calc_roc.rfsrc: Receiver Operator Characteristic calculator

Description

Receiver Operator Characteristic calculator

Usage

# S3 method for rfsrc
calc_roc(object, dta, which_outcome = "all", oob = TRUE, ...)

Value

A gg_roc

data.frame with columns sens

(sensitivity), spec (specificity), and pct (the probability threshold), with one row per unique prediction value. Suitable for passing to calc_auc or plot.gg_roc.

Arguments

object: A fitted rfsrc, predict.rfsrc, or randomForest classification object containing predicted class probabilities.
dta: A factor (or coercible to factor) of the true observed class labels, one per observation. Typically object$yvar for rfsrc or object$y for randomForest.
which_outcome: Integer index of the class for which the ROC curve is computed (e.g. 1 for the first class, 2 for the second). Use "all" to request all classes (currently falls back to class 1 with a warning).
oob: Logical; if TRUE (default for rfsrc) use OOB predicted probabilities. Forced to FALSE for randomForest objects.
...: Extra arguments passed to helper functions (currently unused).

Details

For a randomForestSRC prediction and the actual response value, calculate the specificity (1-False Positive Rate) and sensitivity (True Positive Rate) of a predictor.

This is a helper function for the gg_roc functions, and not intended for use by the end user.

Examples

Run this code

## Taken from the gg_roc example
rfsrc_iris <- randomForestSRC::rfsrc(Species ~ ., data = iris)

gg_dta <- calc_roc(rfsrc_iris, rfsrc_iris$yvar,
  which_outcome = 1, oob = TRUE
)
gg_dta <- calc_roc(rfsrc_iris, rfsrc_iris$yvar,
  which_outcome = 1, oob = FALSE
)

rf_iris <- randomForest::randomForest(Species ~ ., data = iris)
# randomForest stores the response in $y (rfsrc uses $yvar); pass the
# original training factor so calc_roc has the class labels.
gg_dta <- calc_roc(rf_iris, iris$Species,
  which_outcome = 1
)
gg_dta <- calc_roc(rf_iris, iris$Species,
  which_outcome = 2
)