sampleInitial

Sample initial solutions using a probabilistic version of Greedy algorithm.

The framework proposed in Jenul et al., (2022) <doi:10.1007/s10994-022-06221-9>, together with an interactive Shiny dashboard. 'UBayFS' is an ensemble feature selection technique embedded in a Bayesian statistical framework. The method combines data and user knowledge, where the first is extracted via data-driven ensemble feature selection. The user can control the feature selection by assigning prior weights to features and penalizing specific feature combinations. 'UBayFS' can be used for common feature selection as well as block feature selection.

Anna Jenul

UBayFS

A User-Guided Bayesian Framework for Ensemble Feature Selection

Stefan Schrunner

Kristian Hovde Liland

Oliver Tomic

Jürgen Pilz

sampleInitial function

<dl><dt>post_scores</dt>
<dd>a vector of posterior scores (prior scores + likelihood) for each feature</dd>
<dt>constraints</dt>
<dd>a list containing feature-wise constraints</dd>
<dt>size</dt>
<dd>initial number of samples to be created. The output sample size can be lower, since duplicates are removed.</dd></dl>

Arguments

Initial feature set sampling using probabilistic Greedy algorithm — sampleInitial

<dl>

<dt>post_scores</dt>
<dd>a vector of posterior scores (prior scores + likelihood) for each feature</dd>


<dt>constraints</dt>
<dd>a list containing feature-wise constraints</dd>


<dt>size</dt>
<dd>initial number of samples to be created. The output sample size can be lower, since duplicates are removed.</dd>

</dl>

sampleInitial: Initial feature set sampling using probabilistic Greedy algorithm

Description

Usage

Value

Arguments