🧑‍🤝‍🧑 Hy-SC

Submodules

hypergraphx.communities.hy_sc.model module

class hypergraphx.communities.hy_sc.model.HySC(seed=0, inf=1e+40, n_realizations=10, out_inference=False, out_folder='../data/output/', end_file='_sc.dat')[source]

Bases: object

Implementation of Hypergraph Spectral Clustering from “Learning with hypergraphs: Clustering, classification, and embedding”, Zhou D., Huang J., Schölkopf B.

apply_kmeans(X, seed=10)[source]

Apply K-means algorithm to the eigenvectors of the Laplacian matrix.

Parameters:

  • X (matrix with eigenvectors.)

  • seed (random seed.)

Returns:

X_pred

Return type:

membership matrix.

extract_eigenvectors()[source]

Extract eigenvalues and eigenvectors of the Laplacian matrix.

fit(hypergraph, K, weighted_L=False)[source]

Perform community detection on hypergraphs with spectral clustering.

Parameters:

  • hypergraph (the hypergraph to perform inference on.)

  • K (number of communities.)

  • weighted_L (flag to use the weighted Laplacian.)

Returns:

u

Return type:

hard-membership matrix of dimension (N, K).

output_results()[source]

Save the results in a .npz file.

Module contents