onlineforecast issues https://lab.compute.dtu.dk/packages/onlineforecast/-/issues 2021-07-02T17:28:45+02:00 https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/3 Change or create new make_tday for handling other seasonality than daily 2021-07-02T17:28:45+02:00 hgbe Change or create new make_tday for handling other seasonality than daily Allow the user to model other seasonalities than daily, e.g. week: make_tday2 &lt;- function (time, kseq, tstep = 3600, units = &quot;hours&quot;) { tday &lt;- sapply(kseq, function(k) { tk &lt;- time + k * tstep as.numeric(tk - as.POS... Allow the user to model other seasonalities than daily, e.g. week: make_tday2 <- function (time, kseq, tstep = 3600, units = "hours") { tday <- sapply(kseq, function(k) { tk <- time + k * tstep as.numeric(tk - as.POSIXct(as.character(cut(tk, "week")), tz = "UTC"), unit = "hours") }) nams(tday) <- paste0("k", kseq) return(as.data.frame(tday)) } hgbe hgbe https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/13 Feature: Optimize parameters separately on each horizon 2021-07-13T09:38:38+02:00 pbac Feature: Optimize parameters separately on each horizon Optimize the parameters for each horizon, e.g. if kseq = c(1,6,18), then three optimizations are run, yielding the optimal parameters for each horizon. When fitting the model the other horizons, an interpolation could be done, e.g. for k... Optimize the parameters for each horizon, e.g. if kseq = c(1,6,18), then three optimizations are run, yielding the optimal parameters for each horizon. When fitting the model the other horizons, an interpolation could be done, e.g. for k=3 would be the average of the 1 and 6 horizons optimal parameters. https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/2 Fix function that uses time, e.g. subset.data.list if a time comes in without... 2021-07-02T16:24:11+02:00 hgbe Fix function that uses time, e.g. subset.data.list if a time comes in without timezone then use the timezone from the input time vector hgbe hgbe https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/14 Make &quot;forecastmatrix&quot; class 2021-09-12T15:23:14+02:00 pbac Make "forecastmatrix" class by making a &quot;forecastmatrix&quot; and &quot;fmlist&quot; classes such that e.g &quot;bs.forecastmatrix&quot;, and &quot;residuals.forecastmatrix&quot; can be made and simlar. This will allow the use of bs() directly instead of bspline(), so actually nicer overall by making a "forecastmatrix" and "fmlist" classes such that e.g "bs.forecastmatrix", and "residuals.forecastmatrix" can be made and simlar. This will allow the use of bs() directly instead of bspline(), so actually nicer overall https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/4 Make optim run only on the parameters which can be changed 2021-07-02T18:18:02+02:00 pbac Make optim run only on the parameters which can be changed Right now, in the optim functions, all parameters set in prmbound are given to optim(), should only be the ones that can actually be changes (i.e. found in \$insert_prm()) Right now, in the optim functions, all parameters set in prmbound are given to optim(), should only be the ones that can actually be changes (i.e. found in \$insert_prm()) https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/8 Make scoring consistent in optimization and selection 2021-07-13T13:03:50+02:00 pbac Make scoring consistent in optimization and selection Should complete_cases() be run, such that only complete cases across all horizons (and models) are included. How to best make this? Perhaps use the score function everywhere, then it&#39;s easy to say that it, with default parameters, is us... Should complete_cases() be run, such that only complete cases across all horizons (and models) are included. How to best make this? Perhaps use the score function everywhere, then it's easy to say that it, with default parameters, is used everywhere. https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/6 optimizer not robust against outliers 2021-07-02T22:06:29+02:00 hgbe optimizer not robust against outliers When optimizing the dataset with outliers the process becomes unstable. Investigate robust optimizer by replacing rmse with another type of error metric. e.g., Huber’s PSI-function, see 1.1.4.2 Occasional outliers in CTSMR math guide When optimizing the dataset with outliers the process becomes unstable. Investigate robust optimizer by replacing rmse with another type of error metric. e.g., Huber’s PSI-function, see 1.1.4.2 Occasional outliers in CTSMR math guide hgbe hgbe https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/11 Replacement of parameters with same name for an input cannot be set individually 2021-07-02T18:09:32+02:00 pbac Replacement of parameters with same name for an input cannot be set individually https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/10 Setting output variable, such that a different series are used for each horizon 2021-07-02T14:36:17+02:00 pbac Setting output variable, such that a different series are used for each horizon When fitting an error model it would be very useful to pass the Residuals matrix as model output and when then fitting a model, then the residuals for each individual horizon is used when the model is fitted. An &quot;observation matrix&quot; has... When fitting an error model it would be very useful to pass the Residuals matrix as model output and when then fitting a model, then the residuals for each individual horizon is used when the model is fitted. An "observation matrix" has columns "hxx", so when the model for horizon xx the hxx column should be used when fitting the model. https://lab.compute.dtu.dk/packages/onlineforecast/-/issues/7 use scorefunctions with regularization 2021-06-06T21:43:15+02:00 pbac use scorefunctions with regularization E.g. use BIC when fitting with lm_fit E.g. use BIC when fitting with lm_fit