blob: 7c0af2b8e414d485bb82a01c06f480fbd6a0ad81 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
#' Subset an idframe data
#'
#' Subsetting method for datas of class \code{idframe}
#'
#' @param data an object of class \code{idframe}
#' @param indices the indices that need to be subsetted
#' @export
dataSlice <- function(data,indices){
# check if the class is correct
if(class(data)!='idframe')
stop("Not an idframe data")
if(!all(indices %in% seq(to=dim(data$output)[1],by=1)))
stop("Invalid indices")
trim <- data
trim$output <- trim$output[indices,,drop=F]
trim$input <- trim$input[indices,,drop=F]
if(trim$type=="freq"){
trim$frequncies <- trim$frequencies[indices]
} else {
trim$t.start <- trim$t.start + trim$Ts*(indices[1]-1)
trim$t.end <- trim$t.start + trim$Ts*(length(indices)-1)
}
return(trim)
}
#' Split data into training and validation sets
#'
#' The function splits the data into training and validation sets and returns them bundled
#' as a list. The size of the sets are determined by the parameter \code{p}.
#'
#' @param data an object of class \code{idframe}
#' @param p the percentage of the data that goes to training (Default : \code{0.6})
#' @return list containing estimation and validation idframe datas
#'
#' @examples
#' data(cstr)
#' splitList <- dataPartition(cstr,p=0.6)
#' train <- splitList$estimation # training set
#' test <- splitList$validation # testing set
#'
#' @export
dataPartition <- function(data,p=0.6){
# check if the class is correct
if(class(data)!='idframe')
stop("Not an idframe data")
index <- seq_along(data$output[,1])
trainIndex <- index[1:round(p*length(index))]
testIndex <- index[!(index %in% trainIndex)]
train <- dataSlice(data,trainIndex)
test <- dataSlice(data,testIndex)
return(list(estimation=train,validation=test))
}
|
