add realtime option, slightly refactor data acquisition

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

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index df94895..b944dfb 100644 (file)
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -1,13 +1,14 @@
 #' @title Acquire data in a clean format
 #'
-#' @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}).
+#' @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}).
 #'
 #' @param ts_data Time-series, as a data frame (DB style: 2 columns, first is date/time,
 #'   second is value) or a CSV file
-#' @param exo_data Exogenous variables, as a data frame or a CSV file; first comlumn is dates,
-#'   next block are measurements for the day, and final block are exogenous forecasts
+#' @param exo_data Exogenous variables, as a data frame or a CSV file; first comlumn is
+#'   dates, next block are measurements for the day, and final block are exogenous
+#'   forecasts
 #' @param input_tz Timezone in the input files ("GMT" or e.g. "Europe/Paris")
 #' @param date_format How date/time are stored (e.g. year/month/day hour:minutes;
 #'   see \code{strptime})
@@ -15,14 +16,7 @@
 #' @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 A list where data[[i]] contains
-#'   \itemize{
-#'     \item time: vector of times
-#'     \item centered_serie: centered serie
-#'     \item level: corresponding level
-#'     \item exo: exogenous variables
-#'     \item exo_hat: predicted exogenous variables
-#'   }
+#' @return An object of class Data
 #'
 #' @examples
 #' ts_data = read.csv(system.file("extdata","pm10_mesures_H_loc.csv",package="talweg"))
@@ -56,55 +50,57 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
                        read.csv(ts_data)
                else
                        ts_data
+       # Convert to the desired timezone (usually "GMT" or "Europe/Paris")
+       formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz)
+       ts_df[,1] = format(
+               as.POSIXct(formatted_dates_POSIXlt, tz=input_tz), tz=working_tz, usetz=TRUE)
+
        exo_df =
                if (is.character(exo_data))
                        read.csv(exo_data)
                else
                        exo_data
-       # Convert to the desired timezone (usually "GMT" or "Europe/Paris")
-       formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz)
-       ts_df[,1] = format(as.POSIXct(formatted_dates_POSIXlt), tz=working_tz, usetz=TRUE)
+       # Times in exogenous variables file are ignored: no conversions required
 
        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()
+       data = Data$new()
        i = 1 #index of a cell in data
        while (line <= nb_lines)
        {
                time = c()
                serie = c()
+               hat_serie = c()
                repeat
                {
                        {
                                time = c(time, ts_df[line,1])
+                               hat_serie = c(serie, ts_df[line,3])
                                serie = c(serie, ts_df[line,2])
                                line = line + 1
                        };
-                       if (line >= nb_lines + 1 || as.POSIXlt(ts_df[line-1,1])$hour == predict_at)
+                       if (line >= nb_lines + 1
+                               || as.POSIXlt(ts_df[line-1,1],tz=working_tz)$hour == predict_at)
+                       {
                                break
+                       }
                }
 
+               hat_exo = as.data.frame( exo_df[i,(1+nb_exos+1):(1+2*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[[i]] = list("time"=time, "centered_serie"=centered_serie, "level"=level,
-                       "exo"=exo, "exo_hat"=exo_hat)
+               data$appendHat(time, hat_serie, hat_exo)
+               data$append(serie, exo) #in realtime, this call comes hours later
                if (i >= limit)
                        break
                i = i + 1
        }
-       start = 1
-       end = length(data)
-       if (length(data[[1]]$centered_serie) < length(data[[2]]$centered_serie))
-               start = 2
-       if (length(data[[length(data)]]$centered_serie) <
-               length(data[[length(data)-1]]$centered_serie))
+       if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(2)))
+               data$removeFirst()
+       if (length(data$getCenteredSerie(data$getSize()))
+               < length(data$getCenteredSerie(data$getSize()-1)))
        {
-               end = end-1
+               data$removeLast()
        }
-       if (start>1 || end<length(data))
-               data = data[start:end]
        data
 }