Skip to contents

Calculates the F-beta score from a confusion matrix object with an option to include bootstrapped confidence intervals. The F-beta score is a generalization of the F1 score, allowing different importance to precision and recall via the beta parameter.

Usage

dx_fbeta(cm, beta = 1, detail = "full", boot = FALSE, bootreps = 1000)

Arguments

cm

A dx_cm object created by dx_cm().

beta

The beta value determining the weight of precision in the F-score.

detail

Character specifying the level of detail in the output: "simple" for raw estimate, "full" for detailed estimate including 95% confidence intervals.

boot

Logical specifying if confidence intervals should be generated via bootstrapping. Note, this can be slow.

bootreps

The number of bootstrap replications for calculating confidence intervals.

Value

Depending on the detail parameter, returns a single numeric value of F-beta or a data frame with the F-beta and its confidence intervals.

See also

dx_f1(), dx_f2() for specific F-beta scores.

Examples

cm <- dx_cm(dx_heart_failure$predicted, dx_heart_failure$truth,
  threshold =
    0.5, poslabel = 1
)
simple_f <- dx_fbeta(cm, beta = .5, detail = "simple")
detailed_f <- dx_fbeta(cm, beta = .5)
print(simple_f)
#> [1] 0.8056872
print(detailed_f)
#> # A tibble: 1 × 8
#>   measure    summary estimate conf_low conf_high fraction conf_type notes       
#>   <chr>      <chr>      <dbl>    <dbl>     <dbl> <chr>    <chr>     <chr>       
#> 1 F0.5 Score 0.81       0.806       NA        NA ""       NA        Specify `bo…