Re: [R] Running time complexity of Seasonal ARIMA model (forecast package)
*Dear Sir,* Thanks for your response. Here, I was using 'n' to denote the input size (no. of points in time series using which I am building a Seasonal ARIMA model). I can check the running time myself and I have done that as well (it takes some 1-2 minutes for 50 iterations for my input size), but I want to know more about the asysmptotic complexity of the algorithm R uses. I can see three methods CSS, CSS-ML and ML that it uses to optimize the parameters. Like bubble sort takes O(n^2) time where n is the no. of elements. Can I define something like this to build my ARIMA model which has n points? * Thanks Regards Mohit Dhingra +919611190435* On 8 August 2013 12:45, Prof Brian Ripley rip...@stats.ox.ac.uk wrote: On 08/08/2013 05:08, Mohit Dhingra wrote: *Dear All,* I am using Seasonal ARIMA model for predicting cloud workloads. I want to know the running time complexity of building model by the algorithm implemented in R (I am not sure, is it Yule-Walker?). I want to know if it It is not Yule-Walker (which is for AR models only). is polynomial O(n^2) etc. or exponential or linear (O(n)). Can someone please help. What is 'n' here? Please read the references for yourself: they will tell you enough to deduce the answer -- or you could experiment. PLEASE do read the posting guide http://www.R-project.org/** posting-guide.html http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. PLEASE do. -- Brian D. Ripley, rip...@stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~**ripley/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 [[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] Running time complexity of Seasonal ARIMA model (forecast package)
*Dear All,* I am using Seasonal ARIMA model for predicting cloud workloads. I want to know the running time complexity of building model by the algorithm implemented in R (I am not sure, is it Yule-Walker?). I want to know if it is polynomial O(n^2) etc. or exponential or linear (O(n)). Can someone please help. * Thanks Regards Mohit Dhingra +919611190435* [[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] Y label doesn't show up on printing files
Hi David, Thanks for your reply! How do I exactly find it out and solve? Also, the problem is not reproducible every time :-/ Thanks Regards Mohit Dhingra +919611190435 On 22 July 2013 23:55, David Winsemius dwinsem...@comcast.net wrote: On Jul 22, 2013, at 3:17 AM, Mohit Dhingra wrote: Hello, I'm using R version 2.15.1 (2012-06-22) -- Roasted Marshmallows . System info: Linux ubuntu 3.5.0-36-generic #57~precise1-Ubuntu SMP Thu Jun 20 18:21:09 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux. When I plot something, y label does show up on the pop up image. plot (x, rtimel[,2] , xlab=Memory Allocated (in MB), ylab=Response Time (in ms), type=l, col=black, ylim=c(0,m) ) But when I try to save it using dev.copy(pdf,'response_time_with_memory_direct.pdf') dev.off() Y-label doesn't get printed on the pdf file. Can someone please help? Perhaps a difficulty with the fonts in your R installation being different than the fonts in your pdf viewer? -- David Winsemius Alameda, CA, USA __ 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] Y label doesn't show up on printing files
Hello, I'm using R version 2.15.1 (2012-06-22) -- Roasted Marshmallows . System info: Linux ubuntu 3.5.0-36-generic #57~precise1-Ubuntu SMP Thu Jun 20 18:21:09 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux. When I plot something, y label does show up on the pop up image. plot (x, rtimel[,2] , xlab=Memory Allocated (in MB), ylab=Response Time (in ms), type=l, col=black, ylim=c(0,m) ) But when I try to save it using dev.copy(pdf,'response_time_with_memory_direct.pdf') dev.off() Y-label doesn't get printed on the pdf file. Can someone please help? Thanks Regards Mohit Dhingra +919611190435 __ 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] Time Series Prediction using Gaussian Process
*Hello All,* I tried figuring out the problem, I was trying to use laplacedot to predict the long term, which however would not do a good job. Then, I tried to do a point by point prediction and building the model again, everytime. It shows me better results. I tried writing my kernel function (matern covariance function), and attached is the result of that. Red lines show the fit and blue lines show the prediction, however, it always lag the actual data. Now, I am trying to use neural network covariance function. Is that available in R? * Thanks Regards Mohit Dhingra +919611190435* On 5 December 2012 11:15, Mohit Dhingra mohitdhing...@gmail.com wrote: *Hello All,* I am trying to do a time series prediction using Gaussian Processes (need to try with different kernel functions) using R. I am using kernlab package to do so. But I am not sure how do I predict for new data.!! I used following to train the model : gp = gausspr( t, weekdays1_vector_t_t_trunc, kernel=laplacedot, scaled=FALSE ) Then, I predict using predict function : pred = predict(gp, t_new) But, when I plot the data, the model seems to fit quite ok, but prediction is nowhere close to the actual data. ts.plot(weekdays1_vector_t_t_trunc- mean(weekdays1_vector_t_t_trunc),xlim=c(0,600)) lines(alpha(gp), col=red) lines(t_new, pred, col=blue) * * * I am attaching the figure. Can someone please help me out.. * * * * * *Thanks Regards Mohit Dhingra +919611190435* gaussian_process_matern_3600.pdf Description: Adobe PDF document __ 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.
