ds.exposome_HCPC: Hierarchical clustering on principal components

View source: R/ds.exposome_HCPC.R

ds.exposome_HCPCR Documentation

Hierarchical clustering on principal components

Description

Perform a HCPC on the PCA/FAMD of an ExposomeSet

Usage

ds.exposome_HCPC(object, nb.clust = -1, datasources = NULL)

Arguments

object

character Object on the server created by the function ds.exposome_pca

nb.clust

numeric (default -1) Number of clusters to find. If -1, the tree is automatically cut at the suggested level (see details). If a (positive) integer, the tree is cut with nb.cluters clusters.

datasources

a list of DSConnection-class (default NULL) objects obtained after login

Details

The suggested partition is the one with the higher relative loss of inertia (i(clusters n+1)/i(cluster n)). Make use of the function FactoMineR::plot.HCPC() to visualize the results.

Value

Object created by FactoMineR::HCPC with the original dataset removed.


isglobal-brge/dsExposomeClient documentation built on March 5, 2024, 12:26 p.m.