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,
  22     input_tz="GMT", date_format="%d/%m/%Y %H:%M", working_tz="GMT", predict_at=0)
  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         stop("Bad time-series input (data frame or CSV file)")
  31     if (is.character(ts_data))
  32         ts_data = ts_data[1]
  33     predict_at = as.integer(predict_at)[1]
  34     if (predict_at<0 || predict_at>23)
  35         stop("Bad predict_at (0-23)")
  36     if (!is.character(date_format))
  37         stop("Bad date_format (character)")
  38     date_format = date_format[1]
  39
  40     ts_df =
  41         if (is.character(ts_data)) {
  42             read.csv(ts_data)
  43         } else {
  44             ts_data
  45         }
  46     exo_df =
  47         if (is.character(exo_data)) {
  48             read.csv(exo_data)
  49         } else {
  50             exo_data
  51         }
  52     # Convert to the desired timezone (usually "GMT" or "Europe/Paris")
  53     formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz)
  54     ts_df[,1] = format(as.POSIXct(formatted_dates_POSIXlt), tz=working_tz, usetz=TRUE)
  55
  56     line = 1 #index in PM10 file (24 lines for 1 cell)
  57     nb_lines = nrow(ts_df)
  58     nb_exos = ( ncol(exo_df) - 1 ) / 2
  59     data = list() #new("Data")
  60     i = 1 #index of a cell in data
  61     while (line <= nb_lines)
  62     {
  63         time = c()
  64         serie = c()
  65         repeat
  66         {
  67             {
  68                 time = c(time, ts_df[line,1])
  69                 serie = c(serie, ts_df[line,2])
  70                 line = line + 1
  71             };
  72             if (line >= nb_lines + 1 || as.POSIXlt(ts_df[line-1,1])$hour == predict_at)
  73                 break
  74         }
  75
  76         # NOTE: if predict_at does not cut days at midnight,
  77         # for the exogenous to be synchronized they need to be shifted
  78         if (predict_at > 0)
  79         {
  80             exo_hat = as.data.frame(exo_df[max(1,i-1),(1+nb_exos+1):(1+2*nb_exos)])
  81             exo_Dm1 = if (i>=3) as.data.frame(exo_df[i-1,2:(1+nb_exos)]) else NA
  82         } else
  83         {
  84             exo_hat = as.data.frame(exo_df[i,(1+nb_exos+1):(1+2*nb_exos)])
  85             exo_Dm1 = if (i>=2) as.data.frame(exo_df[i-1,2:(1+nb_exos)]) else NA
  86         }
  87         i = i + 1
  88         #center data
  89         level = mean(serie, na.rm=TRUE)
  90         centered_serie = serie - level
  91 #       data$append(time, centered_serie, level, exo_hat, exo_Jm1) #TODO: slow: why ?
  92         data[[length(data)+1]] = list("time"=time, "serie"=centered_serie, "level"=level,
  93             "exo_hat"=exo_hat, "exo_Dm1"=exo_Dm1)
  94     }
  95     new("Data",data=data)
  96 }