[R] CCA no scores for some constraining variables
Dear all, I am performing a CCA using vegan package, function cca. Data loaded are fine (presence-absence data) but when using cca function it seems some constraining variables are not taken into account. While asking for the summary of the CCA: - they appear in call:cca(formula = etc.). - but their scores are not shown in Biplot scores for constraining variables - and they cannot be plotted. If they are considered alone i.e. without other constraining variables in the CCA, their scores appear and they can be plotted. How can it be? May someone help me to be sure they are taken into account in the CCA with all other constraining variables, and to get their scores? Or to understand why they are disregarded and others taken into account? Regards, Lise. __ 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] Avoid using eval in a neat way
I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. [[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] Avoid using eval in a neat way
This has been discussed extensively, on this list as well as elsewhere. I suggest doing a web search, read up on the issue, and post back here only if you have specific questions that are not answered already. Best, Ista On Sat, Feb 1, 2014 at 11:40 AM, Hai Qian hq...@gopivotal.com wrote: I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. [[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] Avoid using eval in a neat way
I have been searching around for some time, but with no luck for this particular problem. -- *Pivotal http://www.gopivotal.com/* A new platform for a new era On Sat, Feb 1, 2014 at 9:02 AM, Ista Zahn istaz...@gmail.com wrote: This has been discussed extensively, on this list as well as elsewhere. I suggest doing a web search, read up on the issue, and post back here only if you have specific questions that are not answered already. Best, Ista On Sat, Feb 1, 2014 at 11:40 AM, Hai Qian hq...@gopivotal.com wrote: I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. [[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] Avoid using eval in a neat way
You have set up your criteria for success to be that your user has full freedom to specify code in strings to evaluate. Then you ask how to achieve this goal without evaluating that code. Are you thinking objectively at all about your question? The advice to not use eval has a number of justifications that you should be able to find yourself online (unnecessary obfuscation and program security are two). Implementing an interpreter is not where this advice applies. At the core of this problem, as long as you accept that your user is working within the R interpreter then they can provide your code with functions that access data on their own. You don't need to assume so much responsibility as your question assumes you have to. Doctor, my head hurts! Then stop banging it against the wall. --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. On February 1, 2014 8:40:47 AM PST, Hai Qian hq...@gopivotal.com wrote: I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. [[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] Avoid using eval in a neat way
On 14-02-01 11:40 AM, Hai Qian wrote: I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. You're asking how to parse some text and evaluate it without using eval. Sounds impossible to me. Duncan Murdoch __ 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] Avoid using eval in a neat way
Hi Jeff, Your answer is good. It makes me think that maybe I should revise some of my designs. Now I know that it is impossible to do this under my settings. Thanks On Sat, Feb 1, 2014 at 9:55 AM, Jeff Newmiller jdnew...@dcn.davis.ca.uswrote: You have set up your criteria for success to be that your user has full freedom to specify code in strings to evaluate. Then you ask how to achieve this goal without evaluating that code. Are you thinking objectively at all about your question? The advice to not use eval has a number of justifications that you should be able to find yourself online (unnecessary obfuscation and program security are two). Implementing an interpreter is not where this advice applies. At the core of this problem, as long as you accept that your user is working within the R interpreter then they can provide your code with functions that access data on their own. You don't need to assume so much responsibility as your question assumes you have to. Doctor, my head hurts! Then stop banging it against the wall. --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. On February 1, 2014 8:40:47 AM PST, Hai Qian hq...@gopivotal.com wrote: I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. [[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] Avoid using eval in a neat way
On Sat, Feb 1, 2014 at 11:40 AM, Hai Qian hq...@gopivotal.com wrote: I know using eval is not optimal and maybe bad, but how to avoid using eval in the following example func1 - function(dat, eval.this) { eval(parse(text = paste0(with(dat, , eval.this, } dat - data.frame(x = 1:2, y = 2:3) func1(dat, x*2+y) func1(dat, sin(x)*cos(y)) Here eval.this is a string that contains whatever the user wants to evaluate. I wonder whether there is a neat way to avoid using eval in this case? So far I have not figured out a way to do this. Since the string is arbitrary R code ultimately it will have to be pushed through the R interpreter but we can avoid the superficial act of calling 'eval' by punting to some other function which in turn invokes 'eval' like this: func2 - function(dat, s) do.call(with, list(dat, parse(text = s))) 'func2' can be run like this: func2(dat, x*2+y) [1] 4 7 func2(dat, sin(x)*cos(y)) [1] -0.3501755 -0.9001976 Note that 'with' dispatches to 'with.default' which in turn invokes `eval`: with.default function (data, expr, ...) eval(substitute(expr), data, enclos = parent.frame()) bytecode: 0x05db6790 environment: namespace:base [[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] predicted values
Consider this dummy dataset. My real dataset with over 1000 records has scatter large and small values. I want to predict for values with NA but I get negative predictions. Is this a normal behaviour or I am missing a gam argument to force the model to predict positive values. library(mgcv) test - data.frame(iddate=seq(as.Date(2014-01-01), as.Date(2014-01-12), by=days), value=c(300,29,22,NA,128,24,15,1,3,30,NA,2)) test str(test) mod - gam(value ~ s(as.numeric(iddate)),data=test) # Predict for values with NA's test$pred - with(test,ifelse(is.na(value),predict(mod,test),value)) test [[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] meta data on infert data set
Hi, I wanted to know what the following columns mean in the infert dataset: parity count matched set number 1-83 stratum number 1-63 Thank you, Fayez Urbana, IL, USA [[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] meta data on infert data set
They appear to be technical terms relevant to fertility. You should probably ask someone with a background in medicine... or Google for these terms in conjunction with the word fertility. --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. On February 1, 2014 5:57:37 PM PST, Aziz, Muhammad Fayez az...@illinois.edu wrote: Hi, I wanted to know what the following columns mean in the infert dataset: parity count matched set number 1-83 stratum number 1-63 Thank you, Fayez Urbana, IL, USA [[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] predicted values
Dear Felipe, That is a normal behavior --- The prediction for that simple model decreases over time, and ends up negative. If the outcome cannot take on negative values, treating it as a continuous gaussian may not be optimal --- perhaps some transformation, like using a log link so that the expoentiated values are always positive would be better? Alternately, if the predictions are going negative, not because the data is over all, but say there is a quick decrease in values in the first part of time but later on it slows, but if you have an overly simplisitic time model, it may just keep decreasing. Using a smoother with a higher basis dimensions may help more accurately model the function over the span of time in your dataset and then not have predicted values. I do not think that there would be any straight forward 'force' the model to be positive only. Best, Joshua On Sat, Feb 1, 2014 at 5:05 PM, Felipe Carrillo mazatlanmex...@yahoo.com wrote: Consider this dummy dataset. My real dataset with over 1000 records has scatter large and small values. I want to predict for values with NA but I get negative predictions. Is this a normal behaviour or I am missing a gam argument to force the model to predict positive values. library(mgcv) test - data.frame(iddate=seq(as.Date(2014-01-01), as.Date(2014-01-12), by=days), value=c(300,29,22,NA,128,24,15,1,3,30,NA,2)) test str(test) mod - gam(value ~ s(as.numeric(iddate)),data=test) # Predict for values with NA's test$pred - with(test,ifelse(is.na(value),predict(mod,test),value)) test [[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. -- Joshua Wiley Ph.D. Student, Health Psychology University of California, Los Angeles http://joshuawiley.com/ Senior Analyst - Elkhart Group Ltd. http://elkhartgroup.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] meta data on infert data set
On Feb 1, 2014, at 6:32 PM, Jeff Newmiller wrote: They appear to be technical terms relevant to fertility. You should probably ask someone with a background in medicine... or Google for these terms in conjunction with the word fertility. Parity is the only technical term and its easy enough to look up in a dictionary. (Or if you do a Google search and choose the first hit you see it accurately defined at least for its biologic meaning. The other two relate to the study design and that why the author put in a citation, which unsurprising brings up the orignal paper as the first hit with a Google search. So, Aziz, please use a bit more initiative. -- David Winsemius --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. On February 1, 2014 5:57:37 PM PST, Aziz, Muhammad Fayez az...@illinois.edu wrote: Hi, I wanted to know what the following columns mean in the infert dataset: parity count matched set number 1-83 stratum number 1-63 Thank you, Fayez Urbana, IL, USA [[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. David Winsemius Alameda, 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] Defining function help
ah, I see! Thanks you for the assistance! I can see how I went wrong. From: arun smartpink...@yahoo.com Sent: Friday, January 31, 2014 2:59 PM To: r-help@r-project.org Cc: Mathew Nagendran Subject: Re: [R] Defining function help Hi, Not sure if this is what you wanted: t.control=function(m, a){(1-exp(-a*m)*((1-(1/30))*m))} t.sham=function(m, a, d){(1-exp(-a*(1-d)*m)*((1-(1/30))*m))} t.control(2,2) #[1] 0.9645898 t.sham(2,2,0.1) #[1] 0.9471741 A.K. On Friday, January 31, 2014 12:29 PM, Mathew Nagendran mathew.nagend...@mail.utoronto.ca wrote: Hello everyone. I am quite new to R and I would appreciate some help in figuring out what I am doing wrong. For the following code: #with cost m.control=c(1.45,9.40,9.96,4.2,1.86,0.2) m.sham=c(3.39,23.94,23.62,10.08,2.99,1.09) t.control=function(m, a){(1-exp(-a*m)*(1-(1/30)*m))} t.sham=function(m, a, d){(1-exp(-a*(1-d)*m)*(1-(1/30)*m))} t.sham(2, 2, 0.1) [1] 0.9744979 t.control(2, 2) [1] 0.9829054 #without cost m.control=c(1.45,9.40,9.96,4.2,1.86,0.2) m.sham=c(3.39,23.94,23.62,10.08,2.99,1.09) t.control=function(m, a){(1-exp(-a*m))} t.sham=function(m, a, d){(1-exp(-a*(1-d)*m))} t.sham(2, 2, 0.1) [1] 0.9726763 t.control(2, 2) [1] 0.9816844 As you can see the values I am getting for t.control and t.sham are larger in the with cost scenario and this shouldn't be the case. (the cost is 1-1/30*m). Is there something wrong I did when defining t.sham and t.control in the with cost section that I am failing to see? [[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] (no subject)
Hi I want R code for bayesian CIF competing risks. best regards __ 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] (no subject)
On 02/02/14 15:37, mohammad javad Azadchehr wrote: Hi I want R code for bayesian CIF competing risks. best regards I want wealth, wisdom, good looks, and to play full forward for the Sydney Swans. cheers, Rolf Turner __ 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] (no subject)
On 02/02/2014 01:37 PM, mohammad javad Azadchehr wrote: Hi I want R code for bayesian CIF competing risks. best regards Hi mohammad, Have a look at the SemiCompRisks package. Jim PS - You deserved Rolf's reply. __ 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] book on parallel programming
I'm about halfway finished writing a book titled, Parallel Computation for Data Science: with Examples in R and Beyond, to be published later this year by Chapman and Hall. I'm making a rough draft of the first half of the book available on the Web: http://heather.cs.ucdavis.edu/paralleldatasci.pdf Your comments and suggestions are welcome, in fact very much hoped-for. I took this approach when I wrote my R programming book, and found it very helpful to me, and of much value to people who downloaded it. Hopefully the same will be true here. Norm Matloff __ 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.