HCPCshiny: Hierarchical Clustering on Principal Components (HCPC) with...

In Factoshiny: Perform Factorial Analysis from 'FactoMineR' with a Shiny Application

Hierarchical Clustering on Principal Components (HCPC) with Factoshiny

Description

Performs Hierarchical Clustering on Principal Components (HCPC) o results from a factor analysis on a Shiny application.
Allows to change HCPC parameters and graphical parmeters.
Graphics can be downloaded in png, jpg and pdf.

Usage

HCPCshiny(res)

Arguments

res	Either the result of a factor analysis or a dataframe, the result of a HCPCshiny app or an HCPC result

Value

Returns several tabs:

Graphs	a tab containing the factor map,individuals colores by cluster, the 3D map (same graph but with tree above) and the tree map
Values	a tab containing the description of classes (by variables and by axes) and the parangons of each cluster
Summary of dataset	a tab containing the summary of the dataset and a boxplot and histogram for quantitative variables.
Data	a tab containing the dataset with a nice display.

The left part of the application allows to change the number of cluster very easily. Some parameters from the graphs can also be changed. By default, the numeric value of the number of clusters is set to the value advised by the HCPC function.

Author(s)

Pauline Vaissie, Astrid Monge, Francois Husson [e-mail]

See Also

HCPC, plot.HCPC
shiny website

Examples

## Not run: 
require(FactoMineR)
data(decathlon)
# HCPC with Factoshiny on a result of a factor analysis:
res.pca <- PCA(decathlon, quanti.sup = 11:12, quali.sup=13)
res.shiny=HCPCshiny(res.pca)

# HCPC with Factoshiny on a dataframe:
data(wine)
res.shiny2=HCPCshiny(wine)

# Find your app the way you left it (by clicking on the "Quit the app" button)
res.shiny3=HCPCshiny(res.shiny2)


## End(Not run)

Factoshiny documentation built on Nov. 20, 2023, 5:06 p.m.