Skip to contents

last_cv() returns the last generated “cv” object. This allows recovering a cross-validation if you have (for example) used the method cv_performance.multimodel() directly, in which case the “cv” is not saved.

set_last_cv(value) causes that value will be returned by last_cv().

Usage

last_cv()

set_last_cv(value)

Arguments

value

Any object of class “cv”.

Value

last_cv() returns a cv object,

See also

Examples

data(mcycle, package = "MASS")
m <- lm(accel ~ times, mcycle)
cv_performance(m)  # m %>% cv %>% cv_performance
#> --- Performance table ---
#> Metric: rmse
#>       train_rmse test_rmse time_cv
#> model     45.959    45.811   0.008
last_cv()      # recovers unsaved output from cv() in previous call
#> --- A “cv” object containing 1 validated model ---
#> 
#> Validation procedure: Complete k-fold Cross-Validation
#>   Number of obs in data:   133
#>   Number of test sets:      10
#>   Size of test sets:       ~13
#>   Size of training sets:  ~120
#> 
#> Model:
#> 
#> ‘model’:
#>   model class:  lm
#>   formula:      accel ~ times
#>   metric:       rmse