Learn R Programming

ehymet: Epigraph-Hypograph based methodologies for functional data

The ehymet package define the epigraph, the hypograph and their modified versions for functional datasets in one and multiple dimensions. These indices allow to transform a functional dataset into a multivariate one, where usual clustering techniques can be applied. This package implements EHyClus method for clustering functional data in one or multiple dimension.

Related Papers:

  • Belén Pulido, Alba M. Franco-Pereira, Rosa E. Lillo (2023). “A fast epigraph and hypograph-based approach for clustering functional data.” Statistics and Computing, 33, 36. doi: 10.1007/s11222-023-10213-7

  • Belén Pulido, Alba M. Franco-Pereira, Rosa E. Lillo (2024). “Clustering multivariate functional data using the epigraph and hypograph indices: a case study on Madrid air quality.” doi: 10.48550/arXiv.2307.16720

Installation

You can install the development version of ehymet from github using the remotes package:

# install.packages("remotes")
remotes::install_github("bpulidob/ehymet")

Copy Link

Version

Install

install.packages('ehymet')

Monthly Downloads

163

Version

0.1.1

License

MIT + file LICENSE

Issues

5

Pull Requests

0

Stars

0

Forks

0

Maintainer

Belen Pulido

Last Published

November 26th, 2024

Functions in ehymet (0.1.1)

clustInd_spc

Spectral clustering using indices
EHyClus

Clustering using Epigraph and Hypograph indices
HI

Hypograph Index (HI) for a functional dataset
MEI

Modified Epigraph Index (MEI) for functional dataset.
clustInd_kmeans

K-means clustering with indices
EI

Epigraph Index (EI) for a functional dataset
clustering_validation

Create a table containing four validation metrics for clustering: Purity, F-measure and Rand Index (RI) and Adjusted Rand Index (ARI). This function considers pairs of points
generate_indices

Create a dataset with indices from a functional dataset in one or multiple dimensions
sim_model_ex1

Function for generating functional data in one dimension
MHI

Modified Hypograph Index (MHI) for a functional dataset
clustInd_hierarch

Perform hierarchical clustering for a different combinations of indices, method and distance
sim_model_ex2

Function for generating functional data in one or multiple dimension
clustInd_kkmeans

Kernel k-means clustering using indices