F ++49/40/7410-57790
__
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.
Re: [R] R example code of Split-plot Manova
Dear Xiang Gao, See the OBrienKaiser example in ?Anova in the car package. I hope this helps, John -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Xiang Gao Sent: March-15-10 4:35 PM To: r-help@r-project.org Subject: [R] R example code of Split-plot Manova Hi, Urgent help- I have not been using R and statistics in my research for a long time, but still remember some concept. I would like to have a sample code for Manova analysis of Split-plot experiment. Could someone please post a sample code and a short input sample as well? Thank you so much! [[alternative HTML version deleted]] __ 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. __ 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.
[R] Using merge
Hi, I have two tables and I need to merge both. I use the merge command, but in this way the name must be exactly. How I can make to compare independently of upper or lower-case? Look: data1-data.frame(journal=c(Ecology,Environmental Entomology,Neotropical Biology And Conservation)) data2-data.frame(journal=c(Ecology,Environmental Entomology,Neotropical Biology and Conservation,Sociobiology),qualis=c(A1,A2,B1,B5)) merge(data1,data2) merge(data1,data2) journal qualis 1 Ecology A1 2 Environmental Entomology A2 the expected result is: journal qualis 1 Ecology A1 2 Environmental Entomology A2 3 Neotropical Biology And Conservation B1 Look that result is wrong because the And and and in the name Neotropical Biology And Conservation how to fix it automatically? Has any function to make all names lowercase or any other mean to make this to work. Thanks Ronaldo -- 16ª lei - Lembre-se, é a sua dissertação. Você (!) é quem precisa fazê-la. --Herman, I. P. 2007. Following the law. NATURE, Vol 445, p. 228. Prof. Ronaldo Reis Júnior | .''`. UNIMONTES/DBG/Lab. Ecologia Comportamental e Computacional | : :' : Campus Universitário Prof. Darcy Ribeiro, Vila Mauricéia | `. `'` CP: 126, CEP: 39401-089, Montes Claros - MG - Brasil | `- Fone: (38) 3229-8192 | ronaldo.r...@unimontes.br | http://www.ppgcb.unimontes.br/lecc | LinuxUser#: 205366 [[alternative HTML version deleted]] __ 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.
[R] censReg or tobit: testing for assumptions in R?
Hello! I'm thinking of applying a censored regression model to cross-sectional data, using either the tobit (package survival) or the censReg function (package censReg). The dependent variable is left and right-censored. My hopefully not too silly question is this: I understand that heteroskedasticity and nonnormal errors are even more serious problems in a censored regression than in an ols-regression. But I'm not sure how to test for these assumptions in R? Is there a way to get to the residuals of censored regression models (given that corresponding functions for lm, such as rstandard, are not applicable)? (Or perhaps I'm on the wrong track in a more fundamental sense and shouldn't be Iooking for equivalences to lm?) Many thanks for any help. EH __ 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.
[R] Using filled.contour and contour functions together
Dear R help contributors, I'd like to plot ground temperature with time on X-axis and depth on Y-axis on this datasets ( http://r.789695.n4.nabble.com/file/n3301033/NEdaily.csv NEdaily.csv ), and to do so I use the following commands: library(RSEIS) xNE - seq(1, as.numeric(as.Date(max(NEdaily[[1]])) - as.Date(min(NEdaily[[1]]))), 1) yNE - rev(c(-0.3, -0.5, -0.7, -0.9, -1.1, -1.4, -1.7, -2, -2.5, -3, -4, -5, -7, -9, -10)) zNE - mirror.matrix(as.matrix(NEdaily[1:(nrow(NEdaily)-1),2:length(NEdaily)])) filled.contour(xNE,yNE,zNE , col = myPal(20) , zlim = c(-20,20) , ylab = Depth [m], , xlab = paste(Days since , as.Date(min(NEdaily[[1]]), format =%d.%m.%Y)) ) contour(xNE,yNE,zNE, lty = 3, add = T) contour(xNE,yNE,zNE, nlevels = 1, level = 0, add = T, lwd = 1.5) I get this graph ( http://r.789695.n4.nabble.com/file/n3301033/NEdaily.png NEdaily.png ) and don't understand why filled.contour and contour plots are no set on the same dimensions and why they don't exactly overlay. Does anyone have an idea and a solution ?! Thanks in advance, Xavier -- View this message in context: http://r.789695.n4.nabble.com/Using-filled-contour-and-contour-functions-together-tp3301033p3301033.html Sent from the R help mailing list archive at Nabble.com. __ 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.
[R] extracting p-values from the Manova function (car library)
hi, i am not able to extract the p-values from the Manova function in the car library. I need to use this function in a high-throughput setting and somehow need the p-values produced. Any ideas? Best regards Bettina Kulle Andreassen -- Bettina Kulle Andreassen University of Oslo Department of Biostatistics and Institute for Epi-Gen (Faculty Division Ahus) tel: +47 22851193 +47 67963923 __ 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.
[R] Extract a slot value from a 'SpatialPolygons' class object
Dear R-users, Im currently trying to extract the value of a slot (area) but cant find out how to do that. str(overlperc) List of 1 $ :Formal class 'SpatialPolygons' [package sp] with 4 slots .. ..@ polygons :List of 1 .. .. ..$ :Formal class 'Polygons' [package sp] with 5 slots .. .. .. .. ..@ Polygons :List of 1 .. .. .. .. .. ..$ :Formal class 'Polygon' [package sp] with 5 slots .. .. .. .. .. .. .. ..@ labpt : num [1:2] 709374 -1507888 .. .. .. .. .. .. .. ..@ area : num 11542604 .. .. .. .. .. .. .. ..@ hole : logi FALSE .. .. .. .. .. .. .. ..@ ringDir: int 1 .. .. .. .. .. .. .. ..@ coords : num [1:23, 1:2] 706840 706657 706840 707294 707585 ... .. .. .. .. .. .. .. .. ..- attr(*, dimnames)=List of 2 .. .. .. .. .. .. .. .. .. ..$ : chr [1:23] 1 2 3 4 ... .. .. .. .. .. .. .. .. .. ..$ : chr [1:2] x y .. .. .. .. ..@ plotOrder: int 1 .. .. .. .. ..@ labpt: num [1:2] 709374 -1507888 .. .. .. .. ..@ ID : chr 1 .. .. .. .. ..@ area : num 11542604 .. ..@ plotOrder : int 1 .. ..@ bbox : num [1:2, 1:2] 706657 -1509411 711710 -1506189 .. .. ..- attr(*, dimnames)=List of 2 .. .. .. ..$ : chr [1:2] x y .. .. .. ..$ : chr [1:2] min max .. ..@ proj4string:Formal class 'CRS' [package sp] with 1 slots .. .. .. ..@ projargs: chr NA Id like to extract the area value so as to be able to use this value for further analysis. Heres below what I get when I only type the name of the object: overlperc [[1]] An object of class SpatialPolygons Slot polygons: [[1]] An object of class Polygons Slot Polygons: [[1]] An object of class Polygon Slot labpt: [1] 709374 -1507888 Slot area: [1] 11542604 Slot hole: [1] FALSE Slot ringDir: [1] 1 Slot coords: xy 1 706839.8 -1508654 2 706657.2 -1508029 3 706839.8 -1507634 4 707293.6 -1507284 5 707584.7 -1507174 6 708329.6 -1506851 7 709013.3 -1506539 8 709074.5 -1506513 9 709819.5 -1506189 10 710564.4 -1506289 11 711021.1 -1506539 12 711309.3 -1506769 13 711642.0 -1507284 14 711709.8 -1508029 15 711309.3 -1508690 16 711246.4 -1508774 17 710564.4 -1509347 18 709819.5 -1509411 19 709074.5 -1509277 20 708329.6 -1509072 21 707584.7 -1509039 22 706927.4 -1508774 23 706839.8 -1508654 Slot plotOrder: [1] 1 Slot labpt: [1] 709374 -1507888 Slot ID: [1] 1 Slot area: [1] 11542604 Slot plotOrder: [1] 1 Slot bbox: minmax x 706657.2 711709.8 y -1509411.3 -1506189.0 Slot proj4string: CRS arguments: NA Im stuck and spent more or less the whole afternoon online trying to find a solution to my problem but I couldnt find anything. I look forward to hear from some of you. Thanks in advance for your kind help. Have a good weekend. Cheers Xavier Xavier Hoenner PhD Student Nesting Ecology, Migrations and Diving Behaviour of Hawksbill Turtles School of Environmental Research, Charles Darwin University Darwin, NT 0909 Ph: (08)8946.7721 email:xavier.hoen...@cdu.edu.au [[alternative HTML version deleted]] __ 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.
Re: [R] When is *interactive* data visualization useful to use?
From: tal.gal...@gmail.com Date: Fri, 11 Feb 2011 08:26:16 +0200 To: r-help@r-project.org Subject: [R] When is *interactive* data visualization useful to use? Hello all, Before getting to my question, I would like to apologize for asking this question here. My question is not directly an R question, however, I still find the topic relevant to R community of users - especially due to only * partial* (current) support for interactive data visualization (see here: http://cran.r-project.org/web/views/Graphics.html were with iplots we are waiting for iplots extreme, and with rggobi, it currently can not run with R 2.12 and windows 7 OS). I guess I would just mention a few related issues that are central to R that I have encountered. This is not well organized but if there is a point here I'm suggesting that maybe the thing to do is make R work better with streaming data and provide a way to pipe text data to and from other graphically oriented tools that could be taken from many unrelated sources. One issue is the concept of streaming for dealing with unlimited data and the other is playing nice with the other tools. I recently encountered your concerns with R ( a few days ago) wondering if interactive may be a good way to survey some plot I had- many thousands of points that were hard to explore without interactive zoom seemed to be a natural for this. Often people here complain about memory limits with large data sets and it is not unreasonable to work with indefinitely long data streams and examine results in real time. I had encountered this in the past, IIRC I wanted to watch histograms from a monte carlo simulation and wanted to know right away if things were going wrong. Probably you would want to consider R capabilities along with those of related tools and means for sharing data. Even complex models or data are normally reducible to text that can piped around to various tools so having a feature like this in any tools or packages is important. If you want to author fixed results but let the viewer interact with them, maybe look at things like PDF once there are more open source tools for dealing with it. I have grown up hating PDF but apparently the viewers can offer reasonable interactivity with properly authored PDF files. The Standard is hardly well supported with open source tools and many features of the standard get referred to only available if you buy this from Adobe. This creates two issues, one just being cost and annoyance but the other is ability to check results. If you suspect something is wrong with open source you are can always look and taking someone's word for software correctness, well, take a look at the credit rating agencies LOL. And there is always a concern for an attitude problem with this too as web designers seem to think that well we created a huge brand-name file that is also a 'standard' if it is that big from a big company there must be lots of information in all those bytes as if they get paid by the megabyte when often just a csv file would be more important to R users. If you really want professional graphics with good interactivity and are willing to dig a little as part of a larger survey, I'd be curious to know if there is anything that can be extracted from all the interactive games LOL... And now for my question: While preparing for a talk I will give soon, I recently started digging into two major (Free) tools for interactive data visualization: GGobi and mondrian - both offer a great range of capabilities (even if they're a bit buggy). I wish to ask for your help in articulating (both to myself, and for my future audience) *When is it helpful to use interactive plots? Either for data exploration (for ourselves) and data presentation (for a client)?* For when explaining the data to a client, I can see the value of animation for: - Using identify/linking/brushing for seeing which data point in the graph is what. - Presenting a sensitivity analysis of the data (e.g: if we remove this point, here is what we will get) - Showing the effect of different groups in the data (e.g: let's look at our graphs for males and now for the females) - Showing the effect of time (or age, or in general, offering another dimension to the presentation) For when exploring the data ourselves, I can see the value of identify/linking/brushing when exploring an outlier in a dataset we are working on. But other then these two examples, I am not sure what other practical use [[elided Hotmail spam]] It could be argued that the interactive part is good for exploring (For example) a different behavior of different groups/clusters in the data. But when (in practice) I approached such situation, what I tended to do was to run the relevant statistical procedures (and post-hoc tests) - and what I found to be significant I would then plot with colors clearly dividing the data
[R] Passing function arguments
Hi All,
Im looking for some help passing function arguments and referencing them,
I've made a replica, less complicated function to show my problem, and how
i've made a work around for this. However i suspect there is a _FAR_ better
way of doing this.
If i do:
BuildDecayModel - function(x = this, y = that, data = model.data) {
model - nls(y ~ SSexp(x, y0, b), data = model.data)
return(model)
}
...
Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
0 (non-NA) cases
This function returns an error because the args are passed as this and
that to the model, and so fails (correct?)
If i do the following:
BuildDecayModel - function(x = total.reach, y = lift, data =
model.data) {
x - data[[x]]
y - data[[y]]
model.data - as.data.frame(cbind(x,y))
model - nls(y ~ SSexp(x, y0, b), data = model.data)
return(model)
}
This works for me, but it seems that i'm missing a trick with just
manipulating the args rather than making an entire new data.frame to work
off,
Can anyone offer some advice?
Thanks in advance
Mike
[[alternative HTML version deleted]]
__
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.
Re: [R] Using merge
Hi, ignore my e-mail, a just use tolower function. thanks and sorry Ronaldo Em 11-02-2011 11:24, Ronaldo Reis Junior escreveu: Hi, I have two tables and I need to merge both. I use the merge command, but in this way the name must be exactly. How I can make to compare independently of upper or lower-case? Look: data1-data.frame(journal=c(Ecology,Environmental Entomology,Neotropical Biology And Conservation)) data2-data.frame(journal=c(Ecology,Environmental Entomology,Neotropical Biology and Conservation,Sociobiology),qualis=c(A1,A2,B1,B5)) merge(data1,data2) merge(data1,data2) journal qualis 1 Ecology A1 2 Environmental Entomology A2 the expected result is: journal qualis 1 Ecology A1 2 Environmental Entomology A2 3 Neotropical Biology And Conservation B1 Look that result is wrong because the And and and in the name Neotropical Biology And Conservation how to fix it automatically? Has any function to make all names lowercase or any other mean to make this to work. Thanks Ronaldo -- 16ª lei - Lembre-se, é a sua dissertação. Você (!) é quem precisa fazê-la. --Herman, I. P. 2007. Following the law. NATURE, Vol 445, p. 228. Prof. Ronaldo Reis Júnior | .''`. UNIMONTES/DBG/Lab. Ecologia Comportamental e Computacional | : :' : Campus Universitário Prof. Darcy Ribeiro, Vila Mauricéia | `. `'` CP: 126, CEP: 39401-089, Montes Claros - MG - Brasil | `- Fone: (38) 3229-8192 |ronaldo.r...@unimontes.br |http://www.ppgcb.unimontes.br/lecc | LinuxUser#: 205366 -- 1ª lei - Suas férias começam após a defesa e entrega de sua dissertação. --Herman, I. P. 2007. Following the law. NATURE, Vol 445, p. 228. Prof. Ronaldo Reis Júnior | .''`. UNIMONTES/DBG/Lab. Ecologia Comportamental e Computacional | : :' : Campus Universitário Prof. Darcy Ribeiro, Vila Mauricéia | `. `'` CP: 126, CEP: 39401-089, Montes Claros - MG - Brasil | `- Fone: (38) 3229-8192 | ronaldo.r...@unimontes.br | http://www.ppgcb.unimontes.br/lecc | LinuxUser#: 205366 [[alternative HTML version deleted]] __ 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.
Re: [R] fitdistr question
Antje Niederlein niederlein-rstat at yahoo.de writes: Hi Ingmar, hi Dennis, okay, you're right. I was expecting that the result would give the best fit to my data even if it's not a real poisson distribution. It looks somehow similar... But how to judge the goodness of fit? I was using the residual sum of squares. I'm not a statistician, so I'm not sure whether this method is the one to choose... If I estimate lambda with mle2() and use the RSS as criteria to minimize, my lambda is much smaller that with fitdistr(). There are many ways to define the best fit; RSS is one reasonable option, maximum likelihood (which in the case of a Poisson distribution is equivalent to least-squares weighted by a variance that is equal to the expected mean, i.e. (y.obs-y.fitted)^2/y.fitted) is another. Which you choose really depends on why you are calculating the estimates in the first place/ what you intend to use them for, although for Poisson data maximum likelihood approaches are more widely accepted. __ 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.
Re: [R] Large Datasets
I have not ever tried to use any GUI package. Thus, I cannot give you a good help. Instead, I would like to report my experience of exploiting the 'ff' package to have access to large dataset. To achieve your goal, I think that you need to make any function which handles ff objects. According to my experience, when I created a function which handles ff objects, it could not recognize these ff objects correctly inside the function. If you encounter such problems, you can refer to this article. http://wonsangyou.blogspot.com/2011/01/fast-access-to-large-database-in-r.html 2011/2/11 John Filben johnfil...@yahoo.com I have recently been using R - more speciifcally the GUI packages Rattle and Rcmdr. I like these products a lot and want to use them for some projects - the problem that I run into is when I start to try and run large datasets through them. The data sets are 10-15 million in record quantity and usually have 15-30 fields (both numerical and categorical). I saw that there were some packages that could deal with large datasets in R - bigmemory, ff, ffdf, biganalytics. My problem is that I am not much of a coder (and the reason I use the above mentioned GUIs). These GUIs do show the executable R code in the background - my thought was to run a small sample through the GUI, copy the code, and then incorporate some of the large data packages mentioned above - have anyone every tried to do this and would you have working examples. In terms of what I am trying to do to the data - really simple stuff - desriptive statistics, k-means clustering, and possibly some decision trees. Any help would be greatly appreciated. Thank you - John John Filben Cell Phone - 773.401.2822 Email - johnfil...@yahoo.com [[alternative HTML version deleted]] __ 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. [[alternative HTML version deleted]] __ 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.
Re: [R] Comparison of glm.nb and negbin from the package aod
sabwo sabsiw at gmx.at writes: [big snip; comparing aod::negbin and MASS::glm.nb fits] The thing i really dont understand is why there is such a big difference between the deviances? (glm.nb = 30.67 and negbin=52.09?) Shouldnt they be nearly the same?? I don't have time to dig into this right now, but calculations of log-likelihoods or deviances often drop additive constants (such as the normalizing constant in a probability distribution), and different implementations often make different choices about which constant terms to include or not. If you dig around in the code you should be able to find out which terms are included or not (although admittedly this would be a nice thing to have included in the documentation). This does make it hard to compare across fits in different packages. The important thing (and the thing I'm fairly certain of, since I've used both packages and they both seem to be well-written) is that the **differences** in deviances when comparing models A and B both fitted in the same package should be the same (because the additive constants that are included or not cancel out in this case). Ben Bolker __ 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.
Re: [R] How can we make a vector call a function element-wise efficiently?
Hi ZhaoXing, without knowledge about the ultimate purpose of your calculations its quite difficult to give further hints. best regards Am 11.02.2011 14:35, schrieb zhaoxing731: Dear Eik What a great idea!!! Thank you so much for your colossal improvment Yes, you have a unique eye on the numerical problem, I am worrying about this problem right now, hope you could give me new idea again Hi, you compute the same results for logx many times. So it is easier and time saving tabulating all intermediate results. smth. like n-10 CT=6000 #assignment to CT NT=29535210 #assignment to NT i - 0:(n-1) lookup- lchoose(NT-n, CT-i) + lchoose(n, i) lgmax-cummax(lookup) calsta2-function(c) lgmax[c] + log(sum(exp(lookup[1:c] - lgmax[c]))) should help for a start, but I think, you are running into numerical troubles, since you are dealing with very high and low (on log scale) numbers and calsta constantly returns 57003.6 for c38 (the summands in sum(exp(logx - logmax)) will become 0 for c38). #check sapply(1:50,calsta2) sapply(1:50,calsta) hth /Yours sincerely/ / / /ZhaoXing Department of Health Statistics West China School of Public Health Sichuan University No.17 Section 3, South Renmin Road Chengdu, Sichuan 610041 P.R.China/ -- Eik Vettorazzi Institut für Medizinische Biometrie und Epidemiologie Universitätsklinikum Hamburg-Eppendorf Martinistr. 52 20246 Hamburg T ++49/40/7410-58243 F ++49/40/7410-57790 __ 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.
[R] Re. When is *interactive* data visualization useful to use?
Hello Tal, You asked *When is it helpful to use interactive plots? Either for data exploration (for ourselves) and data presentation (for a client)?* My answer: It's helpful for checking data quality, for exploration with and without clients, for checking results, and for data presenting. Notes: (1) It's difficult to explain interactive data visualization in print, demonstrations are so much more effective. (2) Interactive data visualization is fun, both for the analyst, and more important, for the dataset owners. You not only get better interaction with the data, you get better interaction with the scientists you cooperate with. They are prepared to contribute, because they can understand what is going on. That is not always the case with statistical models. (3) The key is not animation but direct manipulation. The aim is to be able to directly interact with all statistical objects in a graphic: querying, linking, reordering, reformatting, zooming, whatever. (4) You write of point-based graphics, what about area-based graphics like histograms, barcharts and mosaicplots? For categorical data the ability to select groups and look at spineplots of other variables to compare proportions is very effective. (And don't forget linking to maps for spatial data.) (5) You mention outliers. How do you decide what is an outlier? Interactive parallel coordinate plots are extremely useful, either for identifying outliers or for checking ones found with an analytic approach. (6) Interactive data visualization is not in competition with other approaches, it complements them. Results found with models should be checked graphically and results found graphically should be checked analytically. Your comment about data dredging is important, though why people think this only happens with graphics and not with modelling approaches always puzzles me! (7) There are often interesting features of a dataset (not just errors and outlier groups) that can be found graphically that would be difficult or impossible to find analytically. Have a look at Interactive Graphics for Data Analysis: Principles and Examples by Martin Theus and Simon Urbanek (Chapman Hall). There are some excellent explanations and case studies there. I could go on (and on), but what you really need is a good demo. Best regards Antony PS Have you reported the bugs in GGobi and Mondrian you have found to the software authors? Antony Unwin Professor of Computer-Oriented Statistics and Data Analysis, Mathematics Institute, University of Augsburg, 86135 Augsburg, Germany __ 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.
[R] RCurl - HTTP request of header ONLY
Hi everyone, I'm trying to send an HTTP request using RCurl that only requests the response header, not the actual content. http://curl.haxx.se/docs/httpscripting.html says you can do this by using the following option: curl --head http://www.something.com/ However, I can't figure out how to do this when using 'getURL()', for example. Here's what I tried: FIRST TRY txt - getURL(http://www.something.com/;, verbose=TRUE, header=TRUE) cat(txt) This gives me header AND content. SECOND TRY headers - basicTextGatherer() txt - getURL(http://www.something.com/;, header=TRUE, trace=TRUE, headerfunction=headers$update) cat(headers$value()) This gives me the header, but the content is also requested and sent to 'txt'. I was looking for a RCurl option like 'head', but only found 'headerdata', which I assumed is not what I want. Then I also tried to understand what the individual RCurl options correspond to in terms of the original libcurl options and found a respective section in http://www.omegahat.org/RCurl/RCurlJSS.pdf (p. 10, The Request Options). Since the name of the libcurl option is 'head', a corresponding RCurl function should also be 'head'. Since it doesn't exist, I take it that it hasn't been implemented (yet), correct? Is there another way to request headers only? Thanks a lot for any advice, Janko Sys.info() sysname release Windows XP version nodename build 2600, Service Pack 3 ASHB-109C-02 machinelogin x86 wwa418 user wwa418 __ 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.
Re: [R] Matrix of Matrices?
Thanks that did the work. Once I have that list what is the easiest way to
export the structure as well as the contents (numbers) into a file.
The purpose is to share that file with a colleague and ask him to load that
variable with its contents and structure.
Best Regards
Alex
--- On Fri, 2/11/11, Petr Savicky savi...@praha1.ff.cuni.cz wrote:
From: Petr Savicky savi...@praha1.ff.cuni.cz
Subject: Re: [R] Matrix of Matrices?
To: r-help@r-project.org
Date: Friday, February 11, 2011, 12:22 PM
On Thu, Feb 10, 2011 at 11:54:50PM
-0800, Alaios wrote:
Dear all I have a few matrices that I would like to
store alltogether under a bigger object.
My matrixes with the same name were calculated inside
a loop like
for (few times){
estimatedsr- this is my matrix
savematrixasimagefile();
}
which means that I was losing all that instances.
What can I do to keep all these matrices? ( I do not
know in advance their number, so I can not preallocate
space).
How can I store them and adress them back again?
I would like to thank you in advance in your help
Hello.
A possible approach is to use list (see ?list).
lst - list()
lst[[1]] - rbind(c(1, 2), c(1, 2))
lst[[2]] - rbind(c(3, 3), c(4, 4))
lst
[[1]]
[,1] [,2]
[1,] 1 2
[2,] 1 2
[[2]]
[,1] [,2]
[1,] 3 3
[2,] 4 4
If you know in advance an upper bound on the number of
matrices,
then it is possible to use an array (see ?array). For
example
storing two matrices 2 x 2 may be done as follows
a - array(dim=c(2, 2, 2))
a[,,1] - rbind(c(1, 2), c(1, 2))
a[,,2] - rbind(c(3, 3), c(4, 4))
a
, , 1
[,1] [,2]
[1,] 1 2
[2,] 1 2
, , 2
[,1] [,2]
[1,] 3 3
[2,] 4 4
Hope this helps.
Petr Savicky.
__
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.
Don't get soaked. Take a quick peek at the forecast
with
uts/#loc_weather
__
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.
Re: [R] Matrix of Matrices?
On Fri, Feb 11, 2011 at 06:17:16AM -0800, Alaios wrote: Thanks that did the work. Once I have that list what is the easiest way to export the structure as well as the contents (numbers) into a file. The purpose is to share that file with a colleague and ask him to load that variable with its contents and structure. Any R object can be stored to a file using save() and read back using load(). Petr Savicky. __ 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.
Re: [R] Revolution Analytics reading SAS datasets
I'm sure the legal ground is tricky. However, OpenOffice and LibreOffice and KWord have been able to open the (proprietary) MS Word doc format for a while now, and they are open source (and Libre Office might even be GPL'd), so the algorithm is in fact published in Jeremy's sense, and has been for several years. I figure the reason for keeping the SAS reading functionality proprietary is Revolution's (perfectly legitimate) wish to make money by separating their product from GNU R and adding features that would make people want to buy rather than just download from CRAN. Within GNU R there are of course sas.get in the Hmisc package (which requires SAS). It should also be quite easy to write a wrapper around dsread, a command-line closed source product freely downloadable in a limited form which will convert sas7bdat files to csv or tsv format (and SQL if you pay). This latter path won't require SAS locally. I'm also sure that SAS has a way to export its datasets into R, since the current version of IML Studio will in fact interact with R. On 02/10/2011 03:11 PM, Jeremy Miles wrote: On 10 February 2011 12:01, Matt Shotwellm...@biostatmatt.com wrote: On Thu, 2011-02-10 at 10:44 -0800, David Smith wrote: The SAS import/export feature of Revolution R Enterprise 4.2 isn't open-source, so we can't release it in open-source Revolution R Community, or to CRAN as we do with the ParallelR packages (foreach, doMC, etc.). Judging by the language of Dr. Nie's comments on the page linked below, it seems unlikely this feature is the result of a licensing agreement with SAS. Is that correct? There was some discussion of this on the SAS email list. People who seem to know what they were talking about said that they would have had to reverse engineer it to decode the file format. It's slightly tricky legal ground - the file format can't be copyrighted but publishing the algorigthm might not be allowed. I guess if they release it as open source, that could be construed as publishing the algorithm. (SPSS and WPS both can open SAS files, and I'd be surprised if SAS licensed to them. [Esp WPS, who SAS are (or were) suing for all kinds of things in court in London.) Jeremy __ 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. __ 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.
[R] cycle in a directed graph
Hi, I have a directed graph and wants to find is there any cycle in it? If it is, which nodes or edges are in the cycle. Is there any way to find the cycle in a directed graph in R? Regards, Amir __ 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.
[R] Creating a ragged array
Dear list I am trying to figure out how to create a ragged array that consists of groups of array elements (indices from the original array) of similar values. I would like to create a ragged array that might look something like this: S[1] 11, 19, 14,7 S[2] 29,4,1,13,44 S[3] 56,9,2,35 S[4] 3,5 ... Thanks in advance Barth PRIVILEGED AND CONFIDENTIAL INFORMATION This transmittal and any attachments may contain PRIVILEGED AND CONFIDENTIAL information and is intended only for the use of the addressee. If you are not the designated recipient, or an employee or agent authorized to deliver such transmittals to the designated recipient, you are hereby notified that any dissemination, copying or publication of this transmittal is strictly prohibited. If you have received this transmittal in error, please notify us immediately by replying to the sender and delete this copy from your system. You may also call us at (309) 827-6026 for assistance. __ 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.
[R] lattice auto.key gives mismatch colors
Hello All,
I am using the following code to draw a figure. But the legend given buy
auto.key has mismatched colors. Could any one help me?
I am using R2.12.1 and most current lattice on windows XP.
Thanks
John
library(lattice)
src - data.frame(t=rep(c('A','B','C','D'), rep(8,4)),
s=rep(c(8132,8140,8178,8180,8224,8230,8337,8345), 4),
v=c(55.10, 56.00, 206.00, 5.86, 164.00, 102.00, 171.00,
280.00, 236.00,
91.10, 238.00, 102.00, 59.30, 227.00, 280.00, 316.00,
205.00, 120.00,
273.00, 98.80, 167.00, 104.00, 155.00, 370.00, 215.00,
97.60, 133.00,
135.00, 48.60, 135.00, 77.10, 91.90))
colors - rgb(c(228, 55, 77, 152, 255, 255, 166, 247),
c(26, 126, 175, 78, 127, 255, 86, 129),
c(28, 184, 74, 163, 0, 51, 40, 191), maxColorValue=255)
xyplot(v~t, groups=s, type='o', data=src, col=colors, auto.key =
list(points=TRUE, columns = 4, col=colors))
[[alternative HTML version deleted]]
__
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.
Re: [R] Loop in variable names
Hi Stella,
if you just want to print the tables, this should also work
for(i in angus) {
tab - paste(table, i, sep=)
cut - paste(P,i, sep = )
print(table(StoreData$CompanyID, !is.na(StoreData[,cut])))
}
If you want to keep them, your approach works, but you can also store
them in a list
tabs-list()
for(i in angus) {
tab - paste(table, i, sep=)
cut - paste(P,i, sep = )
tabs[[i]]-table(StoreData$CompanyID, !is.na(StoreData[,cut]))
}
this produces a list of 5 elements, where only 2 and 5 are populated.
Changing the last line to
tabs[[which(angus==i)]]-table(StoreData$CompanyID, !is.na(StoreData[,cut]))
produces a list of 2 elements, but the information on angus is lost.
best regards
Am 11.02.2011 15:41, schrieb Rita Carreira:
Thanks so much, that worked well; however, it did not print the tables.
I went around it and did the following, which worked:
for(i in angus) {
tab - paste(table, i, sep=)
cut - paste(P,i, sep = )
t - table(StoreData$CompanyID, !is.na(StoreData[,cut]))
assign(tab,t)
}
table2
table5
Is this the only way? Could I not have put table2 and table5 with an i
index inside the loop?
Sorry to bother you.
Stella
Date: Wed, 9 Feb 2011 20:15:23 +0100
From: e.vettora...@uke.uni-hamburg.de
To: ritacarre...@hotmail.com
CC: r-help@r-project.org
Subject: Re: [R] Loop in variable names
Hi Stella,
in your coding 'cut' is a string, not a data object.
something like
cut - paste(P,i, sep=)
table(StoreData$CompanyID, !is.na(StoreData[,cut]))
should work.
hth.
Am 09.02.2011 19:02, schrieb Rita Carreira:
Hello!
I would like to do some tables for several variables and I would
like to write a loop that does the table for each variable. I should
also point out that my data set has several missing observations and
sometimes the observations that are missing are not the same for all my
variables.
What I would like to do:
table(StoreData$CompanyID,
!is.na(StoreData$P2))
table(StoreData$CompanyID,
!is.na(StoreData$P5))
If I run the above code, I get:
table(StoreData$CompanyID,
+ !is.na(StoreData$P2))
FALSE TRUE
2 940 0
3 0 323
4 288 0
5 306 0
table(StoreData$CompanyID,
+ !is.na(StoreData$P5))
FALSE TRUE
2 940 0
3 0 323
4 288 0
5 306 0
Here's the loop that I wrote, which does not work:
angus - c(2,5)
for(i in angus) {
cut - paste(StoreData$P,i, sep=)
table(StoreData$CompanyID, !is.na(cut))
}
When I run the above, I get the following error message:
Error in table(StoreData$CompanyID, !is.na(cut)) :
all arguments must have the same length
source(.trPaths[5], echo=TRUE, max.deparse.length=150)
Any help is greatly appreciated!
Stella
[[alternative HTML version deleted]]
__
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.
--
Eik Vettorazzi
Institut für Medizinische Biometrie und Epidemiologie
Universitätsklinikum Hamburg-Eppendorf
Martinistr. 52
20246 Hamburg
T ++49/40/7410-58243
F ++49/40/7410-57790
--
Eik Vettorazzi
Institut für Medizinische Biometrie und Epidemiologie
Universitätsklinikum Hamburg-Eppendorf
Martinistr. 52
20246 Hamburg
T ++49/40/7410-58243
F ++49/40/7410-57790
__
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.
Re: [R] Creating a ragged array
On Fri, Feb 11, 2011 at 10:39 AM, Barth B. Riley bbri...@chestnut.org wrote: Dear list I am trying to figure out how to create a ragged array that consists of groups of array elements (indices from the original array) of similar values. I would like to create a ragged array that might look something like this: S[1] 11, 19, 14,7 S[2] 29,4,1,13,44 S[3] 56,9,2,35 S[4] 3,5 Try stack and unstack: S - list(A = c(11,19,14,7), B = c(29,4,1,13,44), C = c(56,9,2,35), D = c(3,5)); S stk - stack(S); stk ustk - unstack(stk); ustk identical(ustk, S) # TRUE -- Statistics Software Consulting GKX Group, GKX Associates Inc. tel: 1-877-GKX-GROUP email: ggrothendieck at gmail.com __ 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.
Re: [R] Extract a slot value from a 'SpatialPolygons' class object
On Feb 11, 2011, at 5:11 AM, Xavier Hoenner wrote: Dear R-users, Im currently trying to extract the value of a slot (area) but cant find out how to do that. Generally the authors of S4 method provide extractor functions, so the first question would be what functions were used to create the object. Fortunately there are big hints in the first line of str() results. The documentation for package sp says there is a summary method for that class as well as a [ method. Those results may offer avenues for progresss These might yield objects that could be further used: area(overlperc[1]) or polygons(overlperc) but my efforts at finding an area-extractor in the sp vignettes and RSiteSearch were not fulfilled. A brute force method is to use the primitive S4 extractor function @ to traverse the tree: So you might try either of these: polygons(overlperc)[[1]]@area #didn't work on the test object I made with one of the examples in pkg::sp This appears more likely to succeed: overlperc@polygons[[1]]@area There's also a specific mailing list for geospatial stats. -- David. str(overlperc) List of 1 $ :Formal class 'SpatialPolygons' [package sp] with 4 slots .. ..@ polygons :List of 1 .. .. ..$ :Formal class 'Polygons' [package sp] with 5 slots .. .. .. .. ..@ Polygons :List of 1 .. .. .. .. .. ..$ :Formal class 'Polygon' [package sp] with 5 slots .. .. .. .. .. .. .. ..@ labpt : num [1:2] 709374 -1507888 .. .. .. .. .. .. .. ..@ area : num 11542604 .. .. .. .. .. .. .. ..@ hole : logi FALSE .. .. .. .. .. .. .. ..@ ringDir: int 1 .. .. .. .. .. .. .. ..@ coords : num [1:23, 1:2] 706840 706657 706840 707294 707585 ... .. .. .. .. .. .. .. .. ..- attr(*, dimnames)=List of 2 .. .. .. .. .. .. .. .. .. ..$ : chr [1:23] 1 2 3 4 ... .. .. .. .. .. .. .. .. .. ..$ : chr [1:2] x y .. .. .. .. ..@ plotOrder: int 1 .. .. .. .. ..@ labpt: num [1:2] 709374 -1507888 .. .. .. .. ..@ ID : chr 1 .. .. .. .. ..@ area : num 11542604 .. ..@ plotOrder : int 1 .. ..@ bbox : num [1:2, 1:2] 706657 -1509411 711710 -1506189 .. .. ..- attr(*, dimnames)=List of 2 .. .. .. ..$ : chr [1:2] x y .. .. .. ..$ : chr [1:2] min max .. ..@ proj4string:Formal class 'CRS' [package sp] with 1 slots .. .. .. ..@ projargs: chr NA Id like to extract the area value so as to be able to use this value for further analysis. Heres below what I get when I only type the name of the object: overlperc [[1]] An object of class SpatialPolygons Slot polygons: [[1]] An object of class Polygons Slot Polygons: [[1]] An object of class Polygon Slot labpt: [1] 709374 -1507888 Slot area: [1] 11542604 Slot hole: [1] FALSE Slot ringDir: [1] 1 Slot coords: xy 1 706839.8 -1508654 2 706657.2 -1508029 3 706839.8 -1507634 4 707293.6 -1507284 5 707584.7 -1507174 6 708329.6 -1506851 7 709013.3 -1506539 8 709074.5 -1506513 9 709819.5 -1506189 10 710564.4 -1506289 11 711021.1 -1506539 12 711309.3 -1506769 13 711642.0 -1507284 14 711709.8 -1508029 15 711309.3 -1508690 16 711246.4 -1508774 17 710564.4 -1509347 18 709819.5 -1509411 19 709074.5 -1509277 20 708329.6 -1509072 21 707584.7 -1509039 22 706927.4 -1508774 23 706839.8 -1508654 Slot plotOrder: [1] 1 Slot labpt: [1] 709374 -1507888 Slot ID: [1] 1 Slot area: [1] 11542604 Slot plotOrder: [1] 1 Slot bbox: minmax x 706657.2 711709.8 y -1509411.3 -1506189.0 Slot proj4string: CRS arguments: NA Im stuck and spent more or less the whole afternoon online trying to find a solution to my problem but I couldnt find anything. I look forward to hear from some of you. Thanks in advance for your kind help. Have a good weekend. Cheers Xavier Xavier Hoenner PhD Student Nesting Ecology, Migrations and Diving Behaviour of Hawksbill Turtles School of Environmental Research, Charles Darwin University Darwin, NT 0909 Ph: (08)8946.7721 email:xavier.hoen...@cdu.edu.au [[alternative HTML version deleted]] __ 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. David Winsemius, MD West Hartford, CT __ 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.
Re: [R] Revolution Analytics reading SAS datasets
I am right now using Revolution R Enterprise 4.2. Could somebody show me how to import/export SAS datasets. Thanks. On Fri, Feb 11, 2011 at 8:52 AM, Abhijit Dasgupta, PhD aikidasgu...@gmail.com wrote: I'm sure the legal ground is tricky. However, OpenOffice and LibreOffice and KWord have been able to open the (proprietary) MS Word doc format for a while now, and they are open source (and Libre Office might even be GPL'd), so the algorithm is in fact published in Jeremy's sense, and has been for several years. I figure the reason for keeping the SAS reading functionality proprietary is Revolution's (perfectly legitimate) wish to make money by separating their product from GNU R and adding features that would make people want to buy rather than just download from CRAN. Within GNU R there are of course sas.get in the Hmisc package (which requires SAS). It should also be quite easy to write a wrapper around dsread, a command-line closed source product freely downloadable in a limited form which will convert sas7bdat files to csv or tsv format (and SQL if you pay). This latter path won't require SAS locally. I'm also sure that SAS has a way to export its datasets into R, since the current version of IML Studio will in fact interact with R. On 02/10/2011 03:11 PM, Jeremy Miles wrote: On 10 February 2011 12:01, Matt Shotwellm...@biostatmatt.com wrote: On Thu, 2011-02-10 at 10:44 -0800, David Smith wrote: The SAS import/export feature of Revolution R Enterprise 4.2 isn't open-source, so we can't release it in open-source Revolution R Community, or to CRAN as we do with the ParallelR packages (foreach, doMC, etc.). Judging by the language of Dr. Nie's comments on the page linked below, it seems unlikely this feature is the result of a licensing agreement with SAS. Is that correct? There was some discussion of this on the SAS email list. People who seem to know what they were talking about said that they would have had to reverse engineer it to decode the file format. It's slightly tricky legal ground - the file format can't be copyrighted but publishing the algorigthm might not be allowed. I guess if they release it as open source, that could be construed as publishing the algorithm. (SPSS and WPS both can open SAS files, and I'd be surprised if SAS licensed to them. [Esp WPS, who SAS are (or were) suing for all kinds of things in court in London.) Jeremy __ 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. __ 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. __ 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.
Re: [R] Passing function arguments
On Feb 11, 2011, at 6:14 AM, Michael Pearmain wrote:
Hi All,
Im looking for some help passing function arguments and referencing
them,
I've made a replica, less complicated function to show my problem,
and how
i've made a work around for this. However i suspect there is a _FAR_
better
way of doing this.
If i do:
BuildDecayModel - function(x = this, y = that, data =
model.data) {
model - nls(y ~ SSexp(x, y0, b), data = model.data)
return(model)
}
...
Error in lm.fit(x, y, offset = offset, singular.ok =
singular.ok, ...) :
0 (non-NA) cases
This function returns an error because the args are passed as this
and
that to the model, and so fails (correct?)
If i do the following:
BuildDecayModel - function(x = total.reach, y = lift, data =
model.data) {
x - data[[x]]
y - data[[y]]
model.data - as.data.frame(cbind(x,y))
model - nls(y ~ SSexp(x, y0, b), data = model.data)
return(model)
}
This works for me, but it seems that i'm missing a trick with just
manipulating the args rather than making an entire new data.frame to
work
off,
The trick you are missing is how to build a formula from component
character objects. The usual approach something like this:
?formula
Perhaps:
form - as.formula( paste(y, ~ SSexp(, , x , , y0, b) ) )
(untested)
model - nls(form, data = model.data)
paste() should result in evaluation of the argument to return this
and that which will then be bundled into a proper language object
which is not just a character string. I should say I hope this works,
but there are mysteries regarding the environment of evaluation that
continue to trip me up.
--
David.
Can anyone offer some advice?
(Some further advice: Set your client to post in plain text.)
Thanks in advance
Mike
David Winsemius, MD
West Hartford, CT
__
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.
Re: [R] Revolution Analytics reading SAS datasets
Liao, Thanks for your reply. Those solutions you mentioned used CSV or 3rd party middleware. I used Revolution R for a while. Since last week Revolution R Enterprise 4.2 could read/write SAS native dataset(.sas7bdat format), I am looking for any documents to try this feature out. Anybody can give a clue? Thanks, Charlie On Fri, Feb 11, 2011 at 10:42 AM, Gong-Yi Liao gong-yi.l...@uconn.edu wrote: If you have SAS, You can read Dr. Harrell's page: http://biostat.mc.vanderbilt.edu/wiki/Main/SASexportHowto if not, you can take a look on WPS: http://www.teamwpc.co.uk/products On Fri, 2011-02-11 at 10:32 -0600, Chao(Charlie) Huang wrote: I am right now using Revolution R Enterprise 4.2. Could somebody show me how to import/export SAS datasets. Thanks. -- Gong-Yi Liao Department of Statistics University of Connecticut 215 Glenbrook Road U4120 Storrs, CT 06269-4120 860-486-9478 __ 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.
Re: [R] Revolution Analytics reading SAS datasets
On Feb 11, 2011, at 11:32 AM, Chao(Charlie) Huang wrote: I am right now using Revolution R Enterprise 4.2. Could somebody show me how to import/export SAS datasets. Thanks. Should you be asking the company from whom you obtained this proprietary product? -- David. On Fri, Feb 11, 2011 at 8:52 AM, Abhijit Dasgupta, PhD aikidasgu...@gmail.com wrote: I'm sure the legal ground is tricky. However, OpenOffice and LibreOffice and KWord have been able to open the (proprietary) MS Word doc format for a while now, and they are open source (and Libre Office might even be GPL'd), so the algorithm is in fact published in Jeremy's sense, and has been for several years. I figure the reason for keeping the SAS reading functionality proprietary is Revolution's (perfectly legitimate) wish to make money by separating their product from GNU R and adding features that would make people want to buy rather than just download from CRAN. Within GNU R there are of course sas.get in the Hmisc package (which requires SAS). It should also be quite easy to write a wrapper around dsread, a command-line closed source product freely downloadable in a limited form which will convert sas7bdat files to csv or tsv format (and SQL if you pay). This latter path won't require SAS locally. I'm also sure that SAS has a way to export its datasets into R, since the current version of IML Studio will in fact interact with R. On 02/10/2011 03:11 PM, Jeremy Miles wrote: On 10 February 2011 12:01, Matt Shotwellm...@biostatmatt.com wrote: On Thu, 2011-02-10 at 10:44 -0800, David Smith wrote: The SAS import/export feature of Revolution R Enterprise 4.2 isn't open-source, so we can't release it in open-source Revolution R Community, or to CRAN as we do with the ParallelR packages (foreach, doMC, etc.). Judging by the language of Dr. Nie's comments on the page linked below, it seems unlikely this feature is the result of a licensing agreement with SAS. Is that correct? There was some discussion of this on the SAS email list. People who seem to know what they were talking about said that they would have had to reverse engineer it to decode the file format. It's slightly tricky legal ground - the file format can't be copyrighted but publishing the algorigthm might not be allowed. I guess if they release it as open source, that could be construed as publishing the algorithm. (SPSS and WPS both can open SAS files, and I'd be surprised if SAS licensed to them. [Esp WPS, who SAS are (or were) suing for all kinds of things in court in London.) Jeremy __ 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. __ 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. __ 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. David Winsemius, MD West Hartford, CT __ 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.
[R] foreach with registerDoMC on R 2.12.0 OSX 10.6 --- errors and warnings
some hints for the search engines. I just did install.packages(foreach) install.packages(doMC) library(doMC) registerDoMC() library(foreach) foreach(i = 1:3) %dopar% sqrt(i) The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. Tcl_ServiceModeHook: Notifier not initialized [[1]] NULL [[2]] [1] 1.414 [[3]] [1] 1.732 The first element is obviously wrong, and the warning messages are scary. Restarting R eliminated all the problems. This seems to be something odd about the install and load process. __ 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.
Re: [R] Large Datasets
On Feb 11, 2011, at 7:51 AM, John Filben wrote: I have recently been using R - more speciifcally the GUI packages Rattle and Rcmdr. I like these products a lot and want to use them for some projects - the problem that I run into is when I start to try and run large datasets through them. The data sets are 10-15 million in record quantity and usually have 15-30 fields (both numerical and categorical). You could instead just buy memory. 32GB ought to be sufficient for descriptives and regression. Might even get away with 24. I saw that there were some packages that could deal with large datasets in R - bigmemory, ff, ffdf, biganalytics. My problem is that I am not much of a coder (and the reason I use the above mentioned GUIs). These GUIs do show the executable R code in the background - my thought was to run a small sample through the GUI, copy the code, and then incorporate some of the large data packages mentioned above - have anyone every tried to do this and would you have working examples. In terms of what I am trying to do to the data - really simple stuff - desriptive statistics, Should be fine here. k-means clustering, and possibly some decision trees. Not sure how well those scale to tasks as large as what you propose, especially since you don't mention packages or functions. Not sure they don't, either. -- David. Any help would be greatly appreciated. Thank you - John John Filben -- David Winsemius, MD West Hartford, CT __ 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.
Re: [R] Revolution Analytics reading SAS datasets
CH == Chao(Charlie) Huang hch...@gmail.com on Fri, 11 Feb 2011 10:32:06 -0600 writes: CH I am right now using Revolution R Enterprise 4.2. Could CH somebody show me how to import/export SAS CH datasets. Thanks. but not primarily on R-help, please. At first, note that R is GNU R, and R-help has been about R as a Free (Libre) Software, for all its many years and hundreds of thousands of messages. Revolutions's product may be fine for some, in some situations, but supporting non-Free parts of it, really does not belong to R and R-help in my view. Martin Maechler, R Core and R mailing list administrator since 1996 CH On Fri, Feb 11, 2011 at 8:52 AM, Abhijit Dasgupta, PhD CH aikidasgu...@gmail.com wrote: I'm sure the legal ground is tricky. However, OpenOffice and LibreOffice and KWord have been able to open the (proprietary) MS Word doc format for a while now, and they are open source (and Libre Office might even be GPL'd), so the algorithm is in fact published in Jeremy's sense, and has been for several years. I figure the reason for keeping the SAS reading functionality proprietary is Revolution's (perfectly legitimate) wish to make money by separating their product from GNU R and adding features that would make people want to buy rather than just download from CRAN. Within GNU R there are of course sas.get in the Hmisc package (which requires SAS). It should also be quite easy to write a wrapper around dsread, a command-line closed source product freely downloadable in a limited form which will convert sas7bdat files to csv or tsv format (and SQL if you pay). This latter path won't require SAS locally. I'm also sure that SAS has a way to export its datasets into R, since the current version of IML Studio will in fact interact with R. On 02/10/2011 03:11 PM, Jeremy Miles wrote: On 10 February 2011 12:01, Matt Shotwellm...@biostatmatt.com wrote: On Thu, 2011-02-10 at 10:44 -0800, David Smith wrote: The SAS import/export feature of Revolution R Enterprise 4.2 isn't open-source, so we can't release it in open-source Revolution R Community, or to CRAN as we do with the ParallelR packages (foreach, doMC, etc.). Judging by the language of Dr. Nie's comments on the page linked below, it seems unlikely this feature is the result of a licensing agreement with SAS. Is that correct? There was some discussion of this on the SAS email list. People who seem to know what they were talking about said that they would have had to reverse engineer it to decode the file format. It's slightly tricky legal ground - the file format can't be copyrighted but publishing the algorigthm might not be allowed. I guess if they release it as open source, that could be construed as publishing the algorithm. (SPSS and WPS both can open SAS files, and I'd be surprised if SAS licensed to them. [Esp WPS, who SAS are (or were) suing for all kinds of things in court in London.) Jeremy __ 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.
Re: [R] extracting p-values from the Manova function (car library)
Hi, one approach is to modify getAnywhere(print.Anova.mlm) to return the information you want. Best, Ista On Fri, Feb 11, 2011 at 7:16 AM, Bettina Kulle Andreassen b.k.andreas...@medisin.uio.no wrote: hi, i am not able to extract the p-values from the Manova function in the car library. I need to use this function in a high-throughput setting and somehow need the p-values produced. Any ideas? Best regards Bettina Kulle Andreassen -- Bettina Kulle Andreassen University of Oslo Department of Biostatistics and Institute for Epi-Gen (Faculty Division Ahus) tel: +47 22851193 +47 67963923 __ 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. -- Ista Zahn Graduate student University of Rochester Department of Clinical and Social Psychology http://yourpsyche.org __ 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.
[R] Help optimizing EMD::extrema()
Hi folks,
I'm attempting to use the EMD package to analyze some neuroimaging
data (timeseries with 64 channels sampled across 1 million time points
within each of 20 people). I found that processing a single channel of
data using EMD::emd() took about 8 hours. Exploration using Rprof()
suggested that most of the compute time was spent in EMD::extrema().
Looking at the code for EMD:extrema(), I managed to find one obvious
speedup (switching from employing rbind() to c()) and I suspect that
there may be a way to further speed things up by pre-allocating all
the objects that are currently being created with c(), but I'm having
trouble understanding the code sufficiently to know when/where to try
this and what sizes to set as the default pre-allocation length. Below
I include code that demonstrates the speedup I achieved by eliminating
calls to rbind(), and also demonstrates that only a few calls to c()
seem to be responsible for most of the compute time. The files
extrema_c.R and extrema_c2.R are available at:
https://gist.github.com/822691
Any suggestions/help would be greatly appreciated.
#load the EMD library for the default version of extrema
library(EMD)
#some data to process
values = rnorm(1e4)
#profile the default version of extrema
Rprof(tmp - tempfile())
temp = extrema(values)
Rprof()
summaryRprof(tmp)
#1.2s total with most time spend doing rbind
unlink(tmp)
#load a rbind-free version of extrema
source('extrema_c.R')
Rprof(tmp - tempfile())
temp = extrema_c(values)
Rprof()
summaryRprof(tmp) #much faster! .5s total
unlink(tmp)
#still, it encounters slowdowns with lots of data
values = rnorm(1e5)
Rprof(tmp - tempfile())
temp = extrema_c(values)
Rprof()
summaryRprof(tmp)
#44s total, hard to see what's taking up so much time
unlink(tmp)
#load an rbind-free version of extrema that labels each call to c()
source('extrema_c2.R')
Rprof(tmp - tempfile())
temp = extrema_c2(values)
Rprof()
summaryRprof(tmp)
#same time as above, but now we see that it spends more time in
certain calls to c() than others
unlink(tmp)
__
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.
Re: [R] series of boxplots
If you could provide a small example of an actual data set (using dput), you may get some suggestions specific to your goals. Here are a few examples of boxplots. If these look along the lines of what you are looking for, you may want to search the ggplot2 mailing list for more examples. library(ggplot2) qplot(factor(cyl), mpg, data=mtcars, geom=boxplot) # example 2 mydata - data.frame( group1= sample(c(C,D),size=100,replace=TRUE), group2=sample(c(E,F),size=100,replace=TRUE), y=rnorm(100)) qplot(group2, y, data=mydata, facets = ~ group1, geom=boxplot) On Mon, Feb 7, 2011 at 6:16 AM, syrvn ment...@gmx.net wrote: hi group, imagine the following data frame df: 1 2 3 4 ... A 5 1 .. A 4 3 .. A 3 4 .. B 7 9 .. B 8 1 .. B 6 8 .. I tried the following and some variations to plot this matrix as boxplots: boxplot(df[1:3,2]~df[1:3,1], xlim=c(1,10)) par(new=TRUE) boxplot(cpd12[4:6,2]~df[1:3,1], xlim=c(2,10)) par(new=TRUE) boxplot(df[1:3,3]~df[1:3,1], xlim=c(1,10)) par(new=TRUE) boxplot(cpd12[4:6,3]~df[1:3,1], xlim=c(2,10)) can anybody help? Cheers -- View this message in context: http://r.789695.n4.nabble.com/series-of-boxplots-tp3263938p3263938.html Sent from the R help mailing list archive at Nabble.com. __ 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. __ 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.
Re: [R] Where can I download/install grDevices
On 2011-02-10 18:41, Dennis Murphy wrote: Hi: Here's one way: plot(1~1,ylab=expression(Areas (~mu*m^2~))) The tildes incorporate space between the math and text elements; they're optional, but useful. Another way that also works is plot(1~1,ylab=expression(paste(Areas (, mu*m^2, ), sep = ' '))) plot(1:5, type=n, axes=FALSE, ann=FALSE) abline(v=3, col=lightgray) text(3, 3.5, expression( paste(Areas (, mu * m^2, ), sep =))) text(3, 3.0, expression( paste(Areas (, mu * m^2, ), sep = ))) text(3, 2.5, expression( paste(Areas (, mu * m^2, ), ))) Peter Ehlers HTH, Dennis On Thu, Feb 10, 2011 at 4:32 PM, Lizbliphome-sick_al...@hotmail.comwrote: Duncan Murdoch-2 wrote: There is no plotmath function. plotmath is the name of the help topic; it describes how various other functions plot text that includes math. grDevices is a base package, so if you've got R, you've got it. Duncan Murdoch ok thanks. I originally thought this was the case and first tried: plot(areas~cell,ylab=expression(Areas (mu*m^2)) but the text wasn't re-formatted so I thought plotmath must be a separate function. How is it supposed to work? -- View this message in context: http://r.789695.n4.nabble.com/Where-can-I-download-install-grDevices-tp2401415p3300559.html Sent from the R help mailing list archive at Nabble.com. __ 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. [[alternative HTML version deleted]] __ 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. __ 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.
Re: [R] Writing R packages in an easier way?
On 11.02.2011 13:38, S Ellison wrote:
Dr. Michael Wolfm-w...@muenster.de 11/02/2011 07:52
is there an easier way to write R packages for the own use - without
RTools and TeX?
Installing Rtools is not hard, and doesn't have to happen often; the
hardest bit in Windows is making sure that the requisite executables are
on the path, and that just involves adding the directory names to the
path environment variable. If I understand you, the problem is the time
spent hacking about in the .Rd help files. That can certainly be
simplified - eliminated, in fact.
Use package.skeleton() once you have a good starting set of functions
and data in R. That creates all the necessary directories, creates
skeleton (but valid) .Rd files, and exports your functions and data
objects for you. You can then edit the code directly, use RCMD check to
check the package (useful anyway) and use RCMD build to build it. (In
fact if all you want is the zip, you can - or at least could - zip the
package directory created by RCMD check).
Actually, just say
R CMD INSTALL --build package
which will generate the zip in a supported way.
Uwe Ligges
S Ellison
***
This email and any attachments are confidential. Any use...{{dropped:8}}
__
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.
__
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.
Re: [R] Calling symbols from dataframe for xyplot
The more common way to do this is to use groups, the default is to have a
different color for each group, but you can change that using trellis.par.set:
tmp - trellis.par.get()
tmp$superpose.symbol$pch = 0:10
trellis.par.set(tmp)
xyplot(Sepal.Width ~ Petal.Width, data=iris, groups=Species, auto.key=TRUE)
If you need more control of the symbols than that, then look at the
panel.my.symbols function in the TeachingDemos package.
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.s...@imail.org
801.408.8111
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-bounces@r-
project.org] On Behalf Of John Poulsen
Sent: Thursday, February 10, 2011 2:22 PM
To: r-help@r-project.org
Subject: [R] Calling symbols from dataframe for xyplot
Hello,
I am trying to make a xyplot plot with points that are different
symbols. I want to call the symbol type (pch) from a column in my
dataframe. Here is a simplified example. In my real example I also
have groups, which I have not included here. This example doesn't
change the symbols or colors.
Any help you can provide would be appreciated.
Thanks,
John
x-c(1:12)
y-c(rpois(12,4))
grp-c(rep(c(3,4), each=6))
z-c(rep(c(1,2), each=6))
p-rep(1:3,4)
xyplot(y~x|z, cex=1.2,
panel=function(x,y,...){
panel.xyplot(x,y,...)
pch=p
fill=list(black,blue)})
[[alternative HTML version deleted]]
__
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.
__
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.
Re: [R] foreach with registerDoMC on R 2.12.0 OSX 10.6 --- errors and warnings
Are you using doMC within the Mac GUI or from the Terminal? The doMC package doesn't work within the GUI, you need to run R directly from the command line. # David Smith On Fri, Feb 11, 2011 at 8:56 AM, ivo welch ivo...@gmail.com wrote: some hints for the search engines. I just did install.packages(foreach) install.packages(doMC) library(doMC) registerDoMC() library(foreach) foreach(i = 1:3) %dopar% sqrt(i) The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__() to debug. Tcl_ServiceModeHook: Notifier not initialized [[1]] NULL [[2]] [1] 1.414 [[3]] [1] 1.732 The first element is obviously wrong, and the warning messages are scary. Restarting R eliminated all the problems. This seems to be something odd about the install and load process. __ 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. -- David M Smith da...@revolutionanalytics.com VP of Marketing, Revolution Analytics http://blog.revolutionanalytics.com Tel: +1 (650) 646-9523 (Palo Alto, CA, USA) __ 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.
Re: [R] Writing R packages in an easier way?
Dear collegues,
thanks for your helpfull and persuasive comments. I see that all of you propose
to work with the official method building R packages. The code of importing
functions which Barry Rowlingson posted to the forum is very interesting and
perhaps I can use this for solving other problems.
I'm thinking about a monitoring project with R in the center of my working.
Therefore I need help files for describing my programming code.
In the consequence of this I have to accept that using the official R way of
writing a package will be the best in the long run - even it will take some time
to me especially to write the help files. SO I will reactivate my RTools and TeX!
Best regards
Dr. Michael Wolf
(m-w...@muenster.de)
Am 11.02.2011 18:49, schrieb Uwe Ligges:
On 11.02.2011 13:38, S Ellison wrote:
Dr. Michael Wolfm-w...@muenster.de 11/02/2011 07:52
is there an easier way to write R packages for the own use - without
RTools and TeX?
Installing Rtools is not hard, and doesn't have to happen often; the
hardest bit in Windows is making sure that the requisite executables are
on the path, and that just involves adding the directory names to the
path environment variable. If I understand you, the problem is the time
spent hacking about in the .Rd help files. That can certainly be
simplified - eliminated, in fact.
Use package.skeleton() once you have a good starting set of functions
and data in R. That creates all the necessary directories, creates
skeleton (but valid) .Rd files, and exports your functions and data
objects for you. You can then edit the code directly, use RCMD check to
check the package (useful anyway) and use RCMD build to build it. (In
fact if all you want is the zip, you can - or at least could - zip the
package directory created by RCMD check).
Actually, just say
R CMD INSTALL --build package
which will generate the zip in a supported way.
Uwe Ligges
S Ellison
***
This email and any attachments are confidential. Any use...{{dropped:8}}
__
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.
__
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.
Re: [R] When is *interactive* data visualization useful to use?
Dear Tal, dear list, I think the importance of interactive graphics has a lot do with how visual your scientific discipline works. I'm spectroscopist, and I think we are very visually oriented: if I think of a spectrum I mentally see a graph. So for that kind of work, I need a lot of interaction (type: plot, change a bit, plot again), e.g. One example is the removal of spikes from Raman spectra (caused e.g. by cosmic rays hitting the detector). It is fairly easy to compute a list of suspicious signals. It is already much more complicated to find the actual beginning and end of the spike. And it is really difficult not to have false positives by some automatic procedure, because the spectra can look very different for different samples. It would just take me far longer to find a computational description of what is a spike than interactively accepting/rejecting the automatically marked suspicions. Even though it feels like slave work ;-) Roughly the same applies for the choice of pre-processing like baseline correction. A number of different physical causes can produce different kinds of baselines, and usually you don't know which process contributes to what extent. In practice, experience suggests a method, I apply it and look whether the result looks as expected. I'm not aware of any performance measure that would indicate success here. The next point where interaction is needed pops up as my data has e.g. spatial and spectral dimensions. So do the models usually: e.g. in a PCA, the loadings would usually capture the spectroscopic direction, whereas the scores belong to the spatial domain. So I have connected graphs: the spatial distribution (intensity map, score map, etc.), and the spectra (or loadings). As soon as I have such connections I wish for interactive visualization: I go back and forth between the plots: what is the spectrum that belongs to this region of the map? Where on the sample are high intensities of this band? What is the substance behind that: if it is x, the intensities at that other spectral band should correlate. And then I want to compare this to the scatterplot (pairs plot of the PCA score) or to a dendrogram of HCA... Also, exploration is not just prerequisite for models, but it frequently is already the very proper scientific work (particularly in basic science). The more so, if you include exploring the models: Now, which of the bands are actually used by my predictive models? Which samples do get their predictions because of which spectral feature? And, the statistical outliers may very well be just the interesting part of the sample. And the outlier statistics cannot interprete the data in terms of interesting ./. crap. For presentation* of results, I personally think that most of the time a careful selection of static graphs is much better than live interaction. *The thing where you talk to an audience far awayf from your work computer. As opposed to sitting down with your client/colleague and analysing the data together. It could be argued that the interactive part is good for exploring (For example) a different behavior of different groups/clusters in the data. But when (in practice) I approached such situation, what I tended to do was to run the relevant statistical procedures (and post-hoc tests) As long as the relevant measure exists, sure. Yet as a non-statistician, my work is focused on the physical/chemical interpretation. Summary statistics are one set of tools for me, and interactive visualisation is another set of tools (overlapping though). I may want to subtract the influence of the overall unchanging sample matrix (that would be the minimal intensity for each wavelength). But the minimum spectrum is too noisy. So I use a quantile. Which one? Depends on the data. I'll have a look at a series (say, the 2nd to 10th percentile) and decide trading off noise and whether any new signals appear. I honestly think there's nothing gained if I sit down and try to write a function scoring the similarity to the minimum spectrum and the noise level: the more so as it just shifts the need for a decision (How much noise outweighs what intensity of real signal being subtracted?). It is a decision I need to take. With number or with eye. And after all, my professional training was thought to enable me taking this decision, and I'm paid (also) for being able to take this decision efficiently (i.e. making a reasonably good choice within not too long time). After all, it may also have to do with a complaint a colleague from a computational data analysis group once had. He said the bad thing with us spectroscopists is that our problems are either so easy that there's no fun in solving them, or they are too hard to solve. - and what I found to be significant I would then plot with colors clearly dividing the data to the relevant groups. From what I've seen, this is a safer approach then wondering around the data
Re: [R] Writing R packages in an easier way?
On Fri, Feb 11, 2011 at 7:38 AM, S Ellison s.elli...@lgc.co.uk wrote: Dr. Michael Wolf m-w...@muenster.de 11/02/2011 07:52 is there an easier way to write R packages for the own use - without RTools and TeX? Installing Rtools is not hard, and doesn't have to happen often; the hardest bit in Windows is making sure that the requisite executables are on the path, and that just involves adding the directory names to the path environment variable. If I understand you, the problem is the time Also you can avoid setting environment variables for R by grabbing Rcmd.bat from http://batchfiles.googlecode.com and placing it anywhere on your path -- note: entering the one word, path, from the Windows cmd line shows you your path. Rcmd.bat looks up R in the registry and then passes its arguments to the real Rcmd. -- Statistics Software Consulting GKX Group, GKX Associates Inc. tel: 1-877-GKX-GROUP email: ggrothendieck at gmail.com __ 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.
Re: [R] Writing R packages in an easier way?
Hi,
Another option is to go ahead and make the package structure you're
used to, but try to load and use it via Hadley's devtools package,
instead of installing it for use.
It might do the trick for you:
https://github.com/hadley/devtools
-steve
On Fri, Feb 11, 2011 at 2:14 PM, Dr. Michael Wolf m-w...@muenster.de wrote:
Dear collegues,
thanks for your helpfull and persuasive comments. I see that all of you
propose to work with the official method building R packages. The code of
importing functions which Barry Rowlingson posted to the forum is very
interesting and perhaps I can use this for solving other problems.
I'm thinking about a monitoring project with R in the center of my working.
Therefore I need help files for describing my programming code.
In the consequence of this I have to accept that using the official R way of
writing a package will be the best in the long run - even it will take some
time to me especially to write the help files. SO I will reactivate my
RTools and TeX!
Best regards
Dr. Michael Wolf
(m-w...@muenster.de)
Am 11.02.2011 18:49, schrieb Uwe Ligges:
On 11.02.2011 13:38, S Ellison wrote:
Dr. Michael Wolfm-w...@muenster.de 11/02/2011 07:52
is there an easier way to write R packages for the own use - without
RTools and TeX?
Installing Rtools is not hard, and doesn't have to happen often; the
hardest bit in Windows is making sure that the requisite executables are
on the path, and that just involves adding the directory names to the
path environment variable. If I understand you, the problem is the time
spent hacking about in the .Rd help files. That can certainly be
simplified - eliminated, in fact.
Use package.skeleton() once you have a good starting set of functions
and data in R. That creates all the necessary directories, creates
skeleton (but valid) .Rd files, and exports your functions and data
objects for you. You can then edit the code directly, use RCMD check to
check the package (useful anyway) and use RCMD build to build it. (In
fact if all you want is the zip, you can - or at least could - zip the
package directory created by RCMD check).
Actually, just say
R CMD INSTALL --build package
which will generate the zip in a supported way.
Uwe Ligges
S Ellison
***
This email and any attachments are confidential. Any use...{{dropped:8}}
__
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.
__
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.
--
Steve Lianoglou
Graduate Student: Computational Systems Biology
| Memorial Sloan-Kettering Cancer Center
| Weill Medical College of Cornell University
Contact Info: http://cbio.mskcc.org/~lianos/contact
__
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.
Re: [R] Getting p-value from summary output
Awesome! Thanks so much! On Thu, Feb 10, 2011 at 6:13 PM, Dennis Murphy djmu...@gmail.com wrote: Hi: Try summary(myprobit)$coefficients[, 4] HTH, Dennis On Thu, Feb 10, 2011 at 3:46 PM, Allie818 alice...@gmail.com wrote: I can get this summary of a model that I am running: summary(myprobit) Call: glm(formula = Response_Slot ~ trial_no, family = binomial(link = probit), data = neg_data, na.action = na.pass) Deviance Residuals: Min 1Q Median 3Q Max -0.9528 -0.8934 -0.8418 1.4420 1.6026 Coefficients: Estimate Std. Error z value Pr(|z|) (Intercept) -0.340528 0.371201 -0.9170.359 trial_no-0.005032 0.012809 -0.3930.694 (Dispersion parameter for binomial family taken to be 1) Null deviance: 62.687 on 49 degrees of freedom Residual deviance: 62.530 on 48 degrees of freedom AIC: 66.53 Number of Fisher Scoring iterations: 4 But I would like to get the p-value [column heading Pr(|z|)] for the esimate. I can get the coefficient estimates with myprobit$coefficients. Is there something similar to get the p-value? Thank you in advance. -- View this message in context: http://r.789695.n4.nabble.com/Getting-p-value-from-summary-output-tp3300503p3300503.html Sent from the R help mailing list archive at Nabble.com. __ 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. [[alternative HTML version deleted]] __ 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.
[R] linear models with factors
i am trying to fit a linear model with both continuous covariates and factors. When fitted with the intercept term the first level of the factor is treated by R as intercept and the estimate of the effects of remaining levels(say i th level) are given as true estimate of i th level - estimate of 1st level.can any please help me? thanks in advance. -- View this message in context: http://r.789695.n4.nabble.com/linear-models-with-factors-tp3301811p3301811.html Sent from the R help mailing list archive at Nabble.com. __ 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.
[R] take my name from the list
How I can take out my name from this list? Fernanda Melo Carneiro contato: (62) 3521-1480 e 8121-7374www.ecoevol.ufg.br Laboratório de Ecologia Teórica e Síntese (UFG) [[alternative HTML version deleted]] __ 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.
Re: [R] Revolution Analytics reading SAS datasets
If you have SAS, You can read Dr. Harrell's page: http://biostat.mc.vanderbilt.edu/wiki/Main/SASexportHowto if not, you can take a look on WPS: http://www.teamwpc.co.uk/products On Fri, 2011-02-11 at 10:32 -0600, Chao(Charlie) Huang wrote: I am right now using Revolution R Enterprise 4.2. Could somebody show me how to import/export SAS datasets. Thanks. -- Gong-Yi Liao Department of Statistics University of Connecticut 215 Glenbrook Road U4120 Storrs, CT 06269-4120 860-486-9478 __ 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.
[R] Package distr and define your own distribution
Hi all
I am using the Package distr (and related)
Do you know if it is possible to define your own distribution (object)
GIVEN that you have an analytical form of the probability density
function (pdf) ?
I would then like to use the standard feature of the distr and related
packages.
Best regards
Giuseppe Gabriel Cardi
Visit our website at http://www.ubs.com
This message contains confidential information and is in...{{dropped:21}}
__
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.
[R] About classification methods.
Dear R users, I'm new of the R, I really don't know much. I want classification some data (two class, many features and huge size of data) by using R. At this case, I want using Support Vector Machine, Bayes theory based classifier, Discriminant Analysis, Regression based at least. Which package should I using, and can I compare each classifier result by predictions? Thank you. __ 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.
Re: [R] Need help merging two dataframes
## i didn't try this, but I would think it would work newAB -data.frame(AB$id, AB$age, AB$sex, AB$area) colnames(newAB)-c(id,age, sex, area) uni.newAB - unique(newAB) t3-merge(t2, uni.newAB, by=id, all=FALSE) -- View this message in context: http://r.789695.n4.nabble.com/Need-help-merging-two-dataframes-tp3297313p3301627.html Sent from the R help mailing list archive at Nabble.com. __ 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.
[R] problem with installing packages
Dear: I am recnetly trying to install some libraries. However, I found this issue for both my laptop and desktop even I uninstall and install it again. I even can not update the R now. I wonder if you have the similar issue. Thakns! Xin chooseCRANmirror() Warning message: In open.connection(con, r) : unable to connect to 'cran.r-project.org' on port 80. setRepositories() utils:::menuInstallPkgs() Warning: unable to access index for repository http://www.stats.bris.ac.uk/R/bin/windows/contrib/2.12 Warning: unable to access index for repository http://www.stats.ox.ac.uk/pub/RWin/bin/windows/contrib/2.12 Error in install.packages(NULL, .libPaths()[1L], dependencies = NA, type = type) : no packages were specified [[alternative HTML version deleted]] __ 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.
Re: [R] How can we make a vector call a function element-wise efficiently?
Dear Eik What a great idea!!! Thank you so much for your colossal improvment Yes, you have a unique eye on the numerical problem, I am worrying about this problem right now, hope you could give me new idea again Hi, you compute the same results for logx many times. So it is easier and time saving tabulating all intermediate results. smth. like n-10 CT=6000 #assignment to CT NT=29535210 #assignment to NT i - 0:(n-1) lookup- lchoose(NT-n, CT-i) + lchoose(n, i) lgmax-cummax(lookup) calsta2-function(c) lgmax[c] + log(sum(exp(lookup[1:c] - lgmax[c]))) should help for a start, but I think, you are running into numerical troubles, since you are dealing with very high and low (on log scale) numbers and calsta constantly returns 57003.6 for c38 (the summands in sum(exp(logx - logmax)) will become 0 for c38). #check sapply(1:50,calsta2) sapply(1:50,calsta) hth Yours sincerely ZhaoXing Department of Health Statistics West China School of Public Health Sichuan University No.17 Section 3, South Renmin Road Chengdu, Sichuan 610041 P.R.China [[alternative HTML version deleted]] __ 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.
Re: [R] Tinn R
Hi Dieter, It works for me. Thanks Karen -- View this message in context: http://r.789695.n4.nabble.com/Tinn-R-tp878805p3301466.html Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]] __ 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.
Re: [R] cycle in a directed graph
If the graph has n nodes and is represented by an adjacency matrix, you can square the matrix (log_2 n)+1 times. Then you can multiply the matrix element-wise by its transpose. The positive entries in the 7th row will tell you all nodes sharing a cycle with node 7. This assumes all edge weights are positive. Are you sure we're not doing your graph theory homework? You asked about MSTs yesterday. -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of amir Sent: Friday, February 11, 2011 10:11 AM To: r-help@r-project.org Subject: [R] cycle in a directed graph Hi, I have a directed graph and wants to find is there any cycle in it? If it is, which nodes or edges are in the cycle. Is there any way to find the cycle in a directed graph in R? Regards, Amir __ 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. message may contain confidential information. If you are not the designated recipient, please notify the sender immediately, and delete the original and any copies. Any use of the message by you is prohibited. __ 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.
Re: [R] take my name from the list
On Feb 11, 2011, at 7:25 AM, Fernanda Melo Carneiro wrote: How I can take out my name from this list? Please read the information on the page where you signed up. Fernanda Melo Carneiro contato: (62) 3521-1480 e 8121-7374www.ecoevol.ufg.br Laboratório de Ecologia Teórica e Síntese (UFG) -- David Winsemius, MD West Hartford, CT __ 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.
Re: [R] take my name from the list
See the link at the bottom of every message sent to this list... -Ista On Fri, Feb 11, 2011 at 7:25 AM, Fernanda Melo Carneiro fermelcar2...@yahoo.com.br wrote: How I can take out my name from this list? Fernanda Melo Carneiro contato: (62) 3521-1480 e 8121-7374www.ecoevol.ufg.br Laboratório de Ecologia Teórica e Síntese (UFG) [[alternative HTML version deleted]] __ 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. -- Ista Zahn Graduate student University of Rochester Department of Clinical and Social Psychology http://yourpsyche.org __ 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.
Re: [R] take my name from the list
The answer to that question appears on each and every message to the list, including this one. But for your convenience: https://stat.ethz.ch/mailman/listinfo/r-help On Fri, Feb 11, 2011 at 7:25 AM, Fernanda Melo Carneiro fermelcar2...@yahoo.com.br wrote: How I can take out my name from this list? -- Sarah Goslee http://www.functionaldiversity.org __ 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.
Re: [R] take my name from the list
There is a link at the bottom of every email sent from this list: https://stat.ethz.ch/mailman/listinfo/r-help Go there, scroll to the bottom of page, and follow the unsubscribe instructions. On Fri, Feb 11, 2011 at 7:25 AM, Fernanda Melo Carneiro fermelcar2...@yahoo.com.br wrote: How I can take out my name from this list? Fernanda Melo Carneiro contato: (62) 3521-1480 e 8121-7374www.ecoevol.ufg.br Laboratório de Ecologia Teórica e Síntese (UFG) [[alternative HTML version deleted]] __ 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. -- Steve Lianoglou Graduate Student: Computational Systems Biology | Memorial Sloan-Kettering Cancer Center | Weill Medical College of Cornell University Contact Info: http://cbio.mskcc.org/~lianos/contact __ 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.
Re: [R] linear models with factors
I don't see any question here, other than can you please help me. Since long-awaited esp package has still not been released, you're going to have to be more specific than that... Best, Ista On Fri, Feb 11, 2011 at 2:05 PM, ATANU ata.s...@gmail.com wrote: i am trying to fit a linear model with both continuous covariates and factors. When fitted with the intercept term the first level of the factor is treated by R as intercept and the estimate of the effects of remaining levels(say i th level) are given as true estimate of i th level - estimate of 1st level.can any please help me? thanks in advance. -- View this message in context: http://r.789695.n4.nabble.com/linear-models-with-factors-tp3301811p3301811.html Sent from the R help mailing list archive at Nabble.com. __ 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. -- Ista Zahn Graduate student University of Rochester Department of Clinical and Social Psychology http://yourpsyche.org __ 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.
Re: [R] About classification methods.
On Feb 11, 2011, at 1:36 PM, Jaeik Cho wrote: Dear R users, I'm new of the R, I really don't know much. I want classification some data (two class, many features and huge size of data) by using R. At this case, I want using Support Vector Machine, Bayes theory based classifier, Discriminant Analysis, Regression based at least. http://cran.r-project.org/web/views/MachineLearning.html http://cran.r-project.org/web/views/Multivariate.html Which package should I using, and can I compare each classifier result by predictions? Thank you. __ 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. David Winsemius, MD West Hartford, CT __ 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.
Re: [R] About classification methods.
Which package should I using, and can I compare each classifier result by predictions? By prediction on the training data, emphastically no. By prediction on new data not used for training, yes. -- Bert __ 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.
[R] [R-pkgs] adehabitatMA, LT, HR and HS version 0.1
Dear all, I have just uploaded 4 new packages on CRAN, which are on the long term designed to replace the old package adehabitat: * adehabitatMA: functions to perform spatial operations (morphology, buffer, etc.) * adehabitatHS: functions for the analysis of habitat selection by wildlife * adehabitatHR: functions for home range estimation of animals * adehabitatLT: functions for animal movement analysis I will still continue to maintain the old adehabitat, but on the long-term, adehabitat will be replaced by these four packages. Detailed justification for the development of these packages is given below. == The R environment has changed a lot since I began the development of adehabitat in 2002 (development of namespace, etc.), and new classes and efficient methods have been developed to deal with spatial data (package sp). In addition, the number of functions available in the package has grown to more than 250 functions, implementing methods for habitat selection analysis, home range estimation, animal movement analysis, or spatial operations. Therefore, I decided to: (i) rewrite the package adehabitat to make it more compliant with these evolutions of the package R, (ii) split adehabitat into four packages The four new packages are: * adehabitatMA: functions to perform spatial operations (morphology, buffer, etc.) * adehabitatHS: functions for the analysis of habitat selection * adehabitatHR: functions for home range estimation * adehabitatLT: functions for movement analysis I will continue to maintain the old adehabitat on CRAN for some time, but on the long term, this package will disappear. These four packages are expected to become the future of adehabitat. I now describe several major changes: * the functions of the packages are documented precisely in a vignette (there is one vignette per package). Both their use and the theory underlying these functions are described there. To access it, type: vignette(packagename) * the home range estimation methods have been homogenized and return classes compliant with the classes of the package sp: - the functions kernelUD, kernelbb, BRB and kernelkc all return objects of class estUDm, which are lists of objects of class estUD. The class estUD extends the class SpatialPixelsDataFrame. - the function clusthr and LoCoH return objects of class MCHu, which are lists of SpatialPolygonsDataFrame - the function mcp returns a SpatialPolygonsDataFrame * home range estimation methods now take objects of class SpatialPoints as arguments * objects of class ltraj are now characterized by an additional attribute infolocs, which is designed to store metadata on the trajectories (e.g. precision on the relocations). Most functions of the package adehabitatLT can be used to analyse these metadata (plotltr, etc. see the vignette). * the method of characteristic hulls (Downs and Horner 2009), suggested by Paolo Cavallini, on the list has been added to adehabitatHR, and returns an object of class MCHu * the method of biased random bridges (Benhamou, 2011) has be added to adehabitatHR, to estimate the utilization distribution from a trajectory. * the canonical OMI analysis, allowing exploration of habitat selection with radio-tracking data, has been added to the package adehabitatHS * the autocorrelation functions described by Dray et al. (2010) for the analysis of movement have been added to the package adehabitatLT; * the function rasterize.ltraj allows to rasterize a trajectory (i.e. useful to identify the habitat characteristics of the steps building the trajectory) * all the packages have a namespace for management of internal functions. * Two additional functions dl and ld to convert efficiently the class ltraj to and from data frames (thanks to Mathieu Basille for the suggestion). Note that the calculations performed by most functions of adehabitat have not changed (e.g. the algorithm implemented in kernelUD of adehabitat is the same as the algorithm implemented in the function kernelUD of the package adehabitatHR), since they have been deeply discussed with users and corrected during the last six years. Only the input and output of the functions have been changed. = Happy testing, Clément Calenge -- Clément CALENGE Cellule d'appui à l'analyse de données Direction des Etudes et de la Recherche Office national de la chasse et de la faune sauvage Saint Benoist - 78610 Auffargis tel. (33) 01.30.46.54.14 ___ R-packages mailing list r-packa...@r-project.org https://stat.ethz.ch/mailman/listinfo/r-packages __ 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
[R] [R-pkgs] ez version 3.0
Hi folks, I'd like to announce the release of version 3.0 of the ez package. This package was developed to aid those that are new to statistical programming. Over the course of several years of helping colleagues and students learn R, I observed that folks are often initially turned off R because they have difficulty obtaining SPSS-like results quickly (SPSS is the dominant environment in my field, psychology). ez attempts to fill this gap, providing quick and easy analysis and graphics for common experimental designs. By easing the early portions of the R learning curve, ez hopes to promote the spread of R as a means of open source and reproducible analysis. ez may also be of interest to more advanced users as it includes the ezMixed() function, which automates the assessment of fixed effects in a mixed effects modelling context, and the ezPredict() function, which obtains predictions for the fixed effects from a mixed effects model. Installing ez Version 3.0 of ez requires that you have R 2.12.1 installed, which is the latest version of R as of this notice. If you have an older version of R you will need to update R by installing the latest version (from http://cran.r-project.org/) before installing ez. Windows and linux users should be able to install the latest version by running the command: install.packages( 'ez' ) Mac users should be able to install the latest version by running the commands: install.packages( c( 'car' , 'reshape2' , 'plyr' , 'ggplot2' , 'stringr' , 'lme4' , 'Matrix' ) ) install.packages( 'ez' , type='source' , dependencies=F ) Once installed, running the following commands will load ez and bring up its help page that links to descriptions of all ez's functions: library( ez ) ?ez Big changes in version 3.0 - A big rework of ezANOVA() to permit more flexibility, including more nuanced handling of numeric predictor variables, specification of sums-of-squares types when data is imbalanced, and an option to compute/return an aov object representing the requested ANOVA for follow-up contrast analysis. (The latter two features follow from the discussion at http://stats.stackexchange.com/questions/6208/should-i-include-an-argument-to-request-type-iii-sums-of-squares-in-ezanova) - An important bugfix for ezMixed(), which previously permitted specification of multiple random effects but silently ignored all but the last! - A big rework of ezMixed(), completely changing the output (including removal of p-values following advice of Pinero Bates, 2000, and many on the R-SIG-Mixed-Models mailing list) and providing a new feature whereby the linearity of numeric fixed effects can be assessed by comparison to higher polynomial degrees. Also new As noted above, this version fixes a big bug in ezMixed() about which I wish I could have warned users sooner. To facilitate future rapid notification of users, I've created a discussion group (http://groups.google.com/group/ez4r) to which users can/should subscribe to keep up to date on development news. Additionally, I created a project page on github (https://github.com/mike-lawrence/ez/issues) where users can submit bug reports and feature requests. Finally, I encourage users to rate or review ez (and any other packages you use) at crantastic.org (http://crantastic.org/packages/ez). Official CHANGES entry 3.0-0 - added urls in all documentation pointing to the bug-report/feature-request site (https://github.com/mike-lawrence/ez/issues) and the discussion group (http://groups.google.com/group/ez4r). - changed reshape dependency to reshape2 - ezANOVA - fixed bug such that if detailed=F and car:Anova fails, the first line of results from stats:aov is cut off. - Added more nuanced treatment of numeric variables - Added type argument to specify sums-of-squares type selection (1,2, or 3) - Added white.adjust argument to permit heteroscedasticity adjustment (see ?car::Anova) - Added return_aov argument to permit returning a stats:aov object along with results (this was requested by a user seeking to use the aov object to compute contrasts) - ezMixed - IMPORTANT: Fixed bug such that only the last specified random effect was implemented - fixed bug such that an error occurred if only one fixed effect was specified - changed output format to a list containing a summary data frame, a list of formulae, a list of errors, a list of warnings, and (optionally) a list of fitted models - Changed format of summary output including removal of p-values (on the strong advice of many that the p-values from a likelihood ratio test of a fixed effect is highly questionable) - removed the return_anovas argument - added nuanced ability to explore non-linear effects via addition of fixed_poly and fixed_poly_max arguments - ezPredict - Added ability to handle models fit with I()'d variables - Added stop error when encountering models with poly() and no supplied prediction data
[R] R for mac, default load package.
Dear R users, I'm looking for solution about how can I add a package to default load package list. Because, some packages, every time I use the package for analysis. I don't want type load(package) every time. On the R instruction, I should change .Rprofile file, but I couldn't find R for Mac. How can I add default load package? Jaeik Cho__ 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.
[R] Fwd: About classification methods.
I mean, after done for the testing step, I want show which data classified to wrong class. That predictions. Jaeik Begin forwarded message: From: Bert Gunter gunter.ber...@gene.com Date: February 11, 2011 3:00:47 PM CST To: David Winsemius dwinsem...@comcast.net Cc: Jaeik Cho choja...@gmail.com, r-help@r-project.org Subject: Re: [R] About classification methods. Which package should I using, and can I compare each classifier result by predictions? By prediction on the training data, emphastically no. By prediction on new data not used for training, yes. -- Bert __ 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.
[R] Summarizing a response variable based on an irregular time period
Hello, I have a question about working with dates in R. I would like to summarize a response variable based on a designated and irregular time period. The purpose of this is to compare the summarized values (which were sampled daily) to another variable that was sampled less frequently. Below is a trivial example where I would like to summarize the response variable dat$x such that I have average and sum values from Sept25-27 and Sept28-Oct1. Can anyone suggest an efficient way to deal with dates like this? As an extremely tedious previous effort, I simply created another grouping variable but I had to do this manually. For a large dataset this really isn't a good option. Thanks in advance! Sam library(plyr) dat - data.frame(x = runif(6, 0, 125), date = as.Date(c(2009-09-25,2009-09-26,2009-09-27,2009-09-28,2009-09-29,2009-09-30,2009-10-01), format=%Y-%m-%d), yy = letters[1:2], stringsAsFactors = TRUE) #If I was using a regular factor, I would do something like this and this is what I would be hoping for as a result (obviously switching yy for date as the grouping variable) ddply(dat, c(yy), function(df) return(c(avg=mean(df$x), sum=sum(df$x #This is the data.frame that I would like to compare to dat. dat2 - data.frame(y = runif(2, 0, 125), date = as.Date(c(2009-09-27,2009-10-01), format=%Y-%m-%d)) -- * Sam Albers Geography Program University of Northern British Columbia University Way Prince George, British Columbia Canada, V2N 4Z9 phone: 250 960-6777 * [[alternative HTML version deleted]] __ 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.
Re: [R] Rioja package, creating transfer function, WA, Error in FUN
Dear Peter, Thank you very much for your suggestion, I went through the matrices and removed the headings for pH, WTD etc and did the same for the site names, which I made purely numerical, and now the WA function is working, Thanks again! Matthew On Fri, Feb 11, 2011 at 12:44 AM, Peter Ehlers [via R] ml-node+3300569-1208751190-212...@n4.nabble.com wrote: On 2011-02-10 09:40, mdc wrote: Hi, I am a new R user and am trying to construct a palaeoenvironmental transfer function (weighted averaging method) using the package rioja. I've managed to insert the two matrices (the species abundance and the environmental data) and have assigned them to the y and x values respectively. When I try and enter the 'WA' function though, I get an 'Error in FUN' message (see below for full values). Alas, I do not know what this means and have struggled to find similar problems to this online. Is there a step I've missed out between assigning the matrices and the WA function? SWED=odbcConnectExcel(file.choose()) (SWED is the environmental data file) sqlTables(SWED) Env=sqlFetch(SWED, Sheet1) odbcClose(SWED) Env SampleId WTD Moisture pH EC 1 N1_1 20 91.72700 3.496674 85.02688 2 N1_22 93.88913 3.550794 85.69465 3 N1_3 26 90.30269 3.948559 113.19206 4 N1_45 94.14427 3.697213 48.56375 5 N1_5 30 90.04269 3.745020 108.57278 90 GAL_15 70 94.07849 3.777932 66.77673 STEST=odbcConnectExcel(file.choose()) sqlTables(STEST) (STEST is the species abundance file) Spe=sqlFetch(STEST, Sheet8) odbcClose(STEST) Spe (The species data contains the abundance of 32 species over 90 sites, set out like this) F1AmpFlavAmpWri ArcCat ArcDis 1N1_1 22.2929936 0.000 0.000 0.000 2N1_2 30.9677419 0.000 0.000 3.2258065 library(rioja) y-as.matrix(Spe) x-as.matrix(Env) WA(y, x, tolDW = FALSE, use.N2=TRUE, check.data=TRUE, lean=FALSE) (the command from the WA section of the rioja booklet) Error in FUN(newX[, i], ...) : invalid 'type' (character) of argument Well, the error message is fairly clear: you're feeding in something of type 'character' where something else (presumably) numeric is wanted. I don't use rioja, but a quick glance at the documentation for WA shows that x should be 'a vector of environmental values to be modelled'. The example uses pH which is almost surely not a character vector. Your x is a *matrix* of *character* values. Possibly, you want to pull, say, pH out of your Env, convert to numeric and try that. Ditto for the other variables. If the above is total nonsense, please forgive my rioja ignorance and wait for more cogent advice from someone more knowledgeable than I. Peter Ehlers Any help would be most appreciated, Best wishes, Matthew __ [hidden email] http://user/SendEmail.jtp?type=nodenode=3300569i=0mailing 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. -- If you reply to this email, your message will be added to the discussion below: http://r.789695.n4.nabble.com/Rioja-package-creating-transfer-function-WA-Error-in-FUN-tp3299636p3300569.html To unsubscribe from Rioja package, creating transfer function, WA, Error in FUN, click herehttp://r.789695.n4.nabble.com/template/NamlServlet.jtp?macro=unsubscribe_by_codenode=3299636code=bWF0dC5kLmNvZUBnbWFpbC5jb218MzI5OTYzNnwyMDMzMDk2ODg2. -- View this message in context: http://r.789695.n4.nabble.com/Rioja-package-creating-transfer-function-WA-Error-in-FUN-tp3299636p3302063.html Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]] __ 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.
Re: [R] R for mac, default load package.
Hi, On Fri, Feb 11, 2011 at 3:21 PM, Jaeik Cho choja...@gmail.com wrote: Dear R users, I'm looking for solution about how can I add a package to default load package list. Because, some packages, every time I use the package for analysis. I don't want type load(package) every time. On the R instruction, I should change .Rprofile file, but I couldn't find R for Mac. How can I add default load package? The file to add your `library(whatever)` line to is ~/.Rprofile ~ is shorthand for your home directory, which is /Users/YOUR_SHORT_LOGIN_NAME on OS X. -- Steve Lianoglou Graduate Student: Computational Systems Biology | Memorial Sloan-Kettering Cancer Center | Weill Medical College of Cornell University Contact Info: http://cbio.mskcc.org/~lianos/contact __ 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.
[R] [R-pkgs] Update: googleVis 0.2.4 - Using the Google Visualisation API with R
Hi all, Version 0.2.4 of the googVis package has been released on CRAN and will be available from your local CRAN mirror soon. googleVis provides an interface between R and the Google Visualisation API. The functions of the package allow users to visualise data stored in R with the Google Visualisation API without uploading their data to Google Since the last version a lot of work has been carried out under the bonnet to make googleVis more flexible and easier to use. The new version no longer requires to install the package into a folder with access rights and provides a better interface to insert the visualisation output into your own sites. For more information see: Project site: http://code.google.com/p/google-motion-charts-with-r/ Overview: http://google-motion-charts-with-r.googlecode.com/files/GoogleVisOverview_0.2.4.pdf Examples: http://code.google.com/p/google-motion-charts-with-r/wiki/GadgetExamples Vignette: http://cran.r-project.org/web/packages/googleVis/vignettes/googleVis.pdf And here are the NEWS: Version 0.2.4 [2011-02-07] == Changes o plot.gvis no longer writes into the package folder. Instead temporary files are created. This overcomes the need to install the package into a directory with write access. Many thanks to Ben Bolker for this suggestion and code contribution. o plot.gvis no longer requires the web server provided by the R.rsp package to display the visualisation output. Instead it uses the internal R HTTP help server. Many thanks to John Verzani for this suggestion and code contribution. o R = 2.11.0 is required to plot googleVis output, as it uses the internal R HTTP help server. o Updated vignette with a section on how to use googleVis with RApache and brew NEW FEATURES o The plot function generates a web page which includes a link to the HTML code of the chart. Many thanks to Henrik Bengtsson for this suggestion. o gvis visualisation functions have a new argument 'chart id', to set the chart id of the exhibit manually. o gvis functions return more details about the visualisation chart in a structured way. Suppose x is a 'gvis' object, than x$html$chart is a named character vector of the chart's JavaScript building blocks and html tags. o print.gvis has a new argument 'tag', which gives the user more control over the output o New brew example files in: system.file(brew, package = googleVis) BUG FIXES o gvisTable did not accept datetime columns. Please feel free to send us an email rvisualisat...@gmail.com if you would like to be kept informed of new versions, or if you have any feedback, ideas, suggestions or would like to collaborate. Best regards, The googleVis team: Markus Gesmann, Diego de Castillo [[alternative HTML version deleted]] ___ R-packages mailing list r-packa...@r-project.org https://stat.ethz.ch/mailman/listinfo/r-packages __ 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.
[R] Time Series in R with ggplot2
Hi Folks, First, the important information. sessionInfo() R version 2.12.1 (2010-12-16) Platform: i386-pc-mingw32/i386 (32-bit) Second, my problem. I have a series of data sets comprised in the following format. totsoc Location Year Value 1 SOUTH 199829 2 SOUTH 199920 3 SOUTH 200032 4 SOUTH 200129 5 SOUTH 200225 6 SOUTH 200328 7 SOUTH 200427 8 SOUTH 200528 9 SOUTH 200622 10SOUTH 200731 In order to generate a time series plot in ggplot2, I ran the following code. qplot(Year, Value, data=totsoc, geom=line) ggplot(totsoc, aes(x=Year, y=Value)) + geom_line() However, neither command acctually produces a plot with lines connecting the data points. I get a blank window with the general gray background and the x and y axis. The strange thing is that ggplot2 gives me the appropriate output when I use bar or point. For example, these commands work. ggplot(totsoc, aes(Year, Value)) + geom_point() qplot(Year, Value, data=totsoc, geom=point) I also tried to generate some sample data, and that worked. However, I'm not sure why these same commands aren't working on the earlier data set. Here is the sample data I was working with. df - data.frame(one=c(3,8,5,4,2), two=c(KS,MO,KS,CA,IA), three=c(2001:2005)) qplot(three, one, data=df, geom=line) Can anyone please help? Thank You, A. Mathew __ 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.
Re: [R] Fwd: About classification methods.
On Feb 11, 2011, at 4:11 PM, Jaeik Cho wrote: I mean, after done for the testing step, I want show which data classified to wrong class. That predictions. At this point my suggestion is that your (re?)-read the Posting Guide and determine whether you have adhered to the level of detail and specificity that is implied to be desirable or optimal for questions to r-help. There may be a language issue and without implying any moral issue, the provision of a worked example might be even more important here than it would be in a situation of a shared language. You might also consult the How to ask good questions link which IIRC is at the bottom of that document. (My apologies to Bert if this was a question that he really was hoping to answer.) -- David Jaeik Begin forwarded message: From: Bert Gunter gunter.ber...@gene.com Date: February 11, 2011 3:00:47 PM CST To: David Winsemius dwinsem...@comcast.net Cc: Jaeik Cho choja...@gmail.com, r-help@r-project.org Subject: Re: [R] About classification methods. Which package should I using, and can I compare each classifier result by predictions? By prediction on the training data, emphastically no. By prediction on new data not used for training, yes. -- Bert __ 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. David Winsemius, MD West Hartford, CT __ 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.
Re: [R] lattice auto.key gives mismatch colors
Hi:
This seems to work:
mykey - list(space = 'top',
columns = 4,
text = list(as.character(unique(src$s)), col = colors),
points = list(pch = 1, col = colors)
)
xyplot(v~t, groups=s, type='o', data=src, col=colors, key = mykey)
HTH,
Dennis
On Fri, Feb 11, 2011 at 7:56 AM, John Smith zmr...@gmail.com wrote:
Hello All,
I am using the following code to draw a figure. But the legend given buy
auto.key has mismatched colors. Could any one help me?
I am using R2.12.1 and most current lattice on windows XP.
Thanks
John
library(lattice)
src - data.frame(t=rep(c('A','B','C','D'), rep(8,4)),
s=rep(c(8132,8140,8178,8180,8224,8230,8337,8345), 4),
v=c(55.10, 56.00, 206.00, 5.86, 164.00, 102.00, 171.00,
280.00, 236.00,
91.10, 238.00, 102.00, 59.30, 227.00, 280.00, 316.00,
205.00, 120.00,
273.00, 98.80, 167.00, 104.00, 155.00, 370.00, 215.00,
97.60, 133.00,
135.00, 48.60, 135.00, 77.10, 91.90))
colors - rgb(c(228, 55, 77, 152, 255, 255, 166, 247),
c(26, 126, 175, 78, 127, 255, 86, 129),
c(28, 184, 74, 163, 0, 51, 40, 191), maxColorValue=255)
xyplot(v~t, groups=s, type='o', data=src, col=colors, auto.key =
list(points=TRUE, columns = 4, col=colors))
[[alternative HTML version deleted]]
__
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.
[[alternative HTML version deleted]]
__
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.
[R] How do I add a book title to the R bibliography?
R community: I would like to add a new title to the bibliography on the R website (http://www.r-project.org/doc/bib/R-books.html), but I cannot find instructions for doing that. Can anyone tell me, whom should I contact in order to add a new book? (I added the title to the wiki's list of books, but the bibliography and the list don't seem to be connected.) Thank you! Paul Paul Teetor Elgin, IL USA http://www.linkedin.com/in/paulteetor For quant traders, there are no bad days in the market. It's just more data. __ 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.
Re: [R] Writing R packages in an easier way?
On 2/11/2011 2:52 AM, Dr. Michael Wolf wrote: Dear R colleagues, ... From the point of the costs e. g. I had to learn writing help files in a TeX-like language. But I'm the typical Word user. My last TeX writings were done in the 1990s! If I'm changing only a letter in a source file (r-file or help file) I've to build a new package. Seeing the results in my eyes this is a very expansive way. It's easier to me to write those files in HTML and to change the HTML source code. I don't need help files in Rd format. You can make things a whole lot easier by using prompt() to write the skeletons of the .Rd files. Then you have a ready-made template for your function or data and only need to fill in the details. Once you try this, you'll find it's not really any different than HTML markup. ?prompt __ 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.
Re: [R] Time Series in R with ggplot2
Hi, You probably have Year stored as a factor. See below. totsoc - structure(list(Location = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = SOUTH, class = factor), Year = 1998:2007, Value = c(29L, 20L, 32L, 29L, 25L, 28L, 27L, 28L, 22L, 31L )), .Names = c(Location, Year, Value), class = data.frame, row.names = c(NA, -10L)) qplot(Year, Value, data=totsoc, geom=line)#works as expected ggplot(totsoc, aes(x=Year, y=Value)) + geom_line()#same ##convert year to a factor dat - totsoc dat$Year - factor(dat$Year) qplot(Year, Value, data=dat, geom=line)## this now reproduces your problem ggplot(dat, aes(x=Year, y=Value)) + geom_line() ## same ## Solutions: 1) convert year to numeric, or 2) use group=1 as shown below, or 3) convert year to date class (this always gives me problems so I don't show an example). qplot(Year, Value, data=dat, geom=line, group=1) ggplot(dat, aes(x=Year, y=Value)) + geom_line(aes(group=1)) Best, Ista On Fri, Feb 11, 2011 at 5:29 PM, i...@mathewanalytics.com wrote: Hi Folks, First, the important information. sessionInfo() R version 2.12.1 (2010-12-16) Platform: i386-pc-mingw32/i386 (32-bit) Second, my problem. I have a series of data sets comprised in the following format. totsoc Location Year Value 1 SOUTH 1998 29 2 SOUTH 1999 20 3 SOUTH 2000 32 4 SOUTH 2001 29 5 SOUTH 2002 25 6 SOUTH 2003 28 7 SOUTH 2004 27 8 SOUTH 2005 28 9 SOUTH 2006 22 10 SOUTH 2007 31 In order to generate a time series plot in ggplot2, I ran the following code. qplot(Year, Value, data=totsoc, geom=line) ggplot(totsoc, aes(x=Year, y=Value)) + geom_line() However, neither command acctually produces a plot with lines connecting the data points. I get a blank window with the general gray background and the x and y axis. The strange thing is that ggplot2 gives me the appropriate output when I use bar or point. For example, these commands work. ggplot(totsoc, aes(Year, Value)) + geom_point() qplot(Year, Value, data=totsoc, geom=point) I also tried to generate some sample data, and that worked. However, I'm not sure why these same commands aren't working on the earlier data set. Here is the sample data I was working with. df - data.frame(one=c(3,8,5,4,2), two=c(KS,MO,KS,CA,IA), three=c(2001:2005)) qplot(three, one, data=df, geom=line) Can anyone please help? Thank You, A. Mathew __ 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. -- Ista Zahn Graduate student University of Rochester Department of Clinical and Social Psychology http://yourpsyche.org __ 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.
Re: [R] How to compute yaxp and usr without plotting ?
The usr parameter is either ylim or ylim plus 4 percent on either side (see yaxs/xaxs), see the pretty function for possible ways to get the yaxp information. Note that strwidth is based on the current coordinate system and will not give you the proper values unless the plot region has already been set up. -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare greg.s...@imail.org 801.408.8111 -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-bounces@r- project.org] On Behalf Of Yves REECHT Sent: Friday, February 11, 2011 3:38 AM To: r-help@r-project.org Subject: [R] How to compute yaxp and usr without plotting ? Dear all, I'd like to know how I could compute the parameters yaxp and (the y components of) usr without having to plot the data first. Note that ylim is /a priori/ fixed. The aim is to automatically adjust the parameter mgp without having to make the plot twice. Then, with yaxp and usr known, it should be easy to calculate a suitable mgp with the axTicks and strwidth functions. Many thanks in advance, Yves [[alternative HTML version deleted]] __ 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. __ 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.
Re: [R] Writing R packages in an easier way?
I guess Emacs + ESS + roxygen might be the easiest way to write an R
package. Writing or modifying Rd files/templates, in my eyes, is
really time-consuming and the Rd files are difficult to maintain
(unless you really have a good memory). I became reluctant to maintain
my R packages simply because I felt painful to maintain the
documentation. After I learned a bit about roxygen and ESS a few
months ago, several of my packages came back to life again (e.g. this
picture is a piece of evidence:
https://github.com/yihui/animation/graphs/impact). The feeling was
probably like when Dr Harrell switched from SAS to S (see
library(fortunes); fortune('I quit using SAS')).
Anyway, prompt() and package.skeleton() are very helpful in the short run.
Regards,
Yihui
--
Yihui Xie xieyi...@gmail.com
Phone: 515-294-2465 Web: http://yihui.name
Department of Statistics, Iowa State University
2215 Snedecor Hall, Ames, IA
On Fri, Feb 11, 2011 at 5:30 PM, Michael Friendly frien...@yorku.ca wrote:
On 2/11/2011 2:52 AM, Dr. Michael Wolf wrote:
Dear R colleagues,
...
From the point of the costs e. g. I had to learn writing help files in
a TeX-like language. But I'm the typical Word user. My last TeX writings
were done in the 1990s! If I'm changing only a letter in a source file
(r-file or help file) I've to build a new package. Seeing the results in
my eyes this is a very expansive way. It's easier to me to write those
files in HTML and to change the HTML source code. I don't need help
files in Rd format.
You can make things a whole lot easier by using prompt() to write the
skeletons of the .Rd files. Then you have a ready-made template for
your function or data and only need to fill in the details. Once you
try this, you'll find it's not really any different than HTML markup.
?prompt
__
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.
Re: [R] add mean and sd to dotplot in each panel using lattice
Hi Phil,
This is exactly what I want, I just changed some trivial settings to make it
plot standard error of the mean and color changing with panels.
Thank you very much.
-Xiaokuan
library(lattice)
mypanel = function(x,y,...){
agg-aggregate(y,list(x),function(x)c(mean(x,na.rm=TRUE),sd(x,na.rm=TRUE),length(x[!is.na(x)])))
mns = agg[,2][,1]
sds = agg[,2][,2]
ns = agg[,2][,3]
for(i in 1:nrow(agg))llines(c(i-.2,i+.2),rep(mns[i],2),lwd=3,col=i)
for(i in 1:nrow(agg)){llines(c(i-.1,i+.1),rep(mns[i] +
sds[i]/(ns[i]^0.5),2),col=i); #standard error
llines(c(i-.1,i+.1),rep(mns[i] -
sds[i]/(ns[i]^0.5),2),col=i)}
panel.dotplot(x,y,col=1:nrow(agg),...)
}
dotplot(Score ~ Dose | Sex , group=Dose, data=dat,panel=mypanel)
From: Phil Spector spec...@stat.berkeley.edu
Cc: r-help r-help@r-project.org
Sent: Wed, February 9, 2011 6:56:32 PM
Subject: Re: [R] add mean and sd to dotplot in each panel using lattice
Xiaokuan -
Maybe this will get you started:
mypanel = function(x,y,...){
agg-aggregate(y,list(x),function(x)c(mean(x,na.rm=TRUE),sd(x,na.rm=TRUE)))
mns = agg[,2][,1]
sds = agg[,2][,2]
for(i in 1:nrow(agg))llines(c(i-.1,i+.1),rep(mns[i],2),lwd=3)
for(i in 1:nrow(agg)){llines(c(i-.1,i+.1),rep(mns[i] + 1.96 * sds[i],2));
llines(c(i-.1,i+.1),rep(mns[i] - 1.96 * sds[i],2))}
panel.dotplot(x,y,...)
}
dotplot(Score ~ Dose | Sex, groups=Sex, data=dat,panel=mypanel)
- Phil Spector
Statistical Computing Facility
Department of Statistics
UC Berkeley
spec...@stat.berkeley.edu
On Wed, 9 Feb 2011, Xiaokuan Wei wrote:
Hi,
I have a data frame like this:
ScoreDoseSex
2.81Dose1M
1.81Dose1M
1.22Dose1M
0.81Dose1M
0.49Dose1M
0.22Dose1M
0.00Dose1M
-0.19Dose1M
-0.17Dose1F
-0.32Dose1F
-0.46Dose1F
-0.58Dose1F
-0.70Dose1F
-0.81Dose1F
-0.91Dose1F
-1.00Dose1F
-1.77Dose2M
-1.85Dose2M
-1.93Dose2M
-2.00Dose2M
-2.07Dose2M
-2.14Dose2M
-2.20Dose2M
-2.26Dose2M
-2.32Dose2F
-2.38Dose2F
-2.17Dose2F
-2.49Dose2F
-2.54Dose2F
-2.58Dose2F
-2.63Dose2F
-2.42Dose2F
I can make the dotplot using lattice package:
library(lattice)
dat-read.table(test.txt,header=T,sep=\t)
dotplot(Score ~ Dose | Sex, groups=Sex, data=dat)
How can I add mean line and stdev bar around mean line to this dotplot?
I have searched maillists, only several post about add sth to dotplot, but
they
are not what I want.
I know it may have sth to do with panel.function, but don't know how to
implement it.
I think the mean and stdev bar are popular additions to dot plot, don't know
why
there is no argument to control this kind of plotting.
Thanks.
Xiaokuan
_
TV dinner still cooling?
[[alternative HTML version deleted]]
__
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.
[[elided Yahoo spam]]
[[alternative HTML version deleted]]
__
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.
Re: [R] Where can I download/install grDevices
djmuseR wrote: Here's one way: plot(1~1,ylab=expression(Areas (~mu*m^2~))) The tildes incorporate space between the math and text elements; they're optional, but useful. This worked, thanks! Elizabeth -- View this message in context: http://r.789695.n4.nabble.com/Where-can-I-download-install-grDevices-tp2401415p3302154.html Sent from the R help mailing list archive at Nabble.com. __ 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.
[R] DiagnosisMed package corrupt?
Hi,
I was borrowing someone's code today, and they were using the package
DiagnosisMed. I downloaded the package using the built-in package
installer in the GUI (R 2.12.1 running on Mac OS 10.6.5). The package
manager lists the following information: ‘DiagnosisMed’ version 0.2.3
Every time I attempted to load the package, I subsequently had R hang.
The same commands which would cause the hanging after loading the
package worked without a hitch when I didn't load the package.
Actually, after I wrote that last sentence I tried starting R from
scratch, loading the package, and then typing 2+2.
This was my result:
library(DiagnosisMed)
Loading required package: epitools
Loading required package: TeachingDemos
Loading required package: tcltk
Loading Tcl/Tk interface ...
2+2
Loading required package: tcltk
*** caught segfault ***
address 0x41002109, cause 'memory not mapped'
Traceback:
1: sys.nframe()
2: dynGet(__NameSpacesLoading__, NULL)
3: loadNamespace(package, c(which.lib.loc, lib.loc), keep.source =
keep.source)
4: doTryCatch(return(expr), name, parentenv, handler)
5: tryCatchOne(expr, names, parentenv, handlers[[1L]])
6: tryCatchList(expr, classes, parentenv, handlers)
7: tryCatch(expr, error = function(e) { call - conditionCall(e) if
(!is.null(call)) { if (identical(call[[1L]], quote(doTryCatch))) call -
sys.call(-4L) dcall - deparse(call)[1L] prefix - paste(Error in,
dcall, : ) LONG - 75L msg - conditionMessage(e) sm - strsplit(msg,
\n)[[1L]] w - 14L + nchar(dcall, type = w) + nchar(sm[1L], type =
w) if (is.na(w)) w - 14L + nchar(dcall, type = b) + nchar(sm[1L],
type = b) if (w LONG) prefix - paste(prefix, \n , sep = ) }
else prefix - Error : msg - paste(prefix, conditionMessage(e),
\n, sep = ) .Internal(seterrmessage(msg[1L])) if (!silent
identical(getOption(show.error.messages), TRUE)) { cat(msg, file =
stderr()) .Internal(printDeferredWarnings()) } invisible(structure(msg,
class = try-error))})
8: try({ ns - loadNamespace(package, c(which.lib.loc, lib.loc),
keep.source = keep.source) dataPath - file.path(which.lib.loc, package,
data) env - attachNamespace(ns, pos = pos, dataPath = dataPath, deps)})
9: library(pkg, character.only = TRUE, logical.return = TRUE, lib.loc =
lib.loc)
10: .getRequiredPackages2(pkgInfo, quietly = quietly)
11: library(DiagnosisMed)
Possible actions:
1: abort (with core dump, if enabled)
2: normal R exit
3: exit R without saving workspace
4: exit R saving workspace
I have a workaround. But I just thought I'd report it anyways.
thanks, Daryl Morris
FHCRC, SCHARP, UW Biostatistics
__
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.
[R] Predictions with missing inputs
Dear users, I'll appreciate your help with this (hopefully) simple problem. I have a model object which was fitted to inputs X1, X2, X3. Now, I'd like to use this object to make predictions on a new data set where only X1 and X2 are available (just use the estimated coefficients for these variables in making predictions and ignoring the coefficient on X3). Here's my attempt but, of course, didn't work. #fit some linear model to random data x=matrix(rnorm(100*3),100,3) y=sample(1:2,100,replace=TRUE) mydata - data.frame(y,x) mymodel - lm(y ~ ns(X1, df=3) + X2 + X3, data=mydata) summary(mymodel) #create new data with 1 missing input mynewdata - data.frame(matrix(rnorm(100*2),100,2)) mypred - predict(mymodel, mynewdata) Thanks in advance for your help! Axel. [[alternative HTML version deleted]] __ 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.
Re: [R] Fwd: About classification methods.
On Feb 11, 2011, at 9:07 PM, Jaeik Cho wrote: Yes, this point i can understand your suggestion and I should read HOW TO ASK GOOD QUESTIONS. I'm a just new mailing list, also a R user for researching on graduate school. Any person can make mistake, also it can be effect to other people, however a good person is teaching good way. Anyway, actually I couldn't understand why you telling me like this, but sorry for my English and stupid first mailing list user. Have your read the Posting Guide yet? Sorry again. ps. I don't know also why should I put your name on CC Bert, sorry. Last of all, R is a kind of professional software. It means many of R user is high level educated person at least I think. Also, so many foreigner using this software who is not good for English writing. Please little bit more understand foreign users. The fact that people asking and answering questions are highly educated is even more reason for including more background and asking a detailed question. My point, which seems to have been misunderstood, is that using a formal language such as R (or mathematics) is probably a superior method of getting the real questions across the language barrier. At the moment your questions seem too vague to allow a specific answer. Thanks. On Feb 11, 2011, at 4:57 PM, David Winsemius wrote: On Feb 11, 2011, at 4:11 PM, Jaeik Cho wrote: I mean, after done for the testing step, I want show which data classified to wrong class. That predictions. At this point my suggestion is that your (re?)-read the Posting Guide and determine whether you have adhered to the level of detail and specificity that is implied to be desirable or optimal for questions to r-help. There may be a language issue and without implying any moral issue, the provision of a worked example might be even more important here than it would be in a situation of a shared language. You might also consult the How to ask good questions link which IIRC is at the bottom of that document. (My apologies to Bert if this was a question that he really was hoping to answer.) -- David Jaeik Begin forwarded message: From: Bert Gunter gunter.ber...@gene.com Date: February 11, 2011 3:00:47 PM CST To: David Winsemius dwinsem...@comcast.net Cc: Jaeik Cho choja...@gmail.com, r-help@r-project.org Subject: Re: [R] About classification methods. Which package should I using, and can I compare each classifier result by predictions? By prediction on the training data, emphastically no. By prediction on new data not used for training, yes. -- Bert __ 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. David Winsemius, MD West Hartford, CT David Winsemius, MD West Hartford, CT __ 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.
