getaggr

Function that generates aggregated features based on the TSLA output.

Implementation of the tree-guided feature selection and logic aggregation approach introduced in Chen et al. (2024) <doi:10.1080/01621459.2024.2326621>. The method enables the selection and aggregation of large-scale rare binary features with a known hierarchical structure using a convex, linearly-constrained regularized regression framework. The package facilitates the application of this method to both linear regression and binary classification problems by solving the optimization problem via the smoothing proximal gradient descent algorithm (Chen et al. (2012) <doi:10.1214/11-AOAS514>).

Jianmin Chen

TSLA

Tree-Guided Rare Feature Selection and Logic Aggregation

Kun Chen

getaggr function

<dl><dt>TSLA.object</dt>
<dd>A fit output from <code>TSLA.fit()</code>,
or the <code>TSLA.fit</code> object in <code>cv.TSLA()</code>.</dd>
<dt>X_2</dt>
<dd>Expanded design matrix in matrix form.</dd>
<dt>X_2.org</dt>
<dd>Original design matrix in matrix form.</dd>
<dt>lambda.index</dt>
<dd>Index of the \(\lambda\) value selected.</dd>
<dt>alpha.index</dt>
<dd>Index of the \(\alpha\) value selected. The \(\alpha\) is
the tuning parameter for generalized lasso penalty.</dd></dl>

Arguments

Generate aggregated features — getaggr

<dl>

<dt>TSLA.object</dt>
<dd>A fit output from <code>TSLA.fit()</code>,
or the <code>TSLA.fit</code> object in <code>cv.TSLA()</code>.</dd>


<dt>X_2</dt>
<dd>Expanded design matrix in matrix form.</dd>


<dt>X_2.org</dt>
<dd>Original design matrix in matrix form.</dd>


<dt>lambda.index</dt>
<dd>Index of the \(\lambda\) value selected.</dd>


<dt>alpha.index</dt>
<dd>Index of the \(\alpha\) value selected. The \(\alpha\) is
the tuning parameter for generalized lasso penalty.</dd>

</dl>

getaggr: Generate aggregated features

Description

Usage

Value

Arguments