Clustering: Clustering

In BouzidiImen/ClusteringR: Clustering package

Clustering

Description

This function serves to clustering data analysis using diverse methods and ploting diverses graphs

Usage

Clustering(Y, ClustMeth = "hierarchical", k = 3,
  Sotadismethod = "euclidean", Pdismethod = "euclidean",
  Cdismethod = "euclidean", Ddismethod = "euclidean",
  Hdismethod = "euclidean", Hmethod = "ward.D2", Graph = T,
  VarCart = F, IndCart = F)

Arguments

Y	a numeric matrix or a data frame with all numeric columns (Ex:consumers scores)
ClustMeth	Clustering method that must be "hierarchical", "diana", "kmeans", "sota", "pam", "clara" or "som"
k	integer, the number of clusters. It is required that 0<k<n where n is the number of observations (i.e., n = nrow(x))
Sotadismethod	character string specifying the metric to be used for calculating dissimilarities between observations for Sota method.It could be "euclidean" or "correlation"
Pdismethod	character string specifying the metric to be used for calculating dissimilarities between observations for PAM method.It could be "euclidean" or "manhattan"
Cdismethod	character string specifying the metric to be used for calculating dissimilarities between observations for Clara method.It could be "euclidean","manhattan" or "jaccard"
Ddismethod	character string specifying the metric to be used for calculating dissimilarities between observations for Diana method.It could be "euclidean" or "manhattan"
Hdismethod	The method to calculate a dissimilarity structure as produced by dist for hierarchical method.It could be :"aitchison", "euclidean", "maximum", "manhattan", "canberra","binary" or "minkowski"
Hmethod	the agglomeration method to be used ,should be "single", "complete", "average", "mcquitty", "ward.D", "ward.D2", "centroid" or "median"
Graph	TRUE if you want to visualize the dendrogram (only for Hierarchical and Diana methods )
VarCart	TRUE if you want to visualize Variables's representation
IndCart	TRUE if you want to visualize Distribution of consumers

Value

Graph,IndCart,VarCart,classes

Examples

 library(ClusteringR)
 cl=Clustering(Y=t(hedo),ClustMeth='hierarchical',
 k=3,Hdismethod='euclidean',Hmethod="ward.D2",
 Graph=FALSE,VarCart=FALSE,IndCart=FALSE)

BouzidiImen/ClusteringR documentation built on March 22, 2022, 8:50 p.m.