Fast Adaptive Spectral Clustering for Single and Multi-View Data
cluster_similarity: cluster a similarity matrix using the Ng method
CNN_kernel: fast adaptive density-aware kernel
estimate_k: estimate K using the eigengap or multimodality gap heurist...
harmonise_ids: works on a list of similarity matrices to add entries o...
integrate_similarity_matrices: integrate similarity matrices using a t...
kernel_pca: A kernel pca function
mean_imputation: mean imputation function for multi-view spectral clus...
ng_kernel: Kernel from the Ng spectral clustering algorithm
pca: A pca function
rbfkernel_b: fast self-tuning kernel
sigma_finder: heuristic to find sigma for the Ng kernel
Spectrum: Fast Adaptive Spectral Clustering for Single and Multi-view ...
A self-tuning spectral clustering method for single or multi-view data. 'Spectrum' uses a new type of adaptive density aware kernel that strengthens connections in the graph based on common nearest neighbours. It uses a tensor product graph data integration and diffusion procedure to integrate different data sources and reduce noise. 'Spectrum' uses either the eigengap or multimodality gap heuristics to determine the number of clusters. The method is sufficiently flexible so that a wide range of Gaussian and non-Gaussian structures can be clustered with automatic selection of K.