Re: [R] plot legend: combining filled boxes and lines
This is not quite what you want but you can try this: legend(3, 0.45, legend = c(x1, x2, mean(x1), mean(x2)), col = c(orange, green),pch = c(15,15,-1,-1), lty=c(-1,-1,2,2)) Although pch=22 should draw a filled square with a border - but it draws only the border instead Monica __ Message: 24Date: Mon, 10 Sep 2007 09:05:27 +0300From: Lauri Nikkinen [EMAIL PROTECTED]Subject: [R] plot legend: combining filled boxes and linesTo: [EMAIL PROTECTED]:[EMAIL PROTECTED]Content-Type: text/plain; charset=ISO-8859-1 Hello, I have difficulties combining boxes and lines in plot legend. Isearched previous R-posts and found this (with no solution):http://tolstoy.newcastle.edu.au/R/help/06/07/30248.html. Is there away to avoid boxes behind the line legends? x1 - rnorm(100)x2 - rnorm(100, 2)hist(x1, main = , col = orange,ylab = density, xlab = x, freq= F, density = 55, xlim = c(-2, 5), ylim = c(0, 0.5))par(new = T)hist(x2, main = , col = green, ylab = , xlab = ,axes = F, xlim= c(-2, 5), ylim = c(0, 0.5), density = 45, freq = F) abline(v = mean(x1), col = orange, lty = 2, lwd = 2.5)abline(v = mean(x2), col = green, lty = 2, lwd = 2.5)legend(3, 0.45, legend = c(x1, x2, mean(x1), mean(x2)), col =c(orange, green), fill=c(orange,green, 0, 0), lty = c(0, 0,2, 2), merge = T) ThanksLauri _ Gear up for Halo® 3 with free downloads and an exclusive offer. Its our way of saying thanks for using Windows Live. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] confusion matrix - better code?
Wolfgang, This looks great and certainly puts to shame my code . Thanks, Monica Date: Fri, 7 Sep 2007 21:04:32 +0100 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] CC: r-help@stat.math.ethz.ch Subject: Re: [R] confusion matrix - better code? Dear Monica, try this: cm = table(tr, pr) cm pr tr 1 2 3 1 2 1 0 2 2 1 0 3 0 0 3 4 0 1 0 rowSums(cm) colSums(cm) Best wishes Wolfgang Huber Monica Pisica ha scritto: Hi,I�ve written some code to obtain a confusion matrix when the true classification and the predicted classification are known. Suppose true classification is called �tr� and predicted classification is �pr�. I have 4 classes in tr, but only 3 classes out of 4 are predicted in �pr�. Following is my code, but looks quite �clunky� to me. I wonder if you have any suggestions to improve it.Thanks,Monica -tr - c(1,2,2,3,3,3,2,4,1,1) pr-c(1,2,1,3,3,3,1,2,1,2) dat - data.frame(tr, pr) class - c(1:length(tr)) m - max(c(length(unique(tr)), length(unique(pr for(i in 1:length(class)) { class[i] - sub(' ','',paste(dat[i,1],dat[i,2])) } dat - data.frame(dat, class) mat - matrix(0, nrow=m, ncol=m) for (i in 1:m){ for (j in 1:m){ mat[i,j] - sub(' ','',paste(i,j)) }} cat - matrix(0, nrow=(m+1), ncol=(m+1)) for (i in 1:m){ for(j in 1:m){ cat[i,j]- nrow(dat[dat$class==mat[i,j],]) }} for (i in 1:m){ cat[(m+1),i]-sum(cat[1:m,i]) cat[i,(m+1)]- sum(cat[i,1:m]) cat[(m+1),(m+1)] - sum(cat[1:m,(m+1)]) } cat [,1] [,2] [,3] [,4] [,5] [1,] 2 1 0 0 3 [2,] 2 1 0 0 3 [3,] 0 0 3 0 3 [4,] 0 1 0 0 1 [5,] 4 3 3 0 10The 5th row / col represents the sum on each row / col respectively. _ Gear up for Halo® 3 with free downloads and an exclusive offer. Itâs our way of saying thanks for using Windows Liveâ¢. http://gethalo3gear.com?ocid=SeptemberWLHalo3_WLHMTxt_2 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] confusion matrix - better code?
Michael, Thank you very much. My code is certainly put to shame by yours. I promise to read about factor to see how you use it and why ;-)) I really appreciate your help. Monica Subject: RE: [R] confusion matrix - better code? Date: Fri, 7 Sep 2007 15:36:00 -0500 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] How about this? tab-table(factor(tr,levels=unique(tr)),factor(pr,levels=unique(tr))) tab-rbind(tab,colSums(tab)) tab-cbind(tab,rowSums(tab)) tab 1 2 3 4 1 2 1 0 0 3 2 2 1 0 0 3 3 0 0 3 0 3 4 0 1 0 0 1 4 3 3 0 10 Of course you can add some dimnames for the 5th row and 5th column if you want. dimnames(tab)[[1]][5]-Total dimnames(tab)[[2]][5]-Total tab 1 2 3 4 Total 1 2 1 0 0 3 2 2 1 0 0 3 3 0 0 3 0 3 4 0 1 0 0 1 Total 4 3 3 0 10 Michael Conklin Chief Methodologist - Advanced Analytics MarketTools, Inc. 6465 Wayzata Blvd. Suite 170 Minneapolis, MN 55426 Tel: 952.417.4719 | Mobile:612.201.8978 [EMAIL PROTECTED] MarketTools(r) http://www.markettools.comThis e-mail and any attachments may contain privileged, confidential or proprietary information. If you are not the intended recipient, be aware that any review, copying, or distribution of this e-mail or any attachment is strictly prohibited. If you have received this e-mail in error, please return it to the sender immediately, and permanently delete the original and any copies from your system. Thank you for your cooperation.-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Monica Pisica Sent: Friday, September 07, 2007 2:53 PM To: r-help@stat.math.ethz.ch Subject: [R] confusion matrix - better code? Importance: High Hi, I've written some code to obtain a confusion matrix when the true classification and the predicted classification are known. Suppose true classification is called tr and predicted classification is pr. I have 4 classes in tr, but only 3 classes out of 4 are predicted in pr. Following is my code, but looks quite clunky to me. I wonder if you have any suggestions to improve it. Thanks, Monica - tr - c(1,2,2,3,3,3,2,4,1,1) pr-c(1,2,1,3,3,3,1,2,1,2) dat - data.frame(tr, pr) class - c(1:length(tr)) m - max(c(length(unique(tr)), length(unique(pr for(i in 1:length(class)) { class[i] - sub(' ','',paste(dat[i,1],dat[i,2])) } dat - data.frame(dat, class) mat - matrix(0, nrow=m, ncol=m) for (i in 1:m){ for (j in 1:m){ mat[i,j] - sub(' ','',paste(i,j)) }} cat - matrix(0, nrow=(m+1), ncol=(m+1)) for (i in 1:m){ for(j in 1:m){ cat[i,j]- nrow(dat[dat$class==mat[i,j],]) }} for (i in 1:m){ cat[(m+1),i]-sum(cat[1:m,i]) cat[i,(m+1)]- sum(cat[i,1:m]) cat[(m+1),(m+1)] - sum(cat[1:m,(m+1)]) } cat [,1] [,2] [,3] [,4] [,5] [1,] 2 1 0 0 3 [2,] 2 1 0 0 3 [3,] 0 0 3 0 3 [4,] 0 1 0 0 1 [5,] 4 3 3 0 10 The 5th row / col represents the sum on each row / col respectively. _ Gear up for Halo(r) 3 with free downloads and an exclusive offer. It's our way of saying thanks for using Windows Live(tm). [[alternative HTML version deleted]] _ é. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] computing distance in miles or km between 2 street
Phil, If you have only a list of addresses and nothing else - i have to recognize i am lost. But if you have more info you can use a GIS software and it will calculate your distance automatically for all your addresses. To have your distance in miles or Km you need to have a projection in your data which will establish your units. The very basic principle is that for each address you have a set of coordinates, x, y and you actually use these to calculate distances. If your file is for exaple a point shape file (standard for ESRI ArcGIS products) you can very simply perform this task using either shortest driving route or as the crow flies - again depending on what other info you have in the file. A shape file is actually a group of files with with data attributes, projection info and so on - so even if you don't see xy coordinates, they actually are imbeded in the file. I suspect Mapquest or any other mapping web product has a database with all those addresses with xy coordinates. The user needs to know only the address and behind doors there is an sql process which selects particular addresses together with all the other attributes attached to it and calculate distances because it knows coordinates, a network of roads and so on. I am not sure this helps but at least maybe gives you some ideas where to look next. Monica Message: 53Date: Thu, 06 Sep 2007 14:42:32 -0400From: Philip James Smith [EMAIL PROTECTED]Subject: [R] computing distance in miles or km between 2 streetaddressesTo: [EMAIL PROTECTED]: [EMAIL PROTECTED]Content-Type: text/plain; charset=ISO-8859-1; format=flowed Hi R-ers: I need to compute the distance between 2 street addresses in either km or miles. I do not care if the distance is a shortest driving route or if it is as the crow flies. Does anybody know how to do this? Can it be done in R? I have thousands of addresses, so I think that Mapquest is out of the question! Please rely to: [EMAIL PROTECTED] Thank you!Phil Smith _ Hotmail®. NOW with 5GB storage. ration_HM_mini_5G_0907 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] confusion matrix - better code?
Hi, Ive written some code to obtain a confusion matrix when the true classification and the predicted classification are known. Suppose true classification is called tr and predicted classification is pr. I have 4 classes in tr, but only 3 classes out of 4 are predicted in pr. Following is my code, but looks quite clunky to me. I wonder if you have any suggestions to improve it. Thanks, Monica - tr - c(1,2,2,3,3,3,2,4,1,1) pr-c(1,2,1,3,3,3,1,2,1,2) dat - data.frame(tr, pr) class - c(1:length(tr)) m - max(c(length(unique(tr)), length(unique(pr for(i in 1:length(class)) { class[i] - sub(' ','',paste(dat[i,1],dat[i,2])) } dat - data.frame(dat, class) mat - matrix(0, nrow=m, ncol=m) for (i in 1:m){ for (j in 1:m){ mat[i,j] - sub(' ','',paste(i,j)) }} cat - matrix(0, nrow=(m+1), ncol=(m+1)) for (i in 1:m){ for(j in 1:m){ cat[i,j]- nrow(dat[dat$class==mat[i,j],]) }} for (i in 1:m){ cat[(m+1),i]-sum(cat[1:m,i]) cat[i,(m+1)]- sum(cat[i,1:m]) cat[(m+1),(m+1)] - sum(cat[1:m,(m+1)]) } cat [,1] [,2] [,3] [,4] [,5] [1,]21003 [2,]21003 [3,]00303 [4,]01001 [5,]4330 10 The 5th row / col represents the sum on each row / col respectively. _ Gear up for Halo® 3 with free downloads and an exclusive offer. Its our way of saying thanks for using Windows Live. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] write geotiff with projection - RGDAL package
Hi, Doing more search i've discovered package RGDAL that can write a geotiff file with projection. I saved a geotiff file in UTM projection and if i read the file back in R and check the projection seems that everything is OK. But if i load the file in ArcGIS (ESRI product) i get the warning that the file is missing spatial reference so it cannot be projected, but it is displayed correctly. I guess somewhere i am doing a mistake when i define the projection in R. My code follows: data.grid - read.csv(x, header=TRUE) gridded(data.grid) = ~East.m.+North.m. proj4string(data.grid) = CRS(+proj=tmerc +lat_0=0.000 +lon_0=-81.000 +k=0.9996 +x_0=50.00 +y_0=0.000 +ellps=GRS80 +units=m) tr - e:\\JELA_veg\\test_gtiff\\test.tif writeGDAL(data.grid[class.pca], tr) mg3 - readGDAL(tr) proj4string(mg3) [1] +proj=utm +zone=17 +ellps=GRS80 +units=m +no_defs I will really appreciate if anybody can point me in the right dirrection. Thanks, Monica _ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] larger decimal numbers get rounded ....
Hi, I am sure there is a reason but .. why larger decimal numbers get rounded to the nearest integer? Example: a - 3308000.5 a [1] 3308001 I would like my numbers to be decimals since they do represent coordinates and i don't want them rounded how can i keep them as they are? Thanks, Monica _ e=wlmailtagline [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] For loop with if else statement
Hans, I think your problem is that you don't use the variable which takes different values in your if statement your i changes values and has really nothing to do with your x variable (except the length part ). Also all the other variables need to be declared somehow - otherwise how can you store values in them??? So your first code may be something like that: t=c(1,2) for(i in 1:length(t)){ if (i==1) t[i]=i+1 else t[i]=i } t[1] 2 2 and your second code: a = c(1,2) b=c(1,2)for(i in 1:2){if (i==1){a[i]=ib[i]=i-1} else{ a[i]=i+1b[i]=i}c-list(a=a,b=b)} c$a[1] 1 3 c$b[1] 0 2 Also when you have only 2 possible values for i i don't think the second if is necessary. I hope this helps a little, although my explanation is not necessarily the best. Monica -- Message: 16Date: Tue, 4 Sep 2007 15:59:54 +0200From: Hans Ole ?rka [EMAIL PROTECTED]Subject: [R] For loop with if else statementTo: 'r-help@stat.math.ethz.ch' r-help@stat.math.ethz.chMessage-ID:[EMAIL PROTECTED]Content-Type: text/plain; charset=iso-8859-1 Hi,I try to make a simple for loop with a if else statement (First example - Below) and extend it to a more complex loop (Second example). However, my results #First example:x=c(1,2)t=for(i in 1:length(x)){if (x==1){a=x+1}elseif (x==2){a=x}} Returned from R:Warning messages:1: the condition has length 1 and only the first element will be used in: if (x == 1) {2: the condition has length 1 and only the first element will be used in: if (x == 1) { t[1] 2 3 However, the result i had liked to get was t=c(2,2) i.e. using the first function (a=x+1) for x[1] and (a=x) for x[2]. I can remove the Warnings by making: if (x[i]==1) etc. but this! do not make the results any better. #Second example:x=c(1,2)t-for(i in 1:length(x)){if (x==1){a=xb=x-1}elseif (x==2){a=x+1b=x}b-list(a=a,b=b)} Returned from R:Warning messages:1: the condition has length 1 and only the first element will be used in: if (x == 1) {2: the condition has length 1 and only the first element will be used in: if (x == 1) { t$a[1] 1 2 $b[1] 0 1 The result i like to get are $a =c(1,3) and $b=c(0,2) Probably there are couple of things that I do wrong and I appreciate all help! _ Discover the new Windows Vista [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] geotiff or tiff files with world files
Hi, I have a matrix of data which i can vizualize as an image - for example. I would like to save this image as a geotiff file or at a tiff file with a world file which holds the projection of my data (ultimately the data represent a map of some sort). I know i can save the data as an ESRI grid, but i am not interested in that. I wonder if anybody knows about any code which will help me do that. Thanks in advance, Monica _ s. It's easy! aspxmkt=en-us [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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 to signal the end of the table?
Well, i am surprise you have problems to read a table that is small enough to be opened entirely in Excel. I work with csv tables with hundreds of thousands of rows, and sometimes even millions with no problems except that sometimes i have to wait up to 1 or 2 minutes for R to read the table. I use the command read.csv. If your tables are always small enough to be read in Excel, the limit of number of rows in Excel is about 64000 or something of that sort (maybe 65000 ) so you can use this number as a limit for your number of rows although you may have to clean-up your data.frame afterwards. I work on a Windows machine with 4 Gb DRAM - just for comparison. I hope this helps, Monica Message: 88Date: Wed, 29 Aug 2007 10:41:05 -0700From: Yuchen Luo [EMAIL PROTECTED]Subject: [R] How to signal the end of the table?To: r-help@stat.math.ethz.chMessage-ID:[EMAIL PROTECTED]Content-Type: text/plainI am using a for loop to read a table row by row and I have to specify howmany records are there in the table. I need to read row by row because thetable is huge and the memory not large enough for the whole table.:number.of.records=100fp=file(abc.csv,r)pos=seek(fp, rw=read)for (i in 1:number.of.record){current.row=scan(file=fp, sep=',', what=list(count=1, cusip6=, idate=1,spread=1.1, vol252=1.1, vol1000=1.1, st_debt=1.1, lt_debt=1.1 , total_liab=1.1, cr=1.1, shrout=1.1, prc=1.1, mkt_cap=1.1, rtng=1.1, sec=1.1, cr3m=1.1,cr5y=1.1, ust3m=1.1, ust5y=1.1), flush=TRUE, nlines=1,quiet=T)...}I need to know the number of records in the table and put it in the variablenamed nu! mber.of.records. When I have a new table that I do not know howmany records it has, I use excel to open the file to figure it out and putit in variable number.of.records. I often have many tables to try andevery one of them has thousands of recordsit takes a lot of time andtrouble to adjust the code every time I read a different table.I am wondering if I can change the for loop to a while loop:while (the end of the table has not been reached){current.row=scan(file=fp, sep=',', what=list(count=1, cusip6=, idate=1,spread=1.1, vol252=1.1, vol1000=1.1, st_debt=1.1, lt_debt=1.1 , total_liab=1.1, cr=1.1, shrout=1.1, prc=1.1, mkt_cap=1.1, rtng=1.1, sec=1.1, cr3m=1.1,cr5y=1.1, ust3m=1.1, ust5y=1.1), flush=TRUE, nlines=1,quiet=T)...}The problem is how to articulate while (the end of the table has not beenreached), or equivalently, how to signal the end of the table?Best WishesYuchen Luo [[alternative HTML version deleted]] _ Discover the new Windows Vista [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] Cleaning up the memory
Hi, I have 4 huge tables on which i want to do a PCA analysis and a kmean clustering. If i run each table individually i have no problems, but if i want to run it in a for loop i exceed the memory alocation after the second table, even if i save the results as a csv table and i clean up all the big objects with rm command. To me it seems that even if i don't have the objects anymore, the memory these objects used to occupy is not cleared. Is there any way to clear up the memory as well? I don't want to close R and start it up again. Also i am running R under Windows. thanks, Monica _ [[trailing spam removed]] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] Cleaning up the memory
Thanks! I will look into ... I have 4 GB RAM, and i was monitoring the memory with Windows task manager so i was looking how R gets more and more memory allocation from less than 100Mb to 1500Mb . My initial tables are between 30 to 80 Mb and the resulting tables that incorporate the initial tables plus PCA and kmeans results are inbetween 50 to 200MB or thereabouts! And yes, i don't really care about memory allocation in detail - what i want is to free that memory after every cycle ;-) Although, after i didn't do anything in R and it was idle for more than 30 min. the memory allocation according to Task manager dropped to 15 Mb . which is good - but i cannot wait inbetween cycles half an hour though . Again thanks, Monica Date: Fri, 10 Aug 2007 18:28:07 +0100 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] CC: r-help@stat.math.ethz.ch Subject: Re: [R] Cleaning up the memory On Fri, 10 Aug 2007, Monica Pisica wrote:Hi, I have 4 huge tables on which i want to do a PCA analysis and a kmean clustering. If i run each table individually i have no problems, but if i want to run it in a for loop i exceed the memory alocation after the second table, even if i save the results as a csv table and i clean up all the big objects with rm command. To me it seems that even if i don't have the objects anymore, the memory these objects used to occupy is not cleared. Is there any way to clear up the memory as well? I don't want to close R and start it up again. Also i am running R under Windows. See ?gc, which does the clearing. However, unless you study the memory allocation in detail (which you cannot do from R code), you don't actually know that this is the problem. More likely is that you have fragmentation of your 32-bit address space: see ?Memory-limits. Without any idea what memory you have and what 'huge' means, we can only make wild guesses. It might be worth raising the memory limit (the --max-mem-size flag).thanks, Monica _ [[trailing spam removed]] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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, [EMAIL PROTECTED] 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, UK Fax: +44 1865 272595 _ Messenger Café open for fun 24/7. Hot games, cool activities served daily. Visit now. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] problems saving jpg files
Hi, I have a batch routine that does PCA on a series of files and saves the results as a csv file, and the respective graphs as pdf and jpg. While pdf's are fine, jpg files have a light grey background does not matter what color i set the bg param. I am running this on a PC with 4 GB RAM - if this makes any difference. My command is as follows: dev.print(jpeg, file=filejpg, width=1024, height=768, quality = 100, bg = white) I would appreciate if you have any explanations, and yes, i did read the help files this time ;-))) Thanks, Monica _ [[trailing spam removed]] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] - round() strange behaviour
Hi, I am getting some strange results using round - it seems that it depends if the number before the decimal point is odd or even For example: round(1.5)[1] 2 round(2.5)[1] 2 While i would expect that round(2.5) be 3 and not 2. Do you have any explanation for that? I really appreciate your input, Monica _ [[trailing spam removed]] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] - round() strange behaviour
Hi again, Mea culpa for not reading help pages before hand - but one would not go there when the function syntax is obvious and known besides other programming languages (for example IDL) with same function do not round to the next even number so i do get 3 for round(2.5), and i didn't realize that it is normal for R to give a 2 instead of 3. Date: Thu, 2 Aug 2007 22:38:49 +0200 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] CC: r-help@stat.math.ethz.ch Subject: Re: [R] - round() strange behaviour On Thu, 2 Aug 2007, Monica Pisica wrote:Hi, I am getting some strange results using round - it seems that it depends if the number before the decimal point is odd or even For example:round(1.5)[1] 2 round(2.5)[1] 2 While i would expect that round(2.5) be 3 and not 2. Do you have any explanation for that? Yes: you obviously did not read the man page! Please do. Z I really appreciate your input, Monica _ [[trailing spam removed]] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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. _ Messenger Café open for fun 24/7. Hot games, cool activities served daily. Visit now. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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] - ICA for less common data
Hi everyone, I am not sure this is the appropriate list I should put this question to, but I hope you will re-direct me to the most appropriate one if necessary. I am doing an independent component analysis on a dataset that represents different metrics for patchreefs such as depth, area, volume, relative relief, shape index and rugosity. Doing different multivariate analyses and correlations among variables we discovered that the average reef depth data is heavily bi-modal, and rugosity behaves differently in each of the depth populations. Other reef metrics behave differently with depth as well. Since not all metrics are really independent we did a PCA analysis followed by cluster analysis and we tried to compare the results with the results from the depth analysis. It was not too conclusive I am afraid, and trying to understand the results I came across independent component analysis (ICA). So .. Ive run it on a combination of principal components and it seems that certainly we have 2 independent components that keep popping up (if I can use this expression) when we run the analysis with 2, 3, or 4 components. So I guess these 2 components are the strongest ones . If I can say so. My next question is . How can I relate these 2 components to the initial data??? Ive plotted each component and if I add a loess line to each, visually it seems that one independent component is an unknown function of rugosity while the other component is an unknown function of reef geometry and depth. But, of course, I would like something more than a visual similarity. Also the 2 independent components seem to split the data in 3 classes, rather than 2, as the analysis of the depth data suggested. Looking back at the depth histogram it is obvious that there are some data that actually are not quite modeled by the 2 mixing functions I came up with. These data correspond to the deepest patch reefs, a category clearly singled out by ICA classification. The bottom line is that I am trying to understand what each independent component tells me about the patch reefs and how I can relate that to the patch reef morphometrics, biology, other factors that impact some reefs but not others, etc. If you have any clarifying thoughts or if you know about any other literature about the subject that can help (except articles that deal with ICA and image analysis or wave form data) I will really appreciate. Thank you very much for your consideration, Monica _ Mortgage refinance is Hot. *Terms. Get a 5.375%* fix rate. Check savings __ R-help@stat.math.ethz.ch 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] ICA for less common data
Hi everyone, I am not sure this is the appropriate list I should put this question to, but I hope you will re-direct me to the most appropriate one if necessary. I am doing an independent component analysis on a dataset that represents different metrics for patchreefs such as depth, area, volume, relative relief, shape index and rugosity. Doing different multivariate analyses and correlations among variables we discovered that the average reef depth data is heavily bi-modal, and rugosity behaves differently in each of the depth populations. Other reef metrics behaves differently with depth as well. Since not all metrics are really independent we did a PCA analysis followed by cluster analysis and we tried to compare the results with the results from the depth analysis. It was not too conclusive I am afraid, and trying to understand the results I came across independent component analysis (ICA). So .. Ive run it on a combination of principal components and it seems that certainly we have 2 independent components that keep popping up (if I can use this expression) when we run the analysis with 2, 3, or 4 components. So I guess these 2 components are the strongest ones . If I can say so. My next question is . How can I relate these 2 components to the initial data??? Ive plotted each component and if I add a loess line to each, visually it seems that one independent component is an unknown function of rugosity while the other component is an unknown function of reef geometry and depth. But, of course, I would like something more than a visual similarity. Also the 2 independent components seem to split the data in 3 classes, rather than 2, as the analysis of the depth data suggested. Looking back at the depth histogram it is obvious that there are some data that actually are not quite modeled by the 2 mixing functions I came up with. These data correspond to the deepest patch reefs, a category clearly singled out by ICA classification. The bottom line is that I am trying to understand what each independent component tells me about the patch reefs and how I can relate that to the patch reef morphometrics, biology, other factors that impact some reefs but not others, etc. If you have any clarifying thoughts or if you know about any other literature about the subject that can help (except articles that deal with ICA and image analysis or wave form data) I will really appreciate. Thank you very much for your consideration, Monica _ The average US Credit Score is 675. The cost to see yours: $0 by Experian. __ R-help@stat.math.ethz.ch 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] Kmeans cluster analysis
Hi Nataniel, As far as i know there is a package called clustTool which has a very nice interface with the capability to do different cluster analyses. It also prodused a plot of each cluster and the mean for each cluster of each variable - and i guess this is what you are after! But depending of which parameters you are using for the cluster analysis, the package is extremely slow if you have more than 5000 datapoints. Maybe you can take the function apart to see where and what generates the plot and use that for your analysis. I hope this helps, Monica Palaseanu-Lovejoy Message: 35 Date: Tue, 10 Apr 2007 19:51:24 + (GMT) From: nathaniel Grey [EMAIL PROTECTED] Subject: [R] Kmeans cluster analysis To: r-help@stat.math.ethz.ch Message-ID: [EMAIL PROTECTED] Content-Type: text/plain Hello, I have a data-set containing 22 variables, after appropriate transformations etc I ran a kmeans cluster analysis for 4 clusters , I ran it 20 times to find a result with the lowest within sum of squares. My question is how best do I go about finding out what the characteristics are of each cluster? Is one cluster dominated by a particular set of variables or by a particular variable? The only way I know is to to look at the means for each variable for each cluster, but as there are 22 variables this is time consuming. Is there a way to graphically represent the clusters in relation to the variables...if so I might need some guidance on the coding as I am new to the R environment. Any advice and direction would be gratefully received. best wishes, Nataniel Grey _ Live! http://clk.atdmt.com/MRT/go/mcrssaub0050001411mrt/direct/01/ __ R-help@stat.math.ethz.ch 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] strange error in robust package
Hi everybody, I am using quite frequently the robust package and until now i never had any problems. Actually last time i used it was last Friday very successfully. Anyway, today anytime i want to use the function fit.models i get the following error even if i use the example form the help file: data(woodmod.dat) woodmod.fm - fit.models(list(Robust = covRob, Classical = cov), data = woodmod.dat) Error in donostah(data, control) : object .Random.seed not found Error in model.list[[i]] : subscript out of bounds Does anybody know what is wrong? Thanks, Monica Palaseanu-Lovejoy USGS / ETI Pro St. Petersburg, FL _ Spaces __ R-help@stat.math.ethz.ch 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] problems with plot.data.frame
Hi list, I have a question about 'plot'. I am trying to plot values registered every month - or every other month. If i build a data.frame called mydata like this (as an example) jan 3 1 7 mar 2 4 2 may 1 3 2 jul3 7 4 sep 5 2 3 nov 3 1 5 and use the command line: plot(mydata[c(1,3)]) I get a graph that has on the x axis my months in alphabetical order - which i don't want, and instead of points i have thick horizontal lines. I've tried everything i could and understood from the R help files to give me points and on x axis the month in my order instead of alpha order. No success. What is the trick? I fixed the month order by using numerals in front of them like 01, 03, ... etc, but this is not an elegant solution. Any help will be much appreciated. Monica __ R-help@stat.math.ethz.ch 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] problems with plot.data.frame
Hi again, OK i came up with this after i got few good sugegstions. First my data.frame actually looks like that (Thanks for clarifications to Prof. Brian Ripley) V1 V2 V3 V4 1 jan 3 1 7 2 mar 2 4 2 3 may 1 3 2 4 jul 3 7 4 5 sep 5 2 3 6 nov 3 1 5 What i want: 1. On x axis i want the ticks with labels column V1 in that order and not alpha order. 2. i want points to represent the data, not horizoltal bars as a box-plot with only one value as it will plot if i use plot.data.frame Note. In my table i already have the order i want, but if i wouldn't have it prof. Ripley's sugegstion is very welcome. What i've done in the end: plot (mydata$V3, xlab=month) axis (side=1, at=c(1:6), labels=c(1:6), ticks=TRUE, col.axis=white) month.label - as.character(mydata[[1]]) axis(side=1, at=c(1:6), labels = month.label, ticks=TRUE) This is not an elegant solution but i get the graph i wanted. If anybody has a better solution certainly i would like to see it. thanks you again for all your help, Monica __ R-help@stat.math.ethz.ch 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.