Learn R Programming

TSLA (version 0.1.2)

Tree-Guided Rare Feature Selection and Logic Aggregation

Description

Implementation of the tree-guided feature selection and logic aggregation approach introduced in Chen et al. (2024) . 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) ).

Copy Link

Version

Install

install.packages('TSLA')

Monthly Downloads

118

Version

0.1.2

License

GPL-3

Maintainer

Jianmin Chen

Last Published

March 17th, 2025

Functions in TSLA (0.1.2)

plot_TSLA

Plot aggregated structure
predict_TSLA

Prediction from TSLA with new data
TSLA-package

Tree-Guided Rare Feature Selection and Logic Aggregation
TSLA.fit

Solve the TSLA optimization problem
getaggr

Generate aggregated features
RegressionExample

Synthesic for the regression example
getetmat

Tree-guided expansion
coef_TSLA

Get coefficients from a fitted TSLA model
get_tree_object

Tree-guided reparameterization
cal2norm

Calculate group norms
cv.TSLA

Cross validation for TSLA
ClassificationExample

Synthesic for the classification example
predict_cvTSLA

Prediction from cross validation
getperform

Get performance metrics for classification