Tidy a(n) roc object

Tidy summarizes information about the components of a model. A model component might be a single term in a regression, a single hypothesis, a cluster, or a class. Exactly what tidy considers to be a model component varies cross models but is usually self-evident. If a model has several distinct types of components, you will need to specify which components to return.

# S3 method for roc
tidy(x, ...)

Arguments

x

An roc object returned from a call to AUC::roc().

...

Additional arguments. Not used. Needed to match generic signature only. Cautionary note: Misspelled arguments will be absorbed in ..., where they will be ignored. If the misspelled argument has a default value, the default value will be used. For example, if you pass conf.lvel = 0.9, all computation will proceed using conf.level = 0.95. Additionally, if you pass newdata = my_tibble to an augment() method that does not accept a newdata argument, it will use the default value for the data argument.

Value

A tibble::tibble() with three columns:

cutoff

The cutoff used for classification. Observations with predicted probabilities above this value were assigned class 1, and observations with predicted probabilities below this value were assigned class 0.

tpr

The true positive rate at the given cutoff.

fpr

The false positive rate at the given cutoff.

See also

tidy(), AUC::roc()

Examples

if (require("AUC", quietly = TRUE)) {
  data(churn)
  r <- roc(churn$predictions,churn$labels)

  td <- tidy(r)
  td

  library(ggplot2)

  ggplot(td, aes(fpr, tpr)) +
    geom_line()

  # compare the ROC curves for two prediction algorithms

  library(dplyr)
  library(tidyr)

  rocs <- churn %>%
    gather(algorithm, value, -labels) %>%
    nest(-algorithm) %>%
    mutate(tidy_roc = purrr::map(data, ~tidy(roc(.x$value, .x$labels)))) %>%
    unnest(tidy_roc)

  ggplot(rocs, aes(fpr, tpr, color = algorithm)) +
    geom_line()
}
#> Warning: there is no package called ‘AUC’