# spectralGraphTopology

spectralGraphTopology provides estimators to learn k-component, bipartite, and k-component bipartite graphs from data by imposing spectral constraints on the eigenvalues and eigenvectors of the Laplacian and adjacency matrices. Those estimators leverage spectral properties of the graphical models as a prior information which turn out to play key roles in unsupervised machine learning tasks such as clustering.

Documentation: https://mirca.github.io/spectralGraphTopology.

## Installation

From inside an R session, type:

> install.packages("spectralGraphTopology")

Alternatively, you can install the development version from GitHub:

> devtools::install_github("dppalomar/spectralGraphTopology")

#### Microsoft Windows

On MS Windows environments, make sure to install the most recent version of Rtools.

#### macOS

spectralGraphTopology depends on RcppArmadillo which requires gfortran.

## Usage: clustering

We illustrate the usage of the package with simulated data, as follows:

library(spectralGraphTopology)
library(clusterSim)
library(igraph)
set.seed(42)

# generate graph and data
n <- 50  # number of nodes per cluster
twomoon <- clusterSim::shapes.two.moon(n)  # generate data points
k <- 2  # number of components

# estimate underlying graph
S <- crossprod(t(twomoon\$data))
graph <- learn_k_component_graph(S, k = k, beta = .25, verbose = FALSE, abstol = 1e-3)

# plot
# build network
# colorify nodes and edges
colors <- c("#706FD3", "#FF5252")
V(net)\$cluster <- twomoon\$clusters
E(net)\$color <- apply(as.data.frame(get.edgelist(net)), 1,
function(x) ifelse(V(net)\$cluster[x[1]] == V(net)\$cluster[x[2]],
colors[V(net)\$cluster[x[1]]], '#000000'))
V(net)\$color <- colors[twomoon\$clusters]
# plot nodes
plot(net, layout = twomoon\$data, vertex.label = NA, vertex.size = 3)

## Contributing

We welcome all sorts of contributions. Please feel free to open an issue to report a bug or discuss a feature request.