mb_retrieval: A function to calculate the classification accuracy of a...

In kelvinyangli/mbmml: Learn Markov blankets using Minimum Message Length

Description

This is a function to calculate the classification accuracy of a Markov blanket learner. In details, the function calculates TP, TN, FP, FN, and returns precision and recall as outputs. If true mb is empty but learned mb is not, then both precision and recall are 0; if learned mb is empty but true mb is not, then both precision and recall are 0; if both true and learned mbs are empty, then both precision and recall are 1.

Usage

mb_retrieval(mbt, mbl, nvars)

Arguments

mbt	The true Markov blanket
mbl	The learned Markov blanket
nvars	The number of variables.

kelvinyangli/mbmml documentation built on June 29, 2020, 3:12 a.m.