Re: [R] C: drive memory full
Dear R users, Thank you so much for your help. I got deleted all files in my C:\xxx\AppData\Local\Temp file and also run suggested R codes to erase files. I list them below as somebody may be interested in. All in all, I got some space (1 GB) back, and compressing Stata data, I achieved what I needed to do with Stata. Also, Windows tips for finding hidden files and big size files were very helpful. Unfortunately I could not run SequoiaView because of the security issue of my PC at office, but it sounded very useful. Thank you so much for considering my problem. Best wishes, Ayako --- some R codes I used : tempdir() dirname(tempdir()) unlink(tempdir(),recursive=TRUE) rm(list=ls(all=TRUE)) From: r-help-boun...@r-project.org r-help-boun...@r-project.org on behalf of jim holtman jholt...@gmail.com Sent: 18 June 2014 15:14 To: David L Carlson Cc: r-help@r-project.org Subject: Re: [R] C: drive memory full One program that I have found valuable in looking at the size of files on disk is SequoiaView. It creates a 'treemap' of the sizes of the files and lets you zoom in to specific directories and such. Jim Holtman Data Munger Guru What is the problem that you are trying to solve? Tell me what you want to do, not how you want to do it. On Wed, Jun 18, 2014 at 10:05 AM, David L Carlson dcarl...@tamu.edu wrote: Windows 8 (and earlier versions) has a disk cleanup tool that will let you delete temporary files that might help. At the bottom of the screen on the taskbar, click the folder icon to bring up a windows showing your drives and folders. On the left side click on the drive you are interested in (probably C:). On the top title bar of the window showing the folders in drive C: on the left is an icon showing a sheet of paper with a red checkmark. That brings up a properties window that shows you how much space you are using and how much is free. Close that window and then click on the Manage tab on the line just below the title bar. Click on Cleanup and that will let you select temporary files of various kinds for deletion if your drive is getting full. - David L Carlson Department of Anthropology Texas AM University College Station, TX 77840-4352 -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of jwd Sent: Tuesday, June 17, 2014 8:10 PM To: r-help@r-project.org Subject: Re: [R] C: drive memory full On Tue, 17 Jun 2014 12:48:54 + Hiyoshi, Ayako ayako.hiyoshi...@alumni.ucl.ac.uk wrote: Dear Martyn and Professor Ripley, Thank you so much for your help. I used Window's large file search (it was useful! thank you), but there is no big files detected in C: drive . Perhaps I will have to reinstall Windows.. The problem may not be R at all, but rather Windows. How large is your drive, not RAM but the actual drive? If you can, examine your drive to see if there are either fragmentation problems or hidden files taking up excess space. Look at the drive properties for C:\ and run disk clean-up if possible. Another problem, MS may have fixed this at some point - I don't run Win 8, is that if your deleted files are not removed, you can run out of space. Usually, the space occupied by a file marked for deletion should be scavenged as Windows needs space, but sometimes that may not happen, especially with a very full drive. So, if there are files in the Wastebasket remove them completely. Another space-use that can grow to excess is a print spool. Even Windows uses a print spool and that can grow too large for the system to function efficiently. JWdougherty __ 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. [[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] C: drive memory full
Dear R users, Hello, I am new to R and confused about my PC's memory space after using R a while. My PC is Windows 8, RAM 8GB. I have run some analyses using commands like vglm, aalen(Sruv()), lm()... some regressions. I also use Stata, and when I tried to run Stata (big file), Stata could not do something which used to do because of the lack of memory space. I suspect R's something because R is the only new activity I did recently. I tried to google and found 'tempdir()'. I checked my temporary file but it was empty. Just in case, after running 'unlink(tempdir(),recursive=TRUE)', I restarted my computer, but memory space did not change. But there seems still something big in my C: drive storage and nearly 12GB is eaten. Could it be possible that R saved something somewhere? As I finished analyses, all I need is to erase everything stored so that I can get my memory space back. Thank you so much for your help. Best wishes, Ayako [[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] C: drive memory full
Dear Professor Ripley, Thank you so much for your quick reply. I tried 'dianame(tempdir())' and removed several 'Rtemp' and all other files. Unfortunately it did not changed C: drive space much. I am really sorry, but could there be other things stored in somewhere in C: drive ? I called IT support, but they could not spot either. Kind regards, Ayako From: Prof Brian Ripley rip...@stats.ox.ac.uk Sent: 17 June 2014 10:37 To: Hiyoshi, Ayako; r-help@R-project.org Subject: Re: [R] C: drive memory full tempdir() is specific to an R session. Start up R and run dirname(tempdir()) and look at that directory. Shut down R, then remove all old files/folders in that directory, especially those beginning with 'Rtmp'. An R process tries to clean up after itself but - it cannot do so if it segfaults - Windows has rules which no other OS has which can result in files being locked and hence not deletable. On 17/06/2014 08:49, Hiyoshi, Ayako wrote: Dear R users, Hello, I am new to R and confused about my PC's memory space after using R a while. My PC is Windows 8, RAM 8GB. I have run some analyses using commands like vglm, aalen(Sruv()), lm()... some regressions. I also use Stata, and when I tried to run Stata (big file), Stata could not do something which used to do because of the lack of memory space. I suspect R's something because R is the only new activity I did recently. I tried to google and found 'tempdir()'. I checked my temporary file but it was empty. Just in case, after running 'unlink(tempdir(),recursive=TRUE)', I restarted my computer, but memory space did not change. But there seems still something big in my C: drive storage and nearly 12GB is eaten. Could it be possible that R saved something somewhere? As I finished analyses, all I need is to erase everything stored so that I can get my memory space back. Thank you so much for your help. Best wishes, Ayako [[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. -- Brian D. Ripley, rip...@stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ 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] C: drive memory full
Dear Martyn and Professor Ripley, Thank you so much for your help. I used Window's large file search (it was useful! thank you), but there is no big files detected in C: drive . Perhaps I will have to reinstall Windows.. Thank you so much for your replies. Best wishes, Ayako From: Martyn Byng martyn.b...@nag.co.uk Sent: 17 June 2014 12:10 To: Hiyoshi, Ayako; Prof Brian Ripley; r-help@R-project.org Subject: RE: [R] C: drive memory full Hi, Try http://social.technet.microsoft.com/wiki/contents/articles/19295.windows-8-how-to-search-for-large-files.aspx Martyn -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Hiyoshi, Ayako Sent: 17 June 2014 11:40 To: Prof Brian Ripley; r-help@R-project.org Subject: Re: [R] C: drive memory full Dear Professor Ripley, Thank you so much for your quick reply. I tried 'dianame(tempdir())' and removed several 'Rtemp' and all other files. Unfortunately it did not changed C: drive space much. I am really sorry, but could there be other things stored in somewhere in C: drive ? I called IT support, but they could not spot either. Kind regards, Ayako From: Prof Brian Ripley rip...@stats.ox.ac.uk Sent: 17 June 2014 10:37 To: Hiyoshi, Ayako; r-help@R-project.org Subject: Re: [R] C: drive memory full tempdir() is specific to an R session. Start up R and run dirname(tempdir()) and look at that directory. Shut down R, then remove all old files/folders in that directory, especially those beginning with 'Rtmp'. An R process tries to clean up after itself but - it cannot do so if it segfaults - Windows has rules which no other OS has which can result in files being locked and hence not deletable. On 17/06/2014 08:49, Hiyoshi, Ayako wrote: Dear R users, Hello, I am new to R and confused about my PC's memory space after using R a while. My PC is Windows 8, RAM 8GB. I have run some analyses using commands like vglm, aalen(Sruv()), lm()... some regressions. I also use Stata, and when I tried to run Stata (big file), Stata could not do something which used to do because of the lack of memory space. I suspect R's something because R is the only new activity I did recently. I tried to google and found 'tempdir()'. I checked my temporary file but it was empty. Just in case, after running 'unlink(tempdir(),recursive=TRUE)', I restarted my computer, but memory space did not change. But there seems still something big in my C: drive storage and nearly 12GB is eaten. Could it be possible that R saved something somewhere? As I finished analyses, all I need is to erase everything stored so that I can get my memory space back. Thank you so much for your help. Best wishes, Ayako [[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. -- Brian D. Ripley, rip...@stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ 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. This e-mail has been scanned for all viruses by Star. ...{{dropped:4}} __ 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] Difference in coefficients in Cox proportional hazard estimates between R and Stata, why?
Dear R users, Hi, thank you so much for your help in advance. I have been using Stata but new to R. For my paper revision using Aalen's survival analysis, I need to use R, as the command including Aalen's survival seems to be available in R (32-bit, version 3.1.0 (2014-04-10)) but less ready to be used in Stata (version 13/SE). To make sure that I can do basics, I have fitted logistic regression and Cox proportional hazard regression using R and Stata. The data I used were from UCLA R's textbook example page: http://www.ats.ucla.edu/stat/r/examples/asa/asa_ch1_r.htm. http://www.ats.ucla.edu/stat/r/examples/asa/asa_ch1_r.htm. I used this in Stata too. When I fitted logistic regression as below, the estimates were exactly same between R and Stata. Example using logistic regression R: logistic1 - glm(censor ~ age + drug, data=, family = binomial) summary(logistic1) exp(cbind(OR=coef(logistic1), confint(logistic1))) OR 2.5 %97.5 % (Intercept) 1.0373731 0.06358296 16.797896 age 1.0436805 0.96801933 1.131233 drug0.7192149 0.26042635 1.937502 Stata: logistic censor age i.drug OR CI_lower CI_upper age | 1.043681 .96623881.127329 drug |.719215 .26651941.940835 _cons | 1.037373 .065847 16.3431 However, when I fitted Cox proportional hazard regression, there were some discrepancies in coefficient (and exponentiated hazard ratios). Example using Cox proportioanl hazard regression R: cox1 - coxph(Surv(time, censor) ~ drug, age, data=) summary(cox1) Call: coxph(formula = Surv(time, censor) ~ drug + age, data = ) n= 100, number of events= 80 coef exp(coef) se(coef) z Pr(|z|) drug 1.01670 2.76405 0.25622 3.968 7.24e-05 *** age 0.09714 1.10202 0.01864 5.211 1.87e-07 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 exp(coef) exp(-coef) lower .95 upper .95 drug 2.764 0.3618 1.673 4.567 age 1.102 0.9074 1.062 1.143 Concordance= 0.711 (se = 0.042 ) Rsquare= 0.324 (max possible= 0.997 ) Likelihood ratio test= 39.13 on 2 df, p=3.182e-09 Wald test= 36.13 on 2 df, p=1.431e-08 Score (logrank) test = 38.39 on 2 df, p=4.602e-09 Stata: stset time, f(censor) stcox drug age -- _t | Haz. Ratio Std. Err. zP|z| [95% Conf. Interval] -+ drug | 2.563531 .6550089 3.68 0.000 1.553634.229893 age | 1.095852 .02026 4.95 0.000 1.0568541.136289 -- The HR estimates for drug was 2.76 from R, but 2.56 from Stata. I searched in internet for explanation, but could not find any. In parametric survival regression with exponential distribution, R and Stata's coefficients were completely opposite while the values were exactly same (i.e. say 0.08 for Stata and -0.08 for R). I suspected something like this (http://www.theanalysisfactor.com/ordinal-logistic-regression-mystery/) going on, but for Cox proportional hazard regression, i coudl not find any resource helping me. I highly appreciate if anyone could explain this for me, or suggest me resource that I can read. Thank you so much for your help. Best, Ayako [[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.