ClusterImpactPlots: The method 'ClusterImpactPlots' in IPPModel class

In XZPackage/IPPModel: Impact pattern plots and feature interaction networks

Description

Cluster impact curves to generate impact pattern plots.

Usage

ClusterImpactPlots()

Details

The method clusters the impact curves of each feature based on the predicting results Pred.Res. The parameters of the clustering process are defined in the field ParaTable. The clustering method is defined by the column 'clusteringMethod'; The distance measure is defined by the 'distMeasure'; the column 'centralized' determines if the impact curves are centralized or not before clustering; the 'autoK' tells if the number of clusters is determined automatically by Dunn index or not; the 'numK' determines the maximum number of clusters if autoK = TRUE; otherwise, the 'numK' means the number of clusters. The method is executed in parallel using package parallel. Each feature corresponds to one core.

Value

a list of clustering results of each feature. The result is saved in the field Clustering.Res.

See Also

IPPModel

XZPackage/IPPModel documentation built on May 17, 2019, 6:36 p.m.