Do manyROC analysis with cross-validation for hyperSpec object for each variable

[!!!] // No description yet //

For reproducible results in parallel computing, set seed with parallel::clusterSetRNGStream(iseed = x)(where x is your seed) (and not with set.seed) as package parallelMap is used for paralellization.

# S3 method for hide_it
print(x, ...)

sp_manyroc_with_cv_by_variable(
  Spectra,
  variables_to_analyze,
  k_folds = 3,
  times = 10,
  seeds = NULL,
  kind = NULL
)

Arguments

x	an object used to select a method.
...	further arguments passed to or from other methods.
Spectra	hyperSpec object, that contains colum ID for spectra blocking, columns with grouping variables as well as spectroscopic information.
variables_to_analyze	(character) A character vector with names of grouping variables to use in analysis.
k_folds	(positive integer) The number of folds in k-fold cross-validation.
times	(positive integer) The number of repetitions in repeated k-fold cross-validation.
seeds	(NULL | integer) Either a vector of integers of length times to set seed for each repetition of k-fold cross-validation. For more about seeds see set.seed(). Each seed will be passed to cvo_create_folds.()
kind	character or NULL. If kind is a character string, set R's RNG to the kind desired. Use "default" to return to the R default. See ‘Details’ for the interpretation of NULL.

Value

A list with results
[!!!] Description needs more specification.

Details

[!!!] The seeds nust be at least of length 6 and meet other requirements for "L'Ecuyer-CMRG" random number generator.

[!!!] At the moment Seeding section needs revision if it is necessary to use "L'Ecuyer-CMRG" (pseudo)random number generator as set.seed() does not work with parallelMap package. Instead parallel::clusterSetRNGStream(iseed = x) (where x is your seed) should be used with parallelMap to get reproducible results.

See also

sp_manyroc_with_cv

Examples

library(manyROC)

fluorescence$ID  <- 1:nrow(fluorescence)
sp_manyroc_with_cv_by_variable(
  fluorescence[, , 500 ~ 501],
  c("gr", "class"),
  k_folds = 3,
  times = 2)
#> Exporting objects to package env on master for mode: local
#> $n_included
#>    gr class
#> 1 150   150
#> 
#> $ind_included_rows
#>       gr class
#> 1   TRUE  TRUE
#> 2   TRUE  TRUE
#> 3   TRUE  TRUE
#> 4   TRUE  TRUE
#> ...  ...   ...
#> 147 TRUE  TRUE
#> 148 TRUE  TRUE
#> 149 TRUE  TRUE
#> 150 TRUE  TRUE
#>               
#> 
#> $cvo
#> *** First non-empty element: ***
#> --- A cvo object: ----------------------------------------------------
#>  indices stratified blocked         cv_type k repetitions sample_size
#>    Train       TRUE   FALSE Repeated k-fold 3           2         150
#> ----------------------------------------------------------------------
#> 
#> *** Other elements are not shown ***
#> 
#> 
#> $results
#>     grouping      set       fold compared_groups feature median_neg cutoff
#> 1         gr training Rep1_Fold1         A vs. B       1        339    320
#> 2         gr training Rep1_Fold1         A vs. C       1        339    343
#> 3         gr training Rep1_Fold1         B vs. C       1        330    342
#> 4         gr training Rep1_Fold2         A vs. B       1        338    334
#> ...      ...      ...        ...             ...     ...        ...    ...
#> 213    class     test Rep2_Fold3        K vs. S1       2         NA    329
#> 214    class     test Rep2_Fold3         l vs. N       2         NA    337
#> 215    class     test Rep2_Fold3        l vs. S1       2         NA    342
#> 216    class     test Rep2_Fold3        N vs. S1       2         NA    327
#>                                                                           
#>     median_pos  tp  fn  fp  tn sens spec  ppv  npv  bac youden kappa  auc
#> 1          330  15  21   6  28 0.42 0.82 0.71 0.57 0.62   0.24  0.24 0.62
#> 2          344  16  13  12  22 0.55 0.65 0.57 0.63 0.60   0.20  0.20 0.50
#> 3          344  16  13  10  26 0.55 0.72 0.62 0.67 0.64   0.27  0.28 0.61
#> 4          332  25  12  17  18 0.68 0.51 0.60 0.60 0.59   0.19  0.19 0.55
#> ...        ... ... ... ... ...  ...  ...  ...  ...  ...    ...   ...  ...
#> 213         NA   9   8   6  11 0.53 0.65 0.60 0.58 0.59   0.18  0.18   NA
#> 214         NA   4   2   6   4 0.67 0.40 0.40 0.67 0.53   0.07  0.06   NA
#> 215         NA  12   5   6   4 0.71 0.40 0.67 0.44 0.55   0.11  0.11   NA
#> 216         NA   8   9   3   3 0.47 0.50 0.73 0.25 0.49  -0.03 -0.02   NA
#>                                                                          
#> 
#> $variables_included
#> [1] "gr"    "class"
#> 
#> $variables_errored
#> character(0)
#> 
#> $error_messages
#> *** First non-empty element: ***
#> NULL
#> 
#> *** Other elements are not shown ***
#> 
#>