PerfsBinClassif

Computes various performance measures for binary classification tasks : true positive rate, true negative rate, accuracy, balanced accuracy, area under curve (AUC).

tree

Additions to 'party' and 'partykit' packages : tools for the interpretation of forests (surrogate trees, prototypes, etc.), feature selection (see Gregorutti et al (2017) <arXiv:1310.5726>, Hapfelmeier and Ulm (2013) <doi:10.1016/j.csda.2012.09.020>, Altmann et al (2010) <doi:10.1093/bioinformatics/btq134>) and parallelized versions of conditional forest and variable importance functions. Also modules and a shiny app for conditional inference trees.

Nicolas Robette

moreparty

A Toolbox for Conditional Inference Trees and Random Forests

PerfsBinClassif function

<dl> <dt>pred</dt>
<dd>numerical vector of predicted values</dd> <dt>actual</dt>
<dd>numerical vector of actual values</dd></dl>

Arguments

Performance measures for binary classification tasks — PerfsBinClassif

<dl>

 <dt>pred</dt>
<dd>numerical vector of predicted values</dd>

 <dt>actual</dt>
<dd>numerical vector of actual values</dd>

</dl>

PerfsBinClassif: Performance measures for binary classification tasks

Description

Usage

Value

Arguments

Examples