partition_cv: Partition the data for a (non-spatial) cross-validation

Description Usage Arguments Details Value See Also Examples

View source: R/sperrorest_resampling.R

Description

partition_cv creates a represampling object for length(repetition)-repeated nfold-fold cross-validation.

Usage

1
2
partition_cv(data, coords = c("x", "y"), nfold = 10, repetition = 1,
  seed1 = NULL, return_factor = FALSE)

Arguments

data

data.frame containing at least the columns specified by coords

coords

(ignored by partition_cv)

nfold

number of partitions (folds) in nfold-fold cross-validation partitioning

repetition

numeric vector: cross-validation repetitions to be generated. Note that this is not the number of repetitions, but the indices of these repetitions. E.g., use repetition = c(1:100) to obtain (the 'first') 100 repetitions, and repetition = c(101:200) to obtain a different set of 100 repetitions.

seed1

seed1+i is the random seed that will be used by set.seed in repetition i (i in repetition) to initialize the random number generator before sampling from the data set.

return_factor

if FALSE (default), return a represampling object; if TRUE (used internally by other sperrorest functions), return a list containing factor vectors (see Value)

Details

This function does not actually perform a cross-validation or partition the data set itself; it simply creates a data structure containing the indices of training and test samples.

Value

If return_factor = FALSE (the default), a represampling object. Specifically, this is a (named) list of length(repetition) resampling objects. Each of these resampling objects is a list of length nfold corresponding to the folds. Each fold is represented by a list of containing the components train and test, specifying the indices of training and test samples (row indices for data). If return_factor = TRUE (mainly used internally), a (named) list of length length(repetition). Each component of this list is a vector of length nrow(data) of type factor, specifying for each sample the fold to which it belongs. The factor levels are factor(1:nfold).

See Also

sperrorest, represampling

Examples

1
2
3
4
5
6
7
8
data(ecuador)
## non-spatial cross-validation:
resamp <- partition_cv(ecuador, nfold = 5, repetition = 5)
# plot(resamp, ecuador)
# first repetition, second fold, test set indices:
idx <- resamp[['1']][[2]]$test
# test sample used in this particular repetition and fold:
ecuador[idx , ]

sperrorest documentation built on April 1, 2018, 12:27 p.m.