[aggexp.git] / pkg / R / z_getData.R

expertsArray = c(
	"CLM", #1
	"GAM", #2
	"CLM1", #3
	"CLM2", #4
	"S_AIRPARIF", #5
	"S_INERIS", #6
	"D_ESMERALDA", #7
	"D_PREVAIR", #8
	"D_PREVAIR2", #9
	"PERSIST", #10
	#new additions only for PQV_2014
	#TODO: default behavior on station != PQV_2014 ?
	"GAM_sepMar", #11
	"GAM_aprAug", #12
	"GAM_highPollution", #13
	"GAM_lowPollution", #14
	"GAM_hotTemperature", #15
	"GAM_coldTemperature", #16
	"GAM_eastWind", #17
	"GAM_westWind", #18
	"GAM_noRain", #19
	"GAM_rain" #20
)

stationsArray = c(
	"AIL", #1
	"ALE", #2
	"CAE", #3
	"CHD", #4
	"EVT", #5
	"HRI", #6
	"IFS", #7
	"JUS", #8
	"LIS", #9
	"MAS", #10
	"MRA", #11
	"NEI", #12
	"POS", #13
	"PQV", #14
	"SLO", #15
	"HRI_2014", #16
	"LIS_2014", #17
	"PQV_2014", #18
	"PQV2" #19
)

#' @title Get forecasts + observations
#'
#' @description Get forecasts of all specified experts for all specified stations, also with (ordered) dates and (unordered) stations indices.
#'
#' @param experts Names of the experts. Default: all
#' @param station Names of the stations. Default: all
#'
#' @export
getData = function(experts=expertsArray, stations=stationsArray)
{
	#no need because of "LazyData: true" in DESCRIPTION
	#data(list=stations, package="aggexp")
	data = as.data.frame(matrix(nrow=0, ncol=1 + length(experts) + 2))
	names(data) = c("Date", experts, "Measure", "Station")
	for (i in 1:length(stations))
	{
		stationInfo = get(stations[i])
		#date index is sufficient; also add station index
		stationInfo = cbind(Date = 1:nrow(stationInfo), stationInfo[,names(stationInfo) %in% experts], Measure = stationInfo[,"Measure"], Station = i)
		data = rbind(data, stationInfo)
	}

	#extra step: order by date (would be a DB request)
	data = data[order(data[,"Date"]),]

	return (data)
}
Commit	Line	Data
	1	expertsArray = c(
	2	"CLM", #1
	3	"GAM", #2
	4	"CLM1", #3
	5	"CLM2", #4
	6	"S_AIRPARIF", #5
	7	"S_INERIS", #6
	8	"D_ESMERALDA", #7
	9	"D_PREVAIR", #8
	10	"D_PREVAIR2", #9
	11	"PERSIST", #10
	12	#new additions only for PQV_2014
	13	#TODO: default behavior on station != PQV_2014 ?
	14	"GAM_sepMar", #11
	15	"GAM_aprAug", #12
	16	"GAM_highPollution", #13
	17	"GAM_lowPollution", #14
	18	"GAM_hotTemperature", #15
	19	"GAM_coldTemperature", #16
	20	"GAM_eastWind", #17
	21	"GAM_westWind", #18
	22	"GAM_noRain", #19
	23	"GAM_rain" #20
	24	)
	25
	26	stationsArray = c(
	27	"AIL", #1
	28	"ALE", #2
	29	"CAE", #3
	30	"CHD", #4
	31	"EVT", #5
	32	"HRI", #6
	33	"IFS", #7
	34	"JUS", #8
	35	"LIS", #9
	36	"MAS", #10
	37	"MRA", #11
	38	"NEI", #12
	39	"POS", #13
	40	"PQV", #14
	41	"SLO", #15
	42	"HRI_2014", #16
	43	"LIS_2014", #17
	44	"PQV_2014", #18
	45	"PQV2" #19
	46	)
	47
	48	#' @title Get forecasts + observations
	49	#'
	50	#' @description Get forecasts of all specified experts for all specified stations, also with (ordered) dates and (unordered) stations indices.
	51	#'
	52	#' @param experts Names of the experts. Default: all
	53	#' @param station Names of the stations. Default: all
	54	#'
	55	#' @export
	56	getData = function(experts=expertsArray, stations=stationsArray)
	57	{
	58	#no need because of "LazyData: true" in DESCRIPTION
	59	#data(list=stations, package="aggexp")
	60	data = as.data.frame(matrix(nrow=0, ncol=1 + length(experts) + 2))
	61	names(data) = c("Date", experts, "Measure", "Station")
	62	for (i in 1:length(stations))
	63	{
	64	stationInfo = get(stations[i])
	65	#date index is sufficient; also add station index
	66	stationInfo = cbind(Date = 1:nrow(stationInfo), stationInfo[,names(stationInfo) %in% experts], Measure = stationInfo[,"Measure"], Station = i)
	67	data = rbind(data, stationInfo)
	68	}
	69
	70	#extra step: order by date (would be a DB request)
	71	data = data[order(data[,"Date"]),]
	72
	73	return (data)
	74	}