cluster: Data stream clustering with tNN

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

Data stream clustering with tNN

Description

Cluster new data into an existing tNN object.

Usage

cluster(x, newdata, ...)

Arguments

x	a tNN object. Note that this function canges the original object!
newdata	a vector (one observation), or a matrix or data.frame (each row is an observation).
...	further arguments like verbose.

Details

cluster() implements tNN clustering The dissimilarity between the new observation and the centers of the clusters is calculated. The new observation is assigned to the closest cluster if the dissimilarity value is smaller than the threshold (for the state). If no such state exists, a new state is created for the observation. This simple clustering algorithm is called nearest neighbor threshold nearest neighbor (threshold NN).

NAs are handled in the data by using only the other dimensions if the data for dissimilarity computation (see package~proxy).

The clusters which the data points in the last cluster() operation where assigned to can be retrieved using the method last_clustering().

Value

A reference to the changed tNN object with the data added. Note: tNN objects store all variable data in an environment which enables us to update partial data without copying the whole object. Assignment will not create a copy! Use the provided method copy().

See Also

Class tNN, fade and dist in proxy.

Examples

## load EMMTraffic data
data(EMMTraffic)

## create empty clustering
tnn <- tNN(th=0.2, measure="eJaccard")
tnn

## cluster some data
cluster(tnn, EMMTraffic)
tnn

## what clusters were the data points assigned to?
last_clustering(tnn)

## plot the clustering as a scatterplot matrix of the cluster centers
plot(tnn)

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