Hello Chris, 
I 've found two other issues 
with MAE and CRPS, giving warning  when running examples.
I've the same issue on my data. 
Hope that you could find some time to take a
look here.

Thank you

Anna


> library(ensembleBMA)
Loading required package: chron
> example(MAE)

MAE>   data(ensBMAtest)

MAE>   ensMemNames <- c("gfs","cmcg","eta","gasp","jma","ngps","tcwb","ukmo")

MAE>   obs <- paste("T2","obs", sep = ".")

MAE>   ens <- paste("T2", ensMemNames, sep = ".")

MAE>   tempTestData <- ensembleData( forecasts = ensBMAtest[,ens],
MAE+                                 dates = ensBMAtest[,"vdate"],
MAE+                                 observations = ensBMAtest[,obs],
MAE+                                 station = ensBMAtest[,"station"],
MAE+                                 forecastHour = 48,
MAE+                                 initializationTime = "00")

MAE> ## Not run: 
MAE> ##D  # R check
MAE> ##D   tempTestFit <- ensembleBMAnormal( tempTestData, trainingDays = 30)
MAE> ## End(Not run)
MAE> 
MAE>   MAE( tempTestFit, tempTestData)
ensemble      BMA 
2.322651 2.152652 
Warning message:
In matchDates(fitDates, ensembleValidDates(ensembleData), dates) :
  some fit dates dates not represented in data
> example(CRPS)

CRPS>   data(ensBMAtest)

CRPS>   ensMemNames <- c("gfs","cmcg","eta","gasp","jma","ngps","tcwb","ukmo")

CRPS>   obs <- paste("T2","obs", sep = ".")

CRPS>   ens <- paste("T2", ensMemNames, sep = ".")

CRPS>   tempTestData <- ensembleData( forecasts = ensBMAtest[,ens],
CRPS+                                 dates = ensBMAtest[,"vdate"],
CRPS+                                 observations = ensBMAtest[,obs],
CRPS+                                 station = ensBMAtest[,"station"],
CRPS+                                 forecastHour = 48,
CRPS+                                 initializationTime = "00")

CRPS> ## Not run: 
CRPS> ##D # R check
CRPS> ##D   tempTestFit <- ensembleBMAnormal( tempTestData, trainingDays = 30)
CRPS> ## End(Not run)
CRPS>   crpsValues <- crps( tempTestFit, tempTestData)

CRPS>   colMeans(crpsValues)
ensemble      BMA 
1.971644 1.584356 

CRPS>   CRPS( tempTestFit, tempTestData)
ensemble      BMA 
1.971644 1.577258 
Warning messages:
1: In matchDates(fitDates, ensembleValidDates(ensembleData), dates) :
  some fit dates dates not represented in data
2: In matchDates(fitDates, ensembleValidDates(ensembleData), dates) :
  some fit dates dates not represented in data
> sessionInfo()
R version 2.15.1 (2012-06-22)
Platform: x86_64-unknown-linux-gnu (64-bit)

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=C                 LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] ensembleBMA_5.0.3 chron_2.3-42     

loaded via a namespace (and not attached):
[1] tools_2.15.1
 

 
Anna Freni Sterrantino
Department of Statistics
University of Bologna, Italy
via Belle Arti 41, 40124 BO.


________________________________
 Da: Chris Fraley <fra...@washington.edu>

Inviato: Giovedì 12 Luglio 2012 17:42
Oggetto: Re: ensembleBMA pit function warnings

Dear Anna Freni Sterrantino,

      I'll get to this as soon as I can. I'm still maintaining ensembleBMA 
because there is no one else to do it, but my time at the University of 
Washington has recently been greatly reduced, and the queue of things to do is 
rather long at the moment.

Regards,

Chris

On Thu, 12 Jul 2012, anna freni sterrantino wrote:

> Hello!
> I'm having some problems with 
> pit function in ensembleBMA. When I run on mu data I have the
> same warnings as below, when I type the example(pit).
> Any suggestion on how to resolve it?
> 
> 
> > library(ensembleBMA)
> Loading required package: chron
> > example(pit)
> 
> pit>   data(ensBMAtest)
> 
> pit>   ensMemNames <- c("gfs","cmcg","eta","gasp","jma","ngps","tcwb","ukmo")
> 
> pit>   obs <- paste("T2","obs", sep = ".")
> 
> pit>   ens <- paste("T2", ensMemNames, sep = ".")
> 
> pit>   tempTestData <- ensembleData( forecasts = ensBMAtest[,ens],
> pit+                                 dates = ensBMAtest[,"vdate"],
> pit+                                 observations = ensBMAtest[,obs],
> pit+                                 station = ensBMAtest[,"station"],
> pit+                                 forecastHour = 48,
> pit+                                 initializationTime = "00")
> 
> pit> ## Not run: 
> pit> ##D  # R check
> pit> ##D   tempTestFit <- ensembleBMAnormal( tempTestData, trainingDays = 30)
> pit> ## End(Not run)
> pit> 
> pit>   tempTestForc <- quantileForecast( tempTestFit, tempTestData)
> 
> pit>   range(tempTestForc)
> [1] 277.3138 281.1668
> 
> pit>   tempTestPIT <- pit( tempTestFit, tempTestData) 
> Warning messages:
> 1: In matchDates(fitDates, ensembleValidDates(ensembleData), dates) :
>   some fit dates dates not represented in data
> 2: In matchDates(fitDates, ensembleValidDates(ensembleData), dates) :
>   some fit dates dates not represented in data
> 
>  
> > sessionInfo()
> R version 2.15.0 Patched (2012-04-10 r58965)
> Platform: x86_64-unknown-linux-gnu (64-bit)
> 
> locale:
>  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
>  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
>  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
>  [7] LC_PAPER=C                 LC_NAME=C                 
>  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
> 
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods   base     
> 
> other attached packages:
> [1] ensembleBMA_5.0.3 chron_2.3-42     
> 
> loaded via a namespace (and not attached):
> [1] tools_2.15.0
> 
> 
> Any suggestion?
> 
> 
> Anna Freni Sterrantino
> Ph.D Student
> Department of Statistics
> University of Bologna, Italy
> via Belle Arti 41, 40124 BO.
> 
>
        [[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.

Reply via email to