smooth_transitions: Smooths transition counts between neighboring states/clusters

In rEMM: Extensible Markov Model for Modelling Temporal Relationships Between Clusters

Smooths transition counts between neighboring states/clusters

Description

Each state/cluster gets the average count if all the outgoing transitions of its neighbors (i.e., clusters which are within range x its threshold).

Usage

## S4 method for signature 'EMM'
smooth_transitions(x, range = 2, copy = TRUE)

Arguments

x	an object of class "EMM"
range	threshold multiplier for the smoothing range.
copy	logical; make a copy of x before reclustering? Otherwise the function will change x!

Value

smooth_transitions returns invisibly an object of class EMM. If copy=FALSE then it returns a reference to the changes object passed as x.

See Also

prune

Examples

data("EMMTraffic")

## learn a model
emm <- EMM(threshold=0.2, measure="eJaccard")
build(emm, EMMTraffic)

## smooth the model by adding tansitions
emm_s <- smooth_transitions(emm)

## compare graphs
op <- par(mfrow = c(1, 2), pty = "m")
plot(emm, method="MDS", main="Original")
plot(emm_s, method="MDS", main="Smoothed")
par(op)

rEMM documentation built on May 29, 2024, 4:35 a.m.