[R] community
Dear group working on a graph..I parse the graph node by node and create cluster for set of nodes..firstly the number of clusters are not knowen what kind of R object can I flexibly use as community, say I want M communities C1,C2..CM how can I define this ? thanks in advance Ragia [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Different behavior of model.matrix between R 3.2 and R3.1.1
Frank, I don't think there is any way to fix your problem except the way that I did it. library(survival) tdata - data.frame(y=c(1,3,3,5, 5,7, 7,9, 9,13), x1=factor(letters[c(1,1,1,1,1,2,2,2,2,2)]), x2= c(1,2,1,2,1,2,1,2,1,2)) fit1 - lm( y ~ x1 * strata(x2) - strata(x2), tdata) coef(fit1) (Intercept)x1b x1a:strata(x2)x2=2 x1b:strata(x2)x2=2 3.00 5.00 1.00 1.67 Your code is calling model.matrix with the same model frame and terms structure as the lm call above (I checked). In your case you know that the underlying model has 2 intercepts (strata), one for the group with x2=1 and another for the group with x2=2, but how is the model.matrix routine supposed to guess that? It can't, so model.matrix returns the proper result for the lm call. As seen above the result is not singular, while for the Cox model it is singular due to the extra intercept. This is simply an extension of leaving the intercept term in the model and then removing that column from the returned X matrix, which is necessary to have the correct coding for ordinary factor variables, something we've both done since day 1. In order for model.matrix to do the right thing with interactions, it has to know how many intercepts there actually are. I've come to the conclusion that the entire thrust of 'contrasts' in S was wrong headed, i.e., the remove redundant columns from the X matrix ahead of time logic. It is simply not possible for the model.matrix routine to guess correctly for all y and x combinations, something that been acknowledged in R by changing the default for singular.ok to TRUE. Dealing with this after the fact via a good contrast function (a la SAS -- heresy!) would have been a much better design choice. But as long as I'm in R the coxph routine tries to be a good citizen. Terry T. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] version 3.0-0 of bayesm
Version 3.0-0 of bayesm is now on CRAN. All MCMC routines in this version have been recoded using rcpp-Armadillo. This results in speeds gains of between 2 and 30 times faster (hierarchical and density estimation routines are on the higher end of this range) than in bayesm version 2.2-5. The algorithm, rsurGibbs, has been improved for better speed as well as recoded. A Bayesian treatment of aggregate random coefficient models (with instruments) has been added, see rbayesBLP. peter rossi thanks to Neil Fultz, Keunwoo Kim, and Wayne Taylor for their help in the recoding. [[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 -- To UNSUBSCRIBE and more, see 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-es] Regresión logística
Holap. ran out of iterations and failed to converge Prueba aumentando el número de iteraciones, con el argumento maxit: GLM - bigglm(In.hospital_death ~ GCS + BUN, data = DatosGLM, family = binomial(logit), maxit=1000) Salud. -- «No soy aquellas sombras tutelares que honré con versos que no olvida el tiempo.» JL Borges [[alternative HTML version deleted]] ___ R-help-es mailing list R-help-es@r-project.org https://stat.ethz.ch/mailman/listinfo/r-help-es
[R] Boxplot using a shapefile
Dear all, I am trying to generate boxplots by giving a shapefile and an image as input. The shapefile takes the pixel values from the image and shows the distribution of pixels in the form of a boxplot. Can somebody please tell me how I can execute this in R? Many thanks! -- Regards, Preethi Malur Balaji | PhD Student University College Cork | Cork, Ireland. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Request
Dear Sir or Madame, I am a novice in R, and I want to perform a meta analysis of case control studies (analytic), i want a step by step explanation if it's possible, Thanks. Cordially, [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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-es] Regresión logística
Hola, estoy intentando hacer una regresión logística entre la primera columna de mi data.table (In.hospital_death) y otras dos (GSV y BUN) , me da el error de abajo, he intentado eliminar las filas con valor NA por si esta función no lo admite, pero sigue dando el mismo error. ¿Alguien sabe porqué ocurre? (probé previamente a usar la función glm pero obtenía out of memory) library(XLConnect) library(biglm) library(data.table) GLM - bigglm(In.hospital_death ~ GCS + BUN, data = DatosGLM, family = binomial(logit)) Obtengo el error: In bigglm.function(formula = formula, data = datafun, ...) : ran out of iterations and failed to converge Un saludo Gracias MªLuz [[alternative HTML version deleted]] ___ R-help-es mailing list R-help-es@r-project.org https://stat.ethz.ch/mailman/listinfo/r-help-es
[R] Question about saving the context crawled by getNodeSet into a document
Dear Sir/Madam: Thank you for your concern. I’m using getNodeSet in XML package to craw data from web pages, and I need to save it as a document. However, I tried write.table, write, and cat, but none of above could save the data. The error messages just like these: ac-getNodeSet(article, //div[@class='entry-content']) #attention to the majuscule write.table(ac[[1]], file=E:/学术资源网络分析/article.txt)Error in as.data.frame.default(x[[i]], optional = TRUE) : c(cannot coerce class \c(\XMLInternalElementNode\, \XMLInternalNode\, \XMLAbstractNode\\ to a data.frame, cannot coerce class \)\ to a data.frame) write(ac, file=E:/学术资源网络分析/article.txt)Error in cat(list(...), file, sep, fill, labels, append) : argument 1 (type 'list') cannot be handled by 'cat' I have tried to force the data from getNodeSet into data frame, but it does not work either: tmp - data.frame(ac)Error in as.data.frame.default(x[[i]], optional = TRUE, stringsAsFactors = stringsAsFactors) : 不能把XMLNodeSet类别强迫变成数据框 I really confused how to save the data crawled by getNodeSet into a document. I wonder if you could give me some advice on solving this problem with R. And I would be most grateful if you could reply at your earliest convenience. Looking forward to hearing from you. Thank you very much. Sincerely yours Humphrey Zhao [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Error bars and CI
Hi, I want to plot a line graph using this data. IDX is x-axis and V1 is y-axis. I also want standard error bars and 99% CI to be shown. My code is given below. The section that plots the graph is the problem. I don't see all the points in the line graph with error bars. How can I also show the 99% CI in the graph ? V1 IDX 1 0.987 21 2 0.585 22 3 0.770 23 4 0.711 24 library(stringr) library(dplyr) library(ggplot2) data - read.table(D:\\jmh\\jmh.txt,sep=\t) final -data %% select(V1) %% filter(grepl(^Iteration, V1)) %% mutate(V1 = str_extract(V1, \\d+\\.\\d*)) final - mutate(final,IDX = 1:n()) jc - final %% filter(IDX 21) #Convert to numeric jc - data.frame(sapply(jc, function(x) as.numeric(as.character(x print(jc) # The following section is the problem. sem - function(x){ sd(x)/sqrt(length(x)) } meanvalue - apply(jc,2,mean) semvalue - apply(jc, 2, sem) mean_sem - data.frame(mean= meanvalue, sem= semvalue, group=names(jc)) #larger font theme_set(theme_gray(base_size = 20)) #plot using ggplot p - ggplot(mean_sem, aes(x=group, y=mean)) + geom_line(stat='identity') + geom_errorbar(aes(ymin=mean-sem, ymax=mean+sem), width=.2) print(p) Thanks, Mohan This e-mail and any files transmitted with it are for the sole use of the intended recipient(s) and may contain confidential and privileged information. If you are not the intended recipient(s), please reply to the sender and destroy all copies of the original message. Any unauthorized review, use, disclosure, dissemination, forwarding, printing or copying of this email, and/or any action taken in reliance on the contents of this e-mail is strictly prohibited and may be unlawful. Where permitted by applicable law, this e-mail and other e-mail communications sent to and from Cognizant e-mail addresses may be monitored. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] model selection
Hi friends, Im trying to make a model selection comparing models built with lm function (package stats) and lme function (package nlme). Do you know if there is a problem to compare these models with the function AICtab (package bbmle). Thanks!!! Bruno Cid Crespo GuimarãesMestre em EcologiaLaboratório de Ecologia e Conservação de PopulaçõesUniversidade Federal do Rio de Janeiro [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 nlme, environments, and packages
Hello R users, I encountered a strange problem while writing a package that uses the nlme function. First, I wrote some code that uses the nlme function, and it ran without errors. However, when I tried to put the code into a package, the nlme function was unable to locate a function that was used in the formula. Could it be that nlme is looking in the wrong environment? I would appreciate any suggestions. Below is a reproducible example with the problem. ### BEGIN EXAMPLE ## #' Fake package to show nlme error #' @export main_function - function(x){ library(nlme) result - nlme(height ~ SSasymp(age, Asym, R0, lrc) + nonlinear_function(age), data = Loblolly, fixed = Asym + R0 + lrc ~ 1, random = Asym ~ 1, start = c(Asym = 103, R0 = -8.5, lrc = -3.3)) result } nonlinear_function - function(x){ log(x) } ### END EXAMPLE ## The above code can be installed as a package and run with the commands library(devtools) library(roxygen2) setwd(C:/test) # or any prefered directory create(testPackage) setwd(./testPackage) document() setwd(..) install(testPackage) main_function() The output is main_function() Error in eval(expr, envir, enclos) : could not find function nonlinear_function sessionInfo() R version 3.1.3 (2015-03-09) Platform: x86_64-w64-mingw32/x64 (64-bit) Running under: Windows 8 x64 (build 9200) locale: [1] LC_COLLATE=English_United States.1252 [2] LC_CTYPE=English_United States.1252 [3] LC_MONETARY=English_United States.1252 [4] LC_NUMERIC=C [5] LC_TIME=English_United States.1252 attached base packages: [1] stats graphics grDevices utils datasets methods [7] base other attached packages: [1] nlme_3.1-120 testPackage_0.0.0.9000 [3] roxygen2_4.1.1 devtools_1.8.0 loaded via a namespace (and not attached): [1] curl_0.8digest_0.6.8git2r_0.10.1 [4] grid_3.1.3 lattice_0.20-31 magrittr_1.5 [7] memoise_0.2.1 Rcpp_0.11.6 rversions_1.0.1 [10] stringi_0.4-1 stringr_1.0.0 tools_3.1.3 [13] xml2_0.1.1 Note that if I simply paste main_function and nonlinear_function into the R console, then main_function() runs without errors. Greg [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Request
Dear Djamil On 15/06/2015 14:37, MALIOU Djamil wrote: Dear Sir or Madame, I am a novice in R, and I want to perform a meta analysis of case control studies (analytic), i want a step by step explanation if it's possible, You can find details about packages which support meta-analysis in R in the Task View http://CRAN.R-project.org/view=MetaAnalysis Without more details of what you want to do it is hard to offer any more hints. Thanks. Cordially, [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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. -- Michael http://www.dewey.myzen.co.uk/home.html __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Boxplot using a shapefile
Your workflow in principle is: - read the image into an object for which you can obtain values-per-pixel in a 2D structure; - read the shapefile and convert into a polygon; - determine the bounding box of the polygon; - use the inout() function of the splancs package to get a list of booleans for the points in the bounding box, TRUE if they are _inside_ the polygon; - subset your image points to those for which inout() returns TRUE; - plot as boxplot(). The CRAN taskview http://cran.r-project.org/web/views/MedicalImaging.html has a section on general image processing, guiding you to helpful packages. Ask again if you get stuck - but(!): - see here for some hints on how to ask questions productively: http://adv-r.had.co.nz/Reproducibility.html http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example - ... and please read the posting guide and don't post in HTML. B. On Jun 15, 2015, at 7:19 AM, Preethi Balaji preet.balaj...@gmail.com wrote: Dear all, I am trying to generate boxplots by giving a shapefile and an image as input. The shapefile takes the pixel values from the image and shows the distribution of pixels in the form of a boxplot. Can somebody please tell me how I can execute this in R? Many thanks! -- Regards, Preethi Malur Balaji | PhD Student University College Cork | Cork, Ireland. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] search across a row for strings
This faster than your version, and doesn't return NA: df$htn - apply(df[,2:4], 1, function(x)any(grepl(^410, x))) df ID DX1 DX2 DX3 htn 1 1 4109 4280 7102 TRUE 2 2 734 311 490 FALSE 3 3 4011 42822 4101 TRUE system.time({ + for(j in 1:1) { + for (i in 1:nrow(df)) { + df[i,htn] - any(sapply('410', function(x) which( grepl(x, df[i, 2:4], fixed = TRUE) ))) + } + } + }) user system elapsed 6.648 0.008 6.657 There were 50 or more warnings (use warnings() to see the first 50) system.time({ + for(j in 1:1) { + df$htn - apply(df[,2:4], 1, function(x)any(grepl(^410, x))) + } + }) user system elapsed 1.826 0.000 1.826 On Mon, Jun 15, 2015 at 4:12 PM, Federman, Douglas douglas.feder...@utoledo.edu wrote: I'm trying to do the following: search each patient's list of diagnoses for a specific code then create a new column based upon the the presence of the specific code. Simplified data follows: con - textConnection( ID DX1 DX2 DX3 1 410942807102 2 734 311 490 3 401142822 4101 ) df - read.table(con, header = TRUE, strip.white = TRUE, colClasses=character) # # I would like to add a column such the result of searching for 410 would give: The search string would always be at the start of a word and doesn't need regex. # # IDDX1 DX2 DX3 htn # 1 4109428071021 # 2 734 311 490 0 # 3 401142822 41011 # # The following works but is slow and returns NA if the search string is not found: for (i in 1:nrow(df)) { df[i,htn] - any(sapply('410', function(x) which( grepl(x, df[i, 2:4], fixed = TRUE) ))) } Thanks in advance. I never fail to learn new things from this list. -- Sarah Goslee http://www.functionaldiversity.org __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] search across a row for strings
I'm trying to do the following: search each patient's list of diagnoses for a specific code then create a new column based upon the the presence of the specific code. Simplified data follows: con - textConnection( ID DX1 DX2 DX3 1 410942807102 2 734 311 490 3 401142822 4101 ) df - read.table(con, header = TRUE, strip.white = TRUE, colClasses=character) # # I would like to add a column such the result of searching for 410 would give: The search string would always be at the start of a word and doesn't need regex. # # IDDX1 DX2 DX3 htn # 1 4109428071021 # 2 734 311 490 0 # 3 401142822 41011 # # The following works but is slow and returns NA if the search string is not found: for (i in 1:nrow(df)) { df[i,htn] - any(sapply('410', function(x) which( grepl(x, df[i, 2:4], fixed = TRUE) ))) } Thanks in advance. I never fail to learn new things from this list. -- Who is wise? One who learns from every person. Who is strong? One who overpowers his evil inclinations. Who is rich? One who is satisfied with his lot. Who is honorable? One who honors his fellows. - Pirkei Avot [excerpt] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Error in local package install
Hello, I've built a windows binary package from my Mac using the help from this site: http://win-builder.r-project.org As expected, I got back the file mypackage.zip. Also, the logs show no errors. Now, when I try to install on windows using the GUI install package(s) from local zip files, I get the following error: utils:::menuInstallLocal() Error in read.dcf(file.path(pkgname, DESCRIPTION), c(Package, Type)) : cannot open the connection In addition: Warning messages: 1: In unzip(zipname, exdir = dest) : error 1 in extracting from zip file 2: In read.dcf(file.path(pkgname, DESCRIPTION), c(Package, Type)) : cannot open compressed file 'mypackage/DESCRIPTION', probable reason 'No such file or directory' I've attempted to use the solutions from prior similar email threats with no success. Btw - I've install all the packages dependencies prior to the above. I'm on R 3.2.0. Any guidance would be much appreciated. Thank you. Axel. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] search across a row for strings
On Jun 15, 2015, at 1:12 PM, Federman, Douglas wrote: I'm trying to do the following: search each patient's list of diagnoses for a specific code then create a new column based upon the the presence of the specific code. Simplified data follows: con - textConnection( IDDX1 DX2 DX3 1 410942807102 2 734 311 490 3 401142822 4101 ) df - read.table(con, header = TRUE, strip.white = TRUE, colClasses=character) # # I would like to add a column such the result of searching for 410 would give: The search string would always be at the start of a word and doesn't need regex. # # ID DX1 DX2 DX3 htn # 1 4109428071021 # 2 734 311 490 0 # 3 401142822 41011 # # The following works but is slow and returns NA if the search string is not found: for (i in 1:nrow(df)) { df[i,htn] - any(sapply('410', function(x) which( grepl(x, df[i, 2:4], fixed = TRUE) ))) } Is this any better? df$htn - apply(df[-1], 1, function(r) max( substr(r, 1,3) == 410 )) df ID DX1 DX2 DX3 htn 1 1 4109 4280 7102 1 2 2 734 311 490 0 3 3 4011 42822 4101 1 Can add an na.rm=TRUE to the max call if warranted. `max` coerces logicals to integer. -- David Winsemius Alameda, CA, USA __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Error in local package install
On 15.06.2015 22:32, Axel Urbiz wrote: Hello, I've built a windows binary package from my Mac using the help from this site: http://win-builder.r-project.org As expected, I got back the file mypackage.zip. Also, the logs show no errors. No, you got a file packagename_version.zip. Now, when I try to install on windows using the GUI install package(s) from local zip files, I get the following error: utils:::menuInstallLocal() Error in read.dcf(file.path(pkgname, DESCRIPTION), c(Package, Type)) : cannot open the connection In addition: Warning messages: 1: In unzip(zipname, exdir = dest) : error 1 in extracting from zip file 2: In read.dcf(file.path(pkgname, DESCRIPTION), c(Package, Type)) : cannot open compressed file 'mypackage/DESCRIPTION', probable reason 'No such file or directory' I've attempted to use the solutions from prior similar email threats with no success. Btw - I've install all the packages dependencies prior to the above. I'm on R 3.2.0. please try the release condadate of R-3.2.1, R-3.2.0 had a bug for package installation from local zip files. Best, Uwe Ligges Any guidance would be much appreciated. Thank you. Axel. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Missing Values in Table Statement
Hi Why you are so reluctant to use dput for sending us part of your data? The result of str indicates that that SCH_TIME is character vector in which some values are time and others are **empty** strings. But empty string does not mean it is missing string. ***Empty bottle of whisky is not missing bottle of whisky***. So is.na correctly finds that none of your values are missing. see this example test-sample(letters[1:5], 10, replace=T) test[5:7]-NA str(test) chr [1:10] b a d e NA NA NA d d c table(is.na(test)) FALSE TRUE 7 3 test[5:7]- str(test) chr [1:10] b a d ed d c table(is.na(test)) FALSE 10 Cheers Petr -Original Message- From: R-help [mailto:r-help-boun...@r-project.org] On Behalf Of Shivi82 Sent: Saturday, June 13, 2015 6:36 AM To: r-help@r-project.org Subject: Re: [R] Missing Values in Table Statement HI Don, This is the exact result i need. However in my case i am not getting any value under TRUE whereas FALSE captures total observations in each variable. Please find the syntax and output from the code: table(test$ORIGIN_NAME,is.na(test$SCH_TIME)) Output FALSE BAHADURGARH15 BAREILLY44 BAWAL34 DELHI-11 2446 DELHI-39 170 DELHI-40 86 DELHI NCR-121925 The data from str is attached: data.frame': 10765 obs. of 18 variables: $ ORIGIN : chr DLI11 DLI11 NDA50 NDA50 ... $ ORIGIN_NAME: chr DELHI-11 DELHI-11 NOIDA-50 NOIDA-50 ... $ DESTINATION: chr NDA50 NDA50 DLI11 NDA11 ... $ DESTINATION_NM : chr NOIDA-50 NOIDA-50 DELHI-11 NOIDA-11 ... $ RPS_NO : int 1350760 1366368 1352692 1354642 1354642 1349180 1349180 1356091 1348591 1348591 ... $ VENDOR_NAME: chr RAJIV GAUTAM RAJIV GAUTAM RAJIV GAUTAM RAJIV GAUTAM ... $ CR_DT : chr 13-Mar-15 31-Mar-15 15-Mar-15 17-Mar- 15 ... $ SCHD_MRKT : chr SCHEDULE SCHEDULE SCHEDULE MARKET ... $ VHL_NO : chr HR63A0931 HR63A0931 HR63A0931 HR63A0931 ... $ vhl_cap: int 8 8 8 8 8 8 8 8 8 8 ... $ SCH_TIME : chr 6:00 6:00 21:30 ... $ ACTUAL_DEP_DATE: chr 13/03/2015 31/03/2015 15/03/2015 17/03/2015 ... $ ACTUAL_DEP_TIME: chr 6:30 4:05 13:37 20:15 ... $ WAYBILLS : chr - - - 3 ... $ TOTAL_PKG : int 0 0 0 40 256 6 0 0 16 427 ... $ ACTUAL_WT : int 0 0 0 744 3419 65 0 0 193 7223 ... $ CHG_WT : int 0 0 0 770 3730 70 0 0 210 7310 ... $ RTE_CD : chr DELHI-11-NOIDA-50(DLI11-NDA50) DELHI-11-NOIDA-50(DLI11-NDA50) NOIDA-50-DELHI-11(NDA50-DLI11) NOIDA-50-DELHI-11(NDA50-NDA11-DLI11) Scheduled time here is character, could this be the reason for the incorrect result. Thanks, Shivi -- View this message in context: http://r.789695.n4.nabble.com/Missing- Values-in-Table-Statement-tp4708534p4708593.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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. Tento e-mail a jakékoliv k němu připojené dokumenty jsou důvěrné a jsou určeny pouze jeho adresátům. Jestliže jste obdržel(a) tento e-mail omylem, informujte laskavě neprodleně jeho odesílatele. Obsah tohoto emailu i s přílohami a jeho kopie vymažte ze svého systému. Nejste-li zamýšleným adresátem tohoto emailu, nejste oprávněni tento email jakkoliv užívat, rozšiřovat, kopírovat či zveřejňovat. Odesílatel e-mailu neodpovídá za eventuální škodu způsobenou modifikacemi či zpožděním přenosu e-mailu. V případě, že je tento e-mail součástí obchodního jednání: - vyhrazuje si odesílatel právo ukončit kdykoliv jednání o uzavření smlouvy, a to z jakéhokoliv důvodu i bez uvedení důvodu. - a obsahuje-li nabídku, je adresát oprávněn nabídku bezodkladně přijmout; Odesílatel tohoto e-mailu (nabídky) vylučuje přijetí nabídky ze strany příjemce s dodatkem či odchylkou. - trvá odesílatel na tom, že příslušná smlouva je uzavřena teprve výslovným dosažením shody na všech jejích náležitostech. - odesílatel tohoto emailu informuje, že není oprávněn uzavírat za společnost žádné smlouvy s výjimkou případů, kdy k tomu byl písemně zmocněn nebo písemně pověřen a takové pověření nebo plná moc byly adresátovi tohoto emailu případně osobě, kterou adresát zastupuje, předloženy nebo jejich existence je adresátovi či osobě jím zastoupené známá. This e-mail and any documents attached to it may be confidential and are intended only for its intended recipients. If you received this e-mail by mistake, please immediately inform its sender. Delete the contents of this e-mail with all attachments and its copies from your
Re: [R] Different behavior of model.matrix between R 3.2 and R3.1.1
Thank you very much Terry. I'm still puzzled at why this worked a year ago. What changed? I'd very much like to reverse the change by setting an argument somewhere or manipulating the terms object. I echo your sentiments about the general approach. Frank On 06/15/2015 09:05 AM, Therneau, Terry M., Ph.D. wrote: Frank, I don't think there is any way to fix your problem except the way that I did it. library(survival) tdata - data.frame(y=c(1,3,3,5, 5,7, 7,9, 9,13), x1=factor(letters[c(1,1,1,1,1,2,2,2,2,2)]), x2= c(1,2,1,2,1,2,1,2,1,2)) fit1 - lm( y ~ x1 * strata(x2) - strata(x2), tdata) coef(fit1) (Intercept)x1b x1a:strata(x2)x2=2 x1b:strata(x2)x2=2 3.00 5.00 1.00 1.67 Your code is calling model.matrix with the same model frame and terms structure as the lm call above (I checked). In your case you know that the underlying model has 2 intercepts (strata), one for the group with x2=1 and another for the group with x2=2, but how is the model.matrix routine supposed to guess that? It can't, so model.matrix returns the proper result for the lm call. As seen above the result is not singular, while for the Cox model it is singular due to the extra intercept. This is simply an extension of leaving the intercept term in the model and then removing that column from the returned X matrix, which is necessary to have the correct coding for ordinary factor variables, something we've both done since day 1. In order for model.matrix to do the right thing with interactions, it has to know how many intercepts there actually are. I've come to the conclusion that the entire thrust of 'contrasts' in S was wrong headed, i.e., the remove redundant columns from the X matrix ahead of time logic. It is simply not possible for the model.matrix routine to guess correctly for all y and x combinations, something that been acknowledged in R by changing the default for singular.ok to TRUE. Dealing with this after the fact via a good contrast function (a la SAS -- heresy!) would have been a much better design choice. But as long as I'm in R the coxph routine tries to be a good citizen. Terry T. -- Frank E Harrell Jr Professor and Chairman School of Medicine Department of *Biostatistics* *Vanderbilt University* [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.