calc_svd_entropy_importance: Singular Value Decomposition (SVD) Analysis of Networks

In lsaravia/EcoNetwork: Ecological network analyses including multiplex networks

Singular Value Decomposition (SVD) Analysis of Networks

Description

This function performs Singular Value Decomposition (SVD) on a network adjacency matrix. It computes species importance based on the dominant singular values and returns entropy, rank, and key visualizations.

Usage

calc_svd_entropy_importance(A, threshold_factor = 1e-06)

Arguments

A	A square adjacency matrix where rows represent prey and columns represent predators. The values represent interaction strengths.

Value

A list containing:

Rank	The numerical rank of the matrix after small values are rounded for numerical stability.
Entropy	The entropy of the singular value distribution.
Prey_Importance	A data frame ranking prey species by their contribution to the largest singular value.
Predator_Importance	A data frame ranking predator species by their contribution to the largest singular value.
Singular_Values	A numeric vector of the singular values of the matrix.
Plot_Singular_Values	A ggplot object showing the distribution of singular values.
Plot_Prey_Importance	A ggplot object showing the top prey species contributing to the largest singular value.
Plot_Predator_Importance	A ggplot object showing the top predator species contributing to the largest singular value.

Examples

results <- calc_svd_entropy_importance(netData[[1]])
print(results$Rank)
print(results$Entropy)
print(results$Plot_Singular_Values)
print(results$Plot_Prey_Importance)
print(results$Plot_Predator_Importance)

lsaravia/EcoNetwork documentation built on April 5, 2025, 1:51 p.m.