Re: [R] How a clustering algorithm in R can end up with negative silhouette values?

> ABABAEI, Behnam > on Mon, 22 Feb 2016 16:15:32 + writes: > Thank you Martin. > I finally came up with this idea: use clara with 100 samples of the size of 1000, then use the clusters as initial runs for kmeans. I think this combines the advantages of clara and kmeans.

Re: [R] How to merge two tables

Hi Xiyan, It looks like your tables have different numbers of cases. There are: 66 DEAD FEMALES in "cross" 56 DEAD FEMALES in "age" 48 NON-DEAD FEMALES in "cross" 58 NON-DEAD FEMALES in "age" and so on. Perhaps there is some mistake with the counts. If this is the problem you could expand the co

[R] Password-Shiny

Hi R users, Please anyone help me how to create password access in shiny Thanks and Regards Venkatesan [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/list

[R] Fwd: Shiny-Wordcloud

Hi R users, I need Shiny *server and UI* code for creating Uni gram,Bi gram,and Trig ram. for Word cloud from my desktop data. I gone through this link: http://shiny.rstudio.com/gallery/word-cloud.html It contains the source data from some where, but i need to use these word cloud for my *DESKT

Re: [R] Tables, knitr markdown

On 22/02/2016 6:19 PM, Santosh wrote: Sorry.. I forgot to mention that I wanted it be published in MS Word, because it goes into a Report this is prepared using MS Word. I can't help you with that. Hence,the above effort.. yes, it's a lot easier to send it to Latex.. I was also wondering if

[R] majority guessing

dear there what the steps I can find the knn by using majority guessing. thanks. [[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 rea

Re: [R] FD package

Im sorry for everything. I didnt mean to make you loose your time, its just im really new at r and i'm still trying to understand some things. plus my english is not great :/ I'm really sorry. My problem is solved, thank you for your help. Kind regards Fábio Monteiro 2016-02-22 19:54 GMT+00:0

Re: [R] Tables, knitr markdown

On Mon, Feb 22, 2016 at 3:36 PM, Santosh wrote: > Thanks, Gergely.. I wonder if it allows to insert lines etc as sent in > previous email which might need some additional preprocessing.. AFAIK that's not possible, as pandoc's markdown has no markup to add horizontal/vertical lines in tables a

Re: [R] Tables, knitr markdown

Thanks, Gergely.. I wonder if it allows to insert lines etc as sent in previous email which might need some additional preprocessing.. Best, Santosh On Mon, Feb 22, 2016 at 3:27 PM, Gergely Daróczi wrote: > On Mon, Feb 22, 2016 at 1:55 PM, Duncan Murdoch > wrote: > > > > On 22/02/2016 3:46

Re: [R] Tables, knitr markdown

On Mon, Feb 22, 2016 at 1:55 PM, Duncan Murdoch wrote: > > On 22/02/2016 3:46 PM, Santosh wrote: >> >> Just figured out.. >> >> as.data.frame(as.matrix(),stringsAsFactors=F) >> >> could work! :) > > > Why do you want to produce Markdown output? the tables package (lowercase > t!) can produce out

Re: [R] Tables, knitr markdown

Sorry.. I forgot to mention that I wanted it be published in MS Word, because it goes into a Report this is prepared using MS Word. Hence,the above effort.. yes, it's a lot easier to send it to Latex.. I was also wondering if it is possible to add "\hline" separating the categories in a table..

Re: [R] Tables, knitr markdown

On 22/02/2016 3:46 PM, Santosh wrote: Just figured out.. as.data.frame(as.matrix(),stringsAsFactors=F) could work! :) Why do you want to produce Markdown output? the tables package (lowercase t!) can produce output in either LaTeX or HTML. Just tell knitr to leave the output alone, e.g. f

Re: [R] Tables, knitr markdown

Just figured out.. as.data.frame(as.matrix(),stringsAsFactors=F) could work! :) On Mon, Feb 22, 2016 at 12:17 PM, Santosh wrote: > Dear Rxperts.. > I am able to generate tables using Tables R package.. > However, when I have been unsuccessful in using kable (from knitr package) > to generate

[R] lm-step: use train-data model to validate test-data

I have model-data named as: model that is split as model.T(train) and model.V(test or validation). The least square model (from lm to step) is built withmodel.T and I like to see how model.T is robust by comparing predicted model.V toactual model.V. How do I get score for model.V based on model

[R] Tables, knitr markdown

Dear Rxperts.. I am able to generate tables using Tables R package.. However, when I have been unsuccessful in using kable (from knitr package) to generate the table in R markdown script.. It's because the output generated by "tabular" in Tables package is of class "tabular". The kable function in

Re: [R] ReporteRs R package installation issues in R.3.2.3 (Windows)

Thanks so much for your response.. Would try that! Santosh On Mon, Feb 22, 2016 at 12:45 AM, Uwe Ligges < lig...@statistik.tu-dortmund.de> wrote: > I guess you are using a 64 bit version of R for Windows but you have only > a 32-bit installation of Java. Please install a 64-bit Java. > > Best, >

Re: [R] FD package

"data" is the name of a function in base R. It is not a good idea to use that as the name of an actual data object (to which the "$" operator is being applied here). It is not clear from what you have provided what variable names you are working with... you are not communicating yet using repro

Re: [R] How to merge two tables

I can see no coherent way to merge these two tables. They do not appear to have consistent definitions for uniqueness of individual rows. Nor do they have consistent column definitions. If you think they do, you will need to be more clear in your question about how you want them to be merged.

Re: [R] Grep Help

I see numerous backticks in your code, not quotes. "`" and "'" are not the same. Backticks are not string delimiters. As for valid names: look at the help page for make.names(). HTH, Boris On Feb 22, 2016, at 1:32 PM, Burhan ul haq wrote: > Hi, > > # 1) I have read in a CSV file > > df =

[R] How to merge two tables

Dear all, I am currently studying categorical data analysis, if I have two tables: R> cross sex cross death count 1 FEMALE WEF YES26 2MALE WEF YES14 3 FEMALE OGG YES32 4MALE OGG YES43 5 FEMALE TGA YES 8 6MALE TGA YES10 7 FEMALE

[R] Grep Help

Hi, # 1) I have read in a CSV file df = read.csv(file="GiftCards - v1.csv",stringsAsFactors=FALSE) head(df) str(df) # 2) converted to a tbl_df df2 = tbl_df(df) # 3) fixed the names to remove leading "X" character n = names(df2) n2 = gsub(pattern="^\\w","\\1",n) names(df2) = n2 # 4) somehow the

Re: [R] FD package

> hist(data$FRic) Error in data$FRic : object of type 'closure' is not subsettable 2016-02-22 14:10 GMT+00:00 stephen sefick : > Please see ?dput. What you provided is not a minimal, reproducible example > (i.e., there is no R code). > > What kind of plot are you trying to plot? hist(data$FRic) w

Re: [R] Reading a datetime vector

Hello Everyone,  The column begins populated with integers as so:1/1/2013 0:00 in the spreadsheet equals 41257 in R's dataframe1/1/2013 0:15 in the spreadsheet equals 41257.01041664 in R's dataframe...41257 must be in minutes since 1440min/day * .01041664 day = 15 minutes. 41257 minutes

Re: [R] Reading a datetime vector

It is not minutes... read the Excel documentation for representing dates... it is days since December 30, 1899 on Windows. Read the links I provided in my last email. Also read ?str ... that function does not return anything... it only prints out information so don't expect to get anything us

Re: [R] Trying to load a FORTRAN dll but unable

On 22/02/2016 11:35 AM, MAURICE Jean - externe wrote: Hi Murdoch, Thanks for your quick answer. First : I have a 32 bits R running on a 64 bits Windows. So I think I can load 32bits DLL ? Yes. I haven't understood what I must give to is.loaded as parameter : the name of the DLL, the full

[R] [R-pkgs] New package 'netdiffuseR: Network Analysis for Diffusion of Innovations'

Dear useRs, We are happy to announce that the R package 'netdiffuseR: Network Analysis for Diffusion of Innovations' is now on CRAN (https://cran.r-project.org/web/packages/netdiffuseR/). From the package's description: "Empirical statistical analysis, visualization and simulation of network mode

Re: [R] Trying to load a FORTRAN dll but unable

Hi Murdoch, Thanks for your quick answer. First : I have a 32 bits R running on a 64 bits Windows. So I think I can load 32bits DLL ? I haven't understood what I must give to is.loaded as parameter : the name of the DLL, the full path to it, the name of a routine in it, the value given by dyn

[R] colors in facet ggplot and geom_bar

Dear, I wonder if there is a way to 'play' with colors in facet ggplot and geom_bar. With reference to the attached figure, I'd like to - color the green portion based on a numerical variable (say 1 to 10) on all of the four panels and - color-code the y labels based on the values of the 'bias

Re: [R] How a clustering algorithm in R can end up with negative silhouette values?

> Martin Maechler > on Mon, 22 Feb 2016 16:48:39 +0100 writes: > Sarah Goslee > on Fri, 19 Feb 2016 15:22:22 -0500 writes: >> Ah, my guess about the confusion was wrong, then. You're >> misunderstanding silhouette() instead. >>> From ?silhouette: >> Obs

Re: [R] colors in facet ggplot and geom_bar

By failing to provide a reproducible example and framing the desired answer as 'any hint' you are effectively limiting yourself to 'any hint' rather than a working example. The 'any hint' is that err_type should be a factor with levels in your desired order, and you can then use any of the sca

Re: [R] FD package

This is the output. I want to plot, for example FRic $nbsp com1 com2 com3 com4 com5 com6 com7 com8 com9 com10 com11 com12 com13 com14 com15 com16 172118121520161218151816 10111720 com17 com18 com19 com20 com21 com22 com23 com24

Re: [R] Multivariate multiple linear regression question

Thank you Michael for your suggestions. I will try them out and try to understand their interpretations. Regards Virendra Sent from Outlook Mobile On Mon, Feb 22, 2016 at 5:39 AM -0800, "Michael Friendly" mailto:frien...@yorku.ca>> wrote: Hi Vivendra A few suggestio

Re: [R] How a clustering algorithm in R can end up with negative silhouette values?

> Sarah Goslee > on Fri, 19 Feb 2016 15:22:22 -0500 writes: > Ah, my guess about the confusion was wrong, then. You're > misunderstanding silhouette() instead. >> From ?silhouette: > Observations with a large s(i) (almost 1) are very > well clustered, a smal

Re: [R] Trying to load a FORTRAN dll but unable

On 22/02/2016 10:24 AM, MAURICE Jean - externe wrote: Hi, With this piece of code, I get the message 824 : deelel <- paste(AccesDLL, "/regr.dll",sep="") if ( ! is.loaded(deelel)) The is.loaded function checks for symbols, not libraries. See ?is.loaded for examples. {

[R] Trying to load a FORTRAN dll but unable

Hi, With this piece of code, I get the message 824 : deelel <- paste(AccesDLL, "/regr.dll",sep="") if ( ! is.loaded(deelel)) { dyn.load(deelel) if ( ! is.loaded(deelel)) { cat("824 : ", deelel, "non charg�e\n")

Re: [R] Multivariate multiple linear regression question

Hi Vivendra A few suggestions: * You will get more interpretable tests by using Type II (partial) tests of terms in your model via library(car) Manova(MRI_model) as opposed to the Type I (sequential) tests available from manova() * You will be able to understand the results better by making h

Re: [R] FD package

Please see ?dput. What you provided is not a minimal, reproducible example (i.e., there is no R code). What kind of plot are you trying to plot? hist(data$FRic) will plot your data. I guess we need more information to be helpful. On Mon, Feb 22, 2016 at 8:03 AM, Fabio Monteiro < fabio.monteiro1.

Re: [R] FD package

If memory serves me, dbFD returns a lot of output. What do you want to plot? Also, please provide reproducible examples, so that we can help you solve your R related queries. kindest regards, Stephen On Mon, Feb 22, 2016 at 7:00 AM, Fabio Monteiro < fabio.monteiro1...@gmail.com> wrote: > Hi > >

Re: [R] FD package

Hi thank you for your quick answer I finally managed to insert everything correctly and dbFD is caltulated. I'm now trying to plot the results. My objects are matrices. x is a functional trait and species matrice. a is the species and samples Thank you 2016-02-22 12:19 GMT+00:00 PIKAL Petr :

Re: [R] Help required for Rcmdr

Dear sekhar, You don't need a C or C++ compiler to use the Rcmdr package. Nor do you need a compiler to install the package on Windows or Mac OS X, for which binary packages are provided by CRAN. Apparently, from your previous question, you're using a Windows system, and so you don't need a C o

[R] Shiny-Wordcloud

Hi R users, I need Shiny *server and UI* code for creating Uni gram,Bi gram,and Trig ram. for Word cloud from my desktop data. I gone through this link: http://shiny.rstudio.com/gallery/word-cloud.html It contains the source data from some where, but i need to use these word cloud for my *DESKT

Re: [R] FD package

Hi comments inline > -Original Message- > From: R-help [mailto:r-help-boun...@r-project.org] On Behalf Of Fabio > Monteiro > Sent: Monday, February 22, 2016 11:51 AM > To: r-help@r-project.org > Subject: [R] FD package > > Hi. > > First i would like to say that i'm really new in R. I rece

Re: [R] How to create an executable file from R GUI?

Thanks all, I solved this problem using a batch file. Note that my problem was that my GUI disappeared quickly that I solve it using function "gtkMain()" after calling my GUI  function. So, R GUI works with batch file :) The only problem that I had is that one of the buttons in my GUI is used to

Re: [R] How to create an executable file from R GUI?

It doesn't look like HTML because it is not HTML at all, it is actually SVG. I found that creating exact locations for checkboxes, radios and text, using raw HTML, is a pain, therefore I created my own library of functions which combines SVG and Javascript. The graphs are also SVG, although I am lo

[R] FD package

Hi. First i would like to say that i'm really new in R. I recently started working with R and i'm using the FD package. I'm having some errors that doesn't make any sense. I have 2 matrix, one is the species with functional traits and the second one is the species and abundances. When I try to

Re: [R] How to create an executable file from R GUI?

That is a very nice interface, indeed! What kind of HTML you used for this interface, it is looking different from the normal. On Sun, Feb 21, 2016 at 11:37 AM, Adrian Dușa wrote: > Oh, thanks Peter, good example for Mac, but indeed not working on Windows. > For a completely cross-platform solut

[R] GIS Analyses for Economics and Marketing

I am Phdoctorate Candidate at Faculty of economics. Also i am using GIS last 26 years, but lat 3 year i am focused on QGIS. My earea of interests are GIS in Economics and marketing, and now i am combine R and QGIS to have results. Can someone help me with some tutorials, training materials or cours

Re: [R] Problems with the deSolve package

Hello Abdel, I'm trying to model the spread of two viruses between different states, which are i1 and i2, and i12 if you got both viruses, but you can go back to the previous state with given probabilities (alpha, beta). The gamma probabilities are just additional infection (without contact)

Re: [R] Why CLARA clustering method does not give the same classes as when I do clustering manually?

> David L Carlson > on Sun, 21 Feb 2016 16:55:56 + writes: > I do not think this is quite true. When the medoids are > not specified, pam/clara looks for a good initial set > (build phase) and then finds a local minimum of the > objective function (swap phase). Bot

Re: [R] ReporteRs R package installation issues in R.3.2.3 (Windows)

I guess you are using a 64 bit version of R for Windows but you have only a 32-bit installation of Java. Please install a 64-bit Java. Best, Uwe Ligges On 22.02.2016 09:35, Santosh wrote: Dear Rxperts.. I tried to install ReporteRs package..in R.3.2.3 (Windows) Below are the error messages..

[R] ReporteRs R package installation issues in R.3.2.3 (Windows)

Dear Rxperts.. I tried to install ReporteRs package..in R.3.2.3 (Windows) Below are the error messages... > install.packages("ReporteRs",dep=T) trying URL ' http://cran.cnr.berkeley.edu/bin/windows/contrib/3.2/ReporteRs_0.8.2.zip' Content type 'application/zip' length 947836 bytes (925 KB) downlo

[R] Genoa course: Introduction to Zero Inflated Models

We would like to announce the following statistics course: Course: Introduction to Zero Inflated Models Where: Italian National Antarctic Museum, Genoa, Italy When: 9-13 May 2016 Course website: http://www.highstat.com/statscourse.htm Course flyer: http://highstat.com/Courses/Flyers/Flyer2016

[R] R portable is unable to open base package

I'm using shiny package to make a desktop application for my GUI. When I run my batch file, I receive the following error in the log file: Fatal error : unable to open the base package I checked my library path and it was correctly set to R portable library path. Also I tried to install base pac