calcROC: calcROC

Description

Computes the convex hull of the ROC curve created from scores and a positive class.

Usage

calcROC(score, class, positive = 1)

Arguments

score

The probability, in the range [0,1] to be scored.

class

The class of the cases. Either 0 or 1.

positive

Optional. The class for which to build the ROC curve. Defaults to 1.

Value

An object with the convex hull of the ROC curve, with all the parameters necessary to estimate EMP.
n1Number of positive cases.
n2Number of negative cases.
pi0Percentage of negative cases.
pi1Percentage of positive cases.
F1rocCumulative ROC over positive cases.
F0rocCumulative ROC over negative cases.
F1chX axis of the convex hull of the ROC curve
F0chY axis of the convex hull of ROC curve

References

Verbraken, T., Verbeke, W. & Baesens, B., 2011. Novel Profit Maximizing Metrics for Measuring Classification Performance of Customer Churn Prediction Models. IEEE Transactions on Knowledge and Data Engineering 25(2): 961-973.

Examples

Run this code

# Dummy dataset.
score.ex <- runif(1000, 0, 1)
class.ex <- lapply(score.ex, function(x){rbinom(1,1,x)})
class.ex <- unlist(class.ex)

# Calculate ROC curve.
ROC.ex <- calcROC(score.ex, class.ex)
ROC.ex