'update'

[talweg.git] / pkg / R / getData.R

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index 574522b..a4e1e17 100644 (file)
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -2,8 +2,7 @@
 #'
 #' @description Take in input data frames and/or files containing raw data, and timezones, and
 #'   output a Data object, roughly corresponding to a list where each cell contains all value
-#'   for one day (see \code{?Data}). Current limitation: series (in working_tz) must start at
-#'   right after midnight (to keep in sync with exogenous vars)
+#'   for one day (see \code{?Data}).
 #'
 #' @param ts_data Time-series, as a data frame (DB style: 2 columns, first is date/time,
 #'   second is value) or a CSV file
@@ -14,14 +13,14 @@
 #'   see \code{strptime})
 #' @param working_tz Timezone to work with ("GMT" or e.g. "Europe/Paris")
 #' @param predict_at When does the prediction take place ? Integer, in hours. Default: 0
+#' @param limit Number of days to extract (default: Inf, for "all")
 #'
 #' @return An object of class Data
 #'
-#' @example
-#' ts_data = read.csv(system.file("extdata",ts_data,package="talweg",mustWork=TRUE))
-#' exo_data = read.csv(system.file("extdata",exo_data,package="talweg",mustWork=TRUE))
-#' getData(ts_data, exo_data, ...)
-#'
+#' @examples
+#' ts_data = read.csv(system.file("extdata","pm10_mesures_H_loc.csv",package="talweg"))
+#' exo_data = read.csv(system.file("extdata","meteo_extra_noNAs.csv",package="talweg"))
+#' data = getData(ts_data, exo_data, limit=120)
 #' @export
 getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%M",
        working_tz="GMT", predict_at=0, limit=Inf)
@@ -62,7 +61,7 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
        line = 1 #index in PM10 file (24 lines for 1 cell)
        nb_lines = nrow(ts_df)
        nb_exos = ( ncol(exo_df) - 1 ) / 2
-       data = list() #new("Data")
+       data = Data$new()
        i = 1 #index of a cell in data
        while (line <= nb_lines)
        {
@@ -79,18 +78,21 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
                                break
                }
 
-               # NOTE: if predict_at does not cut days at midnight, exogenous vars need to be shifted
-               exo_hat = as.data.frame( exo_df[
-                       ifelse(predict_at>0,max(1,i-1),i) , (1+nb_exos+1):(1+2*nb_exos) ] )
-               exo = as.data.frame( exo_df[ ifelse(predict_at>0,max(1,i-1),i) , 2:(1+nb_exos) ] )
+               exo = as.data.frame( exo_df[i,2:(1+nb_exos)] )
+               exo_hat = as.data.frame( exo_df[i,(1+nb_exos+1):(1+2*nb_exos)] )
                level = mean(serie, na.rm=TRUE)
                centered_serie = serie - level
-               #data$append(time, centered_serie, level, exo_hat, exo_Jm1) #too slow; TODO: use R6 class
-               data[[length(data)+1]] = list("time"=time, "serie"=centered_serie, "level"=level,
-                       "exo_hat"=exo_hat, "exo"=exo)
+               data$append(time, centered_serie, level, exo, exo_hat)
                if (i >= limit)
                        break
                i = i + 1
        }
-       new("Data",data=data)
+       if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(2)))
+               data$removeFirst()
+       if (length(data$getCenteredSerie(data$getSize()))
+               < length(data$getCenteredSerie(data$getSize()-1)))
+       {
+               data$removeLast()
+       }
+       data
 }