Hi , Thanks again for helping me out. Here is the code I am using Ad_1 <- subset(Attrition_data_1,Attrition_ind=="1") Ad_0 <- subset(Attrition_data_1,Attrition_ind=="0")
s1<-sample(1:dim(Ad_0)[1],0.8*dim(Ad_0)[1])# 80% of the non-attrites s2<-sample(1:dim(Ad_1)[1],0.8*dim(Ad_1)[1])# 80% of attritees s3<- Ad_0 [-s1,] summary(s3) s4<- Ad_1 [-s2,] summary(s4) traindata <- rbind(s1,s2) testdata <- rbind(s3,s4) this works for the test dataset but throws up an error of Warning message: In rbind(s1, s2) : number of columns of result is not a multiple of vector length (arg 2) I understand that I am trying to append vectors of unequal vector lengths but don't know how to work around this process. Would you help please Thanks, Dwaipayan From: Jessica Streicher [mailto:j.streic...@micromata.de] Sent: Wednesday, April 25, 2012 9:25 PM To: Dwaipayan Dasgupta Cc: r-help@r-project.org Subject: Re: [R] Splitting data into test and train (80:20) kepping attributes similar Don't know whats wrong there (except if you're using the eclipse R plugin on a mac like me and the window for choosing the download site doesn't pop up.. did it?^^) Anyway, you could just split all of your data into 2 datasets, one that has all the data labeled 0, the other for all labeled 1, then take a random 80% of both, put them back together into the 80% data, and put the rest back together to form the 20%. Since i don't know your data, heres an example: M<-cbind(c(rep(0,10),rep(1,10)),1:20) > M [,1] [,2] [1,] 0 1 [2,] 0 2 [3,] 0 3 [4,] 0 4 [5,] 0 5 [6,] 0 6 [7,] 0 7 [8,] 0 8 [9,] 0 9 [10,] 0 10 [11,] 1 11 [12,] 1 12 [13,] 1 13 [14,] 1 14 [15,] 1 15 [16,] 1 16 [17,] 1 17 [18,] 1 18 [19,] 1 19 [20,] 1 20 index1<-which(M[,1]==1) > index1 [1] 11 12 13 14 15 16 17 18 19 20 > M1<-M[index1,] > M1 [,1] [,2] [1,] 1 11 [2,] 1 12 [3,] 1 13 [4,] 1 14 [5,] 1 15 [6,] 1 16 [7,] 1 17 [8,] 1 18 [9,] 1 19 [10,] 1 20 > M0<-M[-index1,] > M0 [,1] [,2] [1,] 0 1 [2,] 0 2 [3,] 0 3 [4,] 0 4 [5,] 0 5 [6,] 0 6 [7,] 0 7 [8,] 0 8 [9,] 0 9 [10,] 0 10 > s1<-sample(1:dim(M1)[1],0.8*dim(M1)[1]) > s1 [1] 10 3 5 9 2 6 8 7 > s0<-sample(1:dim(M0)[1],0.8*dim(M0)[1]) > s0 [1] 8 10 9 3 7 4 2 1 > data80<-rbind(M1[s1,],M0[s0,]) > data80 [,1] [,2] [1,] 1 20 [2,] 1 13 [3,] 1 15 [4,] 1 19 [5,] 1 12 [6,] 1 16 [7,] 1 18 [8,] 1 17 [9,] 0 8 [10,] 0 10 [11,] 0 9 [12,] 0 3 [13,] 0 7 [14,] 0 4 [15,] 0 2 [16,] 0 1 > data20<-rbind(M1[-s1,],M0[-s0,]) > data20 [,1] [,2] [1,] 1 11 [2,] 1 14 [3,] 0 5 [4,] 0 6 which is probably not how you really do things efficiently, but it should work. greetings Jessi Am 25.04.2012 um 17:18 schrieb Dwaipayan Dasgupta: Thank you so much for replying. I tried what you said but it still throws the same error i.e could not find function "sample.split" Might be because of the version of R I am running (R version 2.12.2).i do not have admin rights to upgrade to the newest version. Is there anything else I can try? Im trying to split my data into 80:20 keeping the ratio of 0,1 in the Y variable(binary) constant. -----Original Message----- From: r-help-boun...@r-project.org<mailto:r-help-boun...@r-project.org> [mailto:r-help-boun...@r-project.org] On Behalf Of Jessica Streicher Sent: Wednesday, April 25, 2012 7:17 PM To: r-help@r-project.org<mailto:r-help@r-project.org> Subject: Re: [R] Splitting data into test and train (80:20) kepping attributes similar Well, it throws an error, because there is no such function in default R. A bit of googling showed it might be the one in the caTools package. execute this: install.packages("caTools") library(caTools) before executing your code Am 25.04.2012 um 12:39 schrieb Dwaipayan Dasgupta: Hi, Could someone help me with this please , im trying to use Y = Attrition_data[,1] # extract labels from the data msk = sample.split (Y, SplitRatio=3/4) table(Y,msk) to do the splitting but it keeps throwing up and error Error: could not find function "sample.split" Could you please help Thanks in advance doy -----Original Message----- From: r-help-boun...@r-project.org<mailto:r-help-boun...@r-project.org> [mailto:r-help-boun...@r-project.org] On Behalf Of Dwaipayan Dasgupta Sent: Tuesday, April 24, 2012 9:08 PM To: r-help@r-project.org<mailto:r-help@r-project.org> Subject: [R] Splitting data into test and train (80:20) kepping attributes similar Hi, I am trying to do some predictive modeling around attrition and want to split the dataset into test and train (80:20) and keep the ratio of attritees:non attrites same. In my dataset the attrition indicator is coded as 0(for non-attritees) and 1 (for attritees) and I want to keep the ratio of 0's to 1 similar. I apologize for this trivial question but this is my second week with R. Thanks, Doy American Express made the following annotations on Tue Apr 24 2012 08:38:50 ****************************************************************************** "This message and any attachments are solely for the intended recipient and may contain confidential or privileged information. If you are not the intended recipient, any disclosure, copying, use, or distribution of the information included in this message and any attachments is prohibited. If you have received this communication in error, please notify us by reply e-mail and immediately and permanently delete this message and any attachments. Thank you." American Express a ajouté le commentaire suivant le Tue Apr 24 2012 08:38:50 Ce courrier et toute pièce jointe qu'il contient sont réservés au seul destinataire indiqué et peuvent renfermer des renseignements confidentiels et privilégiés. Si vous n'êtes pas le destinataire prévu, toute divulgation, duplication, utilisation ou distribution du courrier ou de toute pièce jointe est interdite. Si vous avez reçu cette communication par erreur, veuillez nous en aviser par courrier et détruire immédiatement le courrier et les pièces jointes. Merci. ****************************************************************************** ------------------------------------------------------------------------------- [[alternative HTML version deleted]] American Express made the following annotations on Wed Apr 25 2012 03:39:08 ****************************************************************************** "This message and any attachments are solely for the intended recipient and may contain confidential or privileged information. If you are not the intended recipient, any disclosure, copying, use, or distribution of the information included in this message and any attachments is prohibited. If you have received this communication in error, please notify us by reply e-mail and immediately and permanently delete this message and any attachments. Thank you." American Express a ajouté le commentaire suivant le Wed Apr 25 2012 03:39:08 Ce courrier et toute pièce jointe qu'il contient sont réservés au seul destinataire indiqué et peuvent renfermer des renseignements confidentiels et privilégiés. Si vous n'êtes pas le destinataire prévu, toute divulgation, duplication, utilisation ou distribution du courrier ou de toute pièce jointe est interdite. Si vous avez reçu cette communication par erreur, veuillez nous en aviser par courrier et détruire immédiatement le courrier et les pièces jointes. Merci. ****************************************************************************** ------------------------------------------------------------------------------- ______________________________________________ R-help@r-project.org<mailto: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<mailto: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. American Express made the following annotations on Wed Apr 25 2012 08:18:52 ****************************************************************************** "This message and any attachments are solely for the intended recipient and may contain confidential or privileged information. If you are not the intended recipient, any disclosure, copying, use, or distribution of the information included in this message and any attachments is prohibited. If you have received this communication in error, please notify us by reply e-mail and immediately and permanently delete this message and any attachments. Thank you." American Express a ajouté le commentaire suivant le Wed Apr 25 2012 08:18:52 Ce courrier et toute pièce jointe qu'il contient sont réservés au seul destinataire indiqué et peuvent renfermer des renseignements confidentiels et privilégiés. Si vous n'êtes pas le destinataire prévu, toute divulgation, duplication, utilisation ou distribution du courrier ou de toute pièce jointe est interdite. Si vous avez reçu cette communication par erreur, veuillez nous en aviser par courrier et détruire immédiatement le courrier et les pièces jointes. Merci. ****************************************************************************** ------------------------------------------------------------------------------- American Express made the following annotations on Thu Apr 26 2012 03:56:52 ****************************************************************************** "This message and any attachments are solely for the intended recipient and may contain confidential or privileged information. If you are not the intended recipient, any disclosure, copying, use, or distribution of the information included in this message and any attachments is prohibited. If you have received this communication in error, please notify us by reply e-mail and immediately and permanently delete this message and any attachments. Thank you." American Express a ajouté le commentaire suivant le Thu Apr 26 2012 03:56:52 Ce courrier et toute pièce jointe qu'il contient sont réservés au seul destinataire indiqué et peuvent renfermer des renseignements confidentiels et privilégiés. Si vous n'êtes pas le destinataire prévu, toute divulgation, duplication, utilisation ou distribution du courrier ou de toute pièce jointe est interdite. Si vous avez reçu cette communication par erreur, veuillez nous en aviser par courrier et détruire immédiatement le courrier et les pièces jointes. Merci. ****************************************************************************** ------------------------------------------------------------------------------- [[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.
