pkg/R/getData.R

   1 #' @title Acquire data in a clean format
   2 #'
   3 #' @description Take in input data frames and/or files containing raw data, and timezones, and
   4 #'   output a Data object, roughly corresponding to a list where each cell contains all value
   5 #'   for one day (see \code{?Data}). Current limitation: series (in working_tz) must start at
   6 #'   right after midnight (to keep in sync with exogenous vars)
   7 #'
   8 #' @param ts_data Time-series, as a data frame (DB style: 2 columns, first is date/time,
   9 #'   second is value) or a CSV file
  10 #' @param exo_data Exogenous variables, as a data frame or a CSV file; first comlumn is dates,
  11 #'   next block are measurements for the day, and final block are exogenous forecasts
  12 #' @param input_tz Timezone in the input files ("GMT" or e.g. "Europe/Paris")
  13 #' @param date_format How date/time are stored (e.g. year/month/day hour:minutes;
  14 #'   see \code{strptime})
  15 #' @param working_tz Timezone to work with ("GMT" or e.g. "Europe/Paris")
  16 #' @param predict_at When does the prediction take place ? Integer, in hours. Default: 0
  17 #'
  18 #' @return An object of class Data
  19 #'
  20 #' @export
  21 getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%M",
  22     working_tz="GMT", predict_at=0, limit=Inf)
  23 {
  24     # Sanity checks (not full, but sufficient at this stage)
  25     if (!is.character(input_tz) || !is.character(working_tz))
  26         stop("Bad timezone (see ?timezone)")
  27     input_tz = input_tz[1]
  28     working_tz = working_tz[1]
  29     if ( (!is.data.frame(ts_data) && !is.character(ts_data)) ||
  30             (!is.data.frame(exo_data) && !is.character(exo_data)) )
  31         stop("Bad time-series / exogenous input (data [frame] or CSV file)")
  32     if (is.character(ts_data))
  33         ts_data = ts_data[1]
  34     if (is.character(exo_data))
  35         exo_data = exo_data[1]
  36     predict_at = as.integer(predict_at)[1]
  37     if (predict_at<0 || predict_at>23)
  38         stop("Bad predict_at (0-23)")
  39     if (!is.character(date_format))
  40         stop("Bad date_format (character)")
  41     date_format = date_format[1]
  42
  43     ts_df =
  44         if (is.character(ts_data)) {
  45             if (ts_data %in% data(package="talweg")$results[,"Item"])
  46                 ts_data =
  47
  48
  49
  50
  51                     ############CONTINUE: http://r-pkgs.had.co.nz/data.html
  52
  53
  54
  55
  56
  57                     read.csv(ts_data)
  58         } else {
  59             ts_data
  60         }
  61     exo_df =
  62         if (is.character(exo_data)) {
  63             read.csv(exo_data)
  64         } else {
  65             exo_data
  66         }
  67     # Convert to the desired timezone (usually "GMT" or "Europe/Paris")
  68     formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz)
  69     ts_df[,1] = format(as.POSIXct(formatted_dates_POSIXlt), tz=working_tz, usetz=TRUE)
  70
  71     line = 1 #index in PM10 file (24 lines for 1 cell)
  72     nb_lines = nrow(ts_df)
  73     nb_exos = ( ncol(exo_df) - 1 ) / 2
  74     data = list() #new("Data")
  75     i = 1 #index of a cell in data
  76     while (line <= nb_lines)
  77     {
  78         time = c()
  79         serie = c()
  80         repeat
  81         {
  82             {
  83                 time = c(time, ts_df[line,1])
  84                 serie = c(serie, ts_df[line,2])
  85                 line = line + 1
  86             };
  87             if (line >= nb_lines + 1 || as.POSIXlt(ts_df[line-1,1])$hour == predict_at)
  88                 break
  89         }
  90
  91         # NOTE: if predict_at does not cut days at midnight, exogenous vars need to be shifted
  92         exo_hat = as.data.frame( exo_df[
  93             ifelse(predict_at>0,max(1,i-1),i) , (1+nb_exos+1):(1+2*nb_exos) ] )
  94         exo = as.data.frame( exo_df[ ifelse(predict_at>0,max(1,i-1),i) , 2:(1+nb_exos) ] )
  95         level = mean(serie, na.rm=TRUE)
  96         centered_serie = serie - level
  97         #data$append(time, centered_serie, level, exo_hat, exo_Jm1) #too slow; TODO: use R6 class
  98         data[[length(data)+1]] = list("time"=time, "serie"=centered_serie, "level"=level,
  99             "exo_hat"=exo_hat, "exo"=exo)
 100         if (i >= limit)
 101             break
 102         i = i + 1
 103     }
 104     new("Data",data=data)
 105 }