DataClustering module

Class for multiscale graph-based data clustering.

This class provides an interface for multiscale graph-based data clustering [1] with PyGenStability.

param metric:

The distance metric to use. The distance function can be ‘braycurtis’, ‘canberra’, ‘chebyshev’, ‘cityblock’, ‘correlation’, ‘cosine’, ‘dice’, ‘euclidean’, ‘hamming’, ‘jaccard’, ‘jensenshannon’, ‘kulczynski1’, ‘mahalanobis’, ‘matching’, ‘minkowski’, ‘rogerstanimoto’, ‘russellrao’, ‘seuclidean’, ‘sokalmichener’, ‘sokalsneath’, ‘sqeuclidean’, ‘yule’.

type metric:

str or function, default=’euclidean’

param graph_method:

Method to construct graph from sample-by-feature matrix:

  • ‘knn-mst’ will use k-Nearest Neighbor graph combined with Minimum Spanning Tree.

  • ‘cknn-mst’ will use Continuous k-Nearest Neighbor graph [2] combined with

    Minimum Spanning Tree.

  • ‘precomputed’ assumes that data is already provided as adjacency matrix of a

    sparse graph.

type graph_method:

{‘knn-mst’, ‘cknn-mst’, ‘precomputed’}, default=’cknn-mst’

param k:

Number of neighbors considered in graph construction. This parameter is expected to be positive.

type k:

int, default=5

param delta:

Density parameter for Continuous k-Nearest Neighbor graph. This parameter is expected to be positive.

type delta:

float, default=1.0

param distance_threshold:

Optional thresholding of distance matrix.

type distance_threshold:

float, optional

param seed:

Seed forwarded to pygenstability.run for reproducible results.

type seed:

int, optional

param pgs_kwargs:

Parameters for PyGenStability, see documentation. Some possible arguments:

  • constructor (str/function): name of the generalized Markov Stability constructor,

    or custom constructor function. It must have two arguments, graph and scale.

  • min_scale (float): minimum Markov scale

  • max_scale (float): maximum Markov scale

  • n_scale (int): number of scale steps

  • with_spectral_gap (bool): normalise scale by spectral gap

type pgs_kwargs:

dict, optional

pygenstability.DataClustering.adjacency_

Sparse adjacency matrix of constructed graph.

Type:

sparse matrix of shape (n_samples, n_samples)

pygenstability.DataClustering.results_

PyGenStability results dictionary, see documentation for all arguments.

Type:

dict

pygenstability.DataClustering.labels_

List of robust partitions identified with optimal scale selection.

Type:

list of ndarray

References