[R] R Server Sizing Guidelines

Hi All, Are there any best practices on R Server Sizing Guidelines? Especially around CPU to Memory Ratio and SDD Disks on the Server? Thanks, Manish CONFIDENTIAL NOTE: The information contained in this email is intended only...{{dropped:11}} __ R-hel

Re: [R] Redirect Output to File and Screen in Parallel

PM To: Manish MAHESHWARI Cc: r-help@r-project.org Subject: Re: [R] Redirect Output to File and Screen in Parallel ?sink use the split = TRUE should do the trick On Fri, 29 Jan 2016 at 08:44 David Winsemius mailto:dwinsem...@comcast.net>> wrote: > On Jan 28, 2016, at 10:05 PM, Manish M

Re: [R] Redirect Output to File and Screen in Parallel

Hi David, I did search SO and R-Help Archive. But I haven't got the parallel option. It either prints on screen or logs to the file. Thanks, Manish -Original Message- From: David Winsemius [mailto:dwinsem...@comcast.net] Sent: Friday, January 29, 2016 3:43 PM To: Manish MAHESHWA

[R] Redirect Output to File and Screen in Parallel

Hi, Using the sink we can redirect the output to sink files set as con. However is there a way to do both - Have the Op printed on screen and also to the log file? Thanks, Manish CONFIDENTIAL NOTE: The information contained in this email is intended only...{{dropped:11}} ___

[R] NAs introduced by coercion

Hi, In glmnet, while using a matrix as an input, I get an error of NA's introduced by coercion. However in the input there is no NA value. cvfit = cv.glmnet( x = mat1, y = train$response,family="multinomial", type.multinomial = "grouped", parallel = TRUE) Error in lognet(x, is.sparse, ix, jx, y

[R] Binary Classification / Logistic Regression Models - Metrics

Hi All, For Binary Classification / Logistic Regression Models, Is there a specific preference or standard of what metric to be used for comparison of 2 models, especially when the model types are different - e.g logistic regression vs svd vs gbm vs neural networks? As I understand AUC is the

[R] Caret - Recursive Feature Elimination Error

Hi, I am trying to use caret, for feature selection on glmnet. I get a strange error like below - "arguments imply differing number of rows: 2, 3". x <- data.matrix(train[,features]) y <- train$quoteconversion_flag > str(x) num [1:260753, 1:297] NA NA NA NA NA NA NA NA NA NA ... - attr(

[R] Variable Selection for Logistic Regression

Hi, I have a dataset with approx 400K Rows and 900 columns with a single dependent variable of 0/1 flag. The independent variables are both categorical and numerical. I have looked as SO/Cross Validated Posts but couldn't get an answer for this. Since I cannot try all possible combinations of