find_elastic_variables: Conducts the Lasso Feature Selection

In lcrawlab/SINATRA: Sub Image Analysis using Topological Summary Statistics (SINATRA)

Conducts the Lasso Feature Selection

Description

find_elastic_variables returns a vector of the selected features/indices of the curve

The function uses Elastic Net to conduct feature selection. A cross validated elastic net model is fit on the binary response data, and the feature importances are extracted. Similar to lasso, the selected features are those that are non-zero. These features are returned along with a window of neighboring features if the user wishes (typically recommended).

Usage

find_elastic_variables(
  data,
  radius = 0,
  weights = FALSE,
  grouped_data = TRUE,
  alpha = 0.5
)

Arguments

data	(nxm matrix) A nxm matrix containing the covariates and responses.
radius	(positive integer ). An integer parameter specifying if, and how many neighboring features should be considered for feature selection. This is done to capture critical points that may be 'close' to the selected feature.

Value

The output is a vector of indices/features to be selected.

lcrawlab/SINATRA documentation built on Sept. 13, 2023, 2 p.m.