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
   4 #'   timezones, and output a Data object, roughly corresponding to a list where each cell
   5 #'   contains all value for one day (see \code{?Data}).
   6 #'
   7 #' @param ts_data Time-series, as a data frame (DB style: 2 columns, first is date/time,
   8 #'   second is value) or a CSV file
   9 #' @param exo_data Exogenous variables, as a data frame or a CSV file; first comlumn is
  10 #'   dates, next block are measurements for the day, and final block are exogenous
  11 #'   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 #' @param limit Number of days to extract (default: Inf, for "all")
  18 #'
  19 #' @return An object of class Data
  20 #'
  21 #' @examples
  22 #' ts_data = read.csv(system.file("extdata","pm10_mesures_H_loc.csv",package="talweg"))
  23 #' exo_data = read.csv(system.file("extdata","meteo_extra_noNAs.csv",package="talweg"))
  24 #' data = getData(ts_data, exo_data, limit=120)
  25 #' @export
  26 getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%M",
  27     working_tz="GMT", predict_at=0, limit=Inf)
  28 {
  29     # Sanity checks (not full, but sufficient at this stage)
  30     if (!is.character(input_tz) || !is.character(working_tz))
  31         stop("Bad timezone (see ?timezone)")
  32     input_tz = input_tz[1]
  33     working_tz = working_tz[1]
  34     if ( (!is.data.frame(ts_data) && !is.character(ts_data)) ||
  35             (!is.data.frame(exo_data) && !is.character(exo_data)) )
  36         stop("Bad time-series / exogenous input (data frame or CSV file)")
  37     if (is.character(ts_data))
  38         ts_data = ts_data[1]
  39     if (is.character(exo_data))
  40         exo_data = exo_data[1]
  41     predict_at = as.integer(predict_at)[1]
  42     if (predict_at<0 || predict_at>23)
  43         stop("Bad predict_at (0-23)")
  44     if (!is.character(date_format))
  45         stop("Bad date_format (character)")
  46     date_format = date_format[1]
  47
  48     ts_df =
  49         if (is.character(ts_data))
  50             read.csv(ts_data)
  51         else
  52             ts_data
  53     # Convert to the desired timezone (usually "GMT" or "Europe/Paris")
  54     formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz)
  55     ts_df[,1] = format(
  56         as.POSIXct(formatted_dates_POSIXlt, tz=input_tz), tz=working_tz, usetz=TRUE)
  57
  58     exo_df =
  59         if (is.character(exo_data))
  60             read.csv(exo_data)
  61         else
  62             exo_data
  63     # Times in exogenous variables file are ignored: no conversions required
  64
  65     line = 1 #index in PM10 file (24 lines for 1 cell)
  66     nb_lines = nrow(ts_df)
  67     nb_exos = ( ncol(exo_df) - 1 ) / 2
  68     data = Data$new()
  69     i = 1 #index of a cell in data
  70     while (line <= nb_lines)
  71     {
  72         time = c()
  73         serie = c()
  74         hat_serie = c()
  75         repeat
  76         {
  77             {
  78                 time = c(time, ts_df[line,1])
  79                 hat_serie = c(serie, ts_df[line,3])
  80                 serie = c(serie, ts_df[line,2])
  81                 line = line + 1
  82             };
  83             if (line >= nb_lines + 1
  84                 || as.POSIXlt(ts_df[line-1,1],tz=working_tz)$hour == predict_at)
  85             {
  86                 break
  87             }
  88         }
  89
  90         hat_exo = as.data.frame( exo_df[i,(1+nb_exos+1):(1+2*nb_exos)] )
  91         exo = as.data.frame( exo_df[i,2:(1+nb_exos)] )
  92         data$appendHat(time, hat_serie, hat_exo)
  93         data$append(serie, exo) #in realtime, this call comes hours later
  94         if (i >= limit)
  95             break
  96         i = i + 1
  97     }
  98     if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(2)))
  99         data$removeFirst()
 100     if (length(data$getCenteredSerie(data$getSize()))
 101         < length(data$getCenteredSerie(data$getSize()-1)))
 102     {
 103         data$removeLast()
 104     }
 105     data
 106 }