confusion_matrx: Confusion matrix

In fairmodels: Flexible Tool for Bias Detection, Visualization, and Mitigation

Confusion matrix

Description

Calculates confusion matrix for given cutoff

Usage

confusion_matrix(probs, observed, cutoff)

Arguments

probs	numeric, vector with probabilities given by model
observed	numeric, vector with actual values from outcome, either 0 or 1
cutoff	numeric, single value denoting cutoff/threshold

Value

object of class confussion_matrix It is a list with following fields:

• tpnumber of True Positives

• fpnumber of False Positives

• tnnumber of True Negatives

• fnnumber of False Negatives

Examples

probs <- rnorm(20, 0.4, 0.1)
observed <- round(runif(20))

confusion_matrix(probs, observed, 0.5)

fairmodels documentation built on Aug. 24, 2022, 1:05 a.m.