build_BBQ {CalibratR}R Documentation

build_BBQ

Description

This method builds a BBQ calibration model using the trainings set provided.

Usage

build_BBQ(actual, predicted)

Arguments

actual

vector of observed class labels (0/1)

predicted

vector of uncalibrated predictions

Details

Based on the paper (and matlab code) : "Obtaining Well Calibrated Probabilities Using Bayesian Binning" by Naeini, Cooper and Hauskrecht: ; https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4410090/

Value

returns the BBQ model which includes models for all evaluated binning schemes; the prunedmodel contains only a selection of BBQ models with the best Bayesian score


[Package CalibratR version 0.1.2 Index]