available

available#

Documentation for the package.

A recent developing trend in clustering is the advancement of algorithms that not only identify clusters within data, but also express and capture the uncertainty of cluster membership. Evidential clustering addresses this by using the Dempster-Shafer theory of belief functions, a framework designed to manage and represent uncertainty. This approach results in a credal partition, a structured set of mass functions that quantify the uncertain assignment of each object to potential groups. The Python package evclust, presented here, offers a suite of efficient evidence clustering algorithms as well as tools for visualizing, evaluating and analyzing credal partitions.

Utils Functions in evclust#

Functions	Description
`makeF()`	Creation of a matrix of focal sets
`get_ensembles()`	Labelled focal sets
`ev_summary()`	Summary of a credal partition by extracts basic information
`ev_plot()`	Generates plots of a credal partition
`ev_pcaplot()`	Plot PCA results with cluster colors of a credal partition
`extractMass()`	Computes different outputs from a credal partition

Evidential Clustering Algorithms in evclust#

Methods	Description	Functions
ECM	Evidential C-Means	`ecm()`
RECM	Relational Evidential C-Means	`recm()`
k-EVCLUS	K Evidential Clustering	`kevclus()`
CatECM	Categorical Evidential C-Means	`catecm()`
EGMM	Evidential Gaussian Mixture Model	`egmm()`
BPEC	Belief Peak Evidential Clustering	`bpec()`
ECMdd	Evidential C-Medoids	`ecmdd()`
MECM	Median Evidential C-Means	`mecm()`
WMVEC	Weighted Multi-View Evidential Clustering	`wmvec()`
WMVEC-FP	Weighted Multi-View Evidential Clustering With Feature Preference	`wmvec_fp()`
MECMdd-RWG	Multi-View Evidential C-Medoid with Relevance Weight estimated Globally	`mecmdd_rwg()`
MECMdd-RWL	Multi-View Evidential C-Medoid with Relevance Weight estimated Locally	`mecmdd_rwl()`
CCM	Credal C-Means	`ccm()`

Metrics Functions in evclust#

Functions	Description
`nonspecificity()`	Non specificity of a credal partition
`credalRI()`	Rand index to compare two credal partitions

Coming soon:#

Notebook examples
Belief Shift Clustering (BSC),
Dynamic evidential clustering,
Deep Evidential Clustering (DEC),
Decision tree-based evidential clustering (DTEC),
Transfer learning-based evidential c-means clustering (TECM),
Etc ..