Commit | Line | Data |
---|---|---|
3d69ff21 BA |
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 ? ab[:cd][:ef] where a,b,c,d,e,f | |
17 | #' in (0,9) and define an hour[minute[second]]; time must be present in the file | |
18 | #' | |
19 | #' @return An object of class Data | |
20 | #' | |
21 | #' @export | |
22 | getData = function(ts_data, exo_data, | |
23 | input_tz="GMT", date_format="%d/%m/%Y %H:%M", working_tz="GMT", predict_at="00") | |
24 | { | |
25 | # Sanity checks (not full, but sufficient at this stage) | |
26 | if (!is.character(input_tz) || !is.character(working_tz)) | |
27 | stop("Bad timezone (see ?timezone)") | |
28 | input_tz = input_tz[1] | |
29 | working_tz = working_tz[1] | |
30 | if (!is.data.frame(ts_data) && !is.character(ts_data)) | |
31 | stop("Bad time-series input (data frame or CSV file)") | |
32 | if (is.character(ts_data)) | |
33 | ts_data = ts_data[1] | |
34 | pattern_index_in_predict_at = grep("^[0-9]{2}(:[0-9]{2}){0,2}$", predict_at) | |
35 | if (!is.character(predict_at) || length(pattern_index_in_predict_at) == 0) | |
36 | stop("Bad predict_at ( ^[0-9]{2}(:[0-9]{2}){0,2}$ )") | |
37 | predict_at = predict_at[ pattern_index_in_predict_at[1] ] | |
38 | if (!is.character(date_format)) | |
39 | stop("Bad date_format (character)") | |
40 | date_format = date_format[1] | |
41 | ||
42 | ts_df = | |
43 | if (is.character(ts_data)) { | |
44 | read.csv(ts_data) | |
45 | } else { | |
46 | ts_data | |
47 | } | |
48 | exo_df = | |
49 | if (is.character(exo_data)) { | |
50 | read.csv(exo_data) | |
51 | } else { | |
52 | exo_data | |
53 | } | |
54 | # Convert to the desired timezone (usually "GMT" or "Europe/Paris") | |
55 | formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz) | |
56 | ts_df[,1] = format(as.POSIXct(formatted_dates_POSIXlt), tz=working_tz, usetz=TRUE) | |
57 | ||
58 | if (nchar(predict_at) == 2) | |
59 | predict_at = paste(predict_at,":00",sep="") | |
60 | if (nchar(predict_at) == 5) | |
61 | predict_at = paste(predict_at,":00",sep="") | |
62 | ||
63 | line = 1 #index in PM10 file (24 lines for 1 cell) | |
64 | nb_lines = nrow(ts_df) | |
65 | nb_exos = ( ncol(exo_df) - 1 ) / 2 | |
66 | data = list() #new("Data") | |
67 | i = 1 #index of a cell in data | |
68 | while (line <= nb_lines) | |
69 | { | |
70 | time = c() | |
71 | serie = c() | |
72 | repeat { | |
73 | { | |
74 | time = c(time, ts_df[line,1]) | |
75 | serie = c(serie, ts_df[line,2]) | |
76 | line = line + 1 | |
77 | }; | |
78 | if (line >= nb_lines + 1 | |
79 | # NOTE: always second part of date/time, because it has been formatted | |
80 | || strsplit(as.character(ts_df[line-1,1])," ")[[1]][2] == predict_at) | |
81 | { | |
82 | break | |
83 | }} | |
84 | ||
85 | # NOTE: if predict_at does not cut days at midnight, | |
86 | # for the exogenous to be synchronized they need to be shifted | |
87 | if (predict_at != "00:00:00") | |
88 | { | |
89 | exo_hat = as.data.frame(exo_df[max(1,i-1),(1+nb_exos+1):(1+2*nb_exos)]) | |
90 | exo_Dm1 = if (i>=3) as.data.frame(exo_df[i-1,2:(1+nb_exos)]) else NA | |
91 | } else | |
92 | { | |
93 | exo_hat = as.data.frame(exo_df[i,(1+nb_exos+1):(1+2*nb_exos)]) | |
94 | exo_Dm1 = if (i>=2) as.data.frame(exo_df[i-1,2:(1+nb_exos)]) else NA | |
95 | } | |
96 | i = i + 1 | |
97 | #center data | |
98 | level = mean(serie, na.rm=TRUE) | |
99 | centered_serie = serie - level | |
100 | # data$append(time, centered_serie, level, exo_hat, exo_Jm1) #TODO: slow: why ? | |
101 | data[[length(data)+1]] = list("time"=time, "serie"=centered_serie, "level"=level, | |
102 | "exo_hat"=exo_hat, "exo_Dm1"=exo_Dm1) | |
103 | } | |
104 | new("Data",data=data) | |
105 | } |