Generic Function - ang.cpts

Description

Generic Function

Usage

ang.cpts(object)

Arguments

Details

Generic function

Value

Numeric vector of changepoints in angle measure.

Author(s)

Thomas Grundy

See Also

ang.cpts-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
ang.cpts(x)	#retrieves the ang.cpts slot from x.

~~ Methods for Function ang.cpts<- ~~

Description

~~ Methods for function ang.cpts<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the ang.cpts slot in an object of class cpt.geo.

Generic Function - ang.cpts<-

Description

Generic function

Usage

ang.cpts(object) <- value

Arguments

Details

Generic function.

Value

Numeric vector of changepoints in angle mapping.

Author(s)

Thomas Grundy

See Also

ang.cpts<–methods

Examples

x <- new('cpt.geo')
ang.cpts(x) <- c(50,100)

~~ Methods for Function ang.cpts ~~

Description

~~ Methods for function ang.cpts ~~

Methods

signature(object = "cpt.geo")

Retrieves ang.cpts slot from an object of class cpt.geo.

Generic Function - angle

Description

Generic Function

Usage

angle(object)

Arguments

Details

Generic function

Value

Numeric vector of changepoints in distances.

Author(s)

Thomas Grundy

See Also

angle-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
angle(x)	#retrieves the angle slot from x.

~~ Methods for Function angle<- ~~

Description

~~ Methods for function angle<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the angle slot in an object of class cpt.geo.

Generic Function - angle<-

Description

Generic function

Usage

angle(object) <- value

Arguments

Details

Generic function.

Value

Numeric vector of changepoints in distances.

Author(s)

Thomas Grundy

See Also

angle<–methods

Examples

x <- new('cpt.geo')
angle(x) <- rnorm(100)

~~ Methods for Function angle ~~

Description

~~ Methods for function angle ~~

Methods

signature(object = "cpt.geo")

Retrieves angle slot from an object of class cpt.geo.

Principle angle mapping

Description

Calculates the principle angle of each time vector to the reference vector. Note data points are not translated in this function and error checking is not performed!

Usage

angle.mapping(X,ref.vec.value=rep(1,length(X[1,])))

Arguments

Details

This function calculates the principle angle between each time vector and the reference vector. Note the translation within geomcp happens outside of the function.

Value

A vector of length n is returned with the angle mapping for each time point.

Author(s)

Thomas Grundy

See Also

geomcp

Examples

X <- rbind(matrix(rnorm(100*50,2),ncol=50),matrix(rnorm(100*50,2,4),ncol=50))
ref.vec.value <- rep(1,50)
ans <- angle.mapping(X,ref.vec.value)
ans

Geometrically Inspired Multivariate Changepoint Detection

Description

Implements the high-dimensional changepoint detection method GeomCP (Grundy et al. 2020) and the related mappings used for changepoint detection. These methods view the changepoint problem from a geometrical viewpoint and aim to extract relevant geometrical features in order to detect changepoints. The geomcp() function should be your first point of call.

Details

Author(s)

Thomas Grundy [aut], Rebecca Killick [cre, ths]

Maintainer: Rebecca Killick <r.killick@lancaster.ac.uk>

References

Grundy T, Killick R, Mihalyov G (2020). “High-dimensional changepoint detection via a geometrically inspired mapping.” Stat Comput, 0(0). doi:10.1007/s11222-020-09940-y.

Killick R, Fearnhead P, Eckley IA (2012). “Optimal detection of changepoints with a linear computational cost.” J. Am. Stat. Assoc., 107(500), 1590–1598.

See Also

geomcp

Examples

X <- rbind(matrix(rnorm(100*50),ncol=50),matrix(rnorm(100*50,0,2),ncol=50))
ans <- geomcp(X)
summary(ans)

Input all required arguments into cpt.geo class - Only intended for developer use.

Description

This function helps to input all necessary information into the correct format for the cpt.geo class.

This function is called when class=TRUE. This is not intended for use by regular users of the package. It is exported for developers to call directly for speed and convenience.

WARNING: No checks on arguments are performed!

Usage

class_input(data.set, distance, angle, penalty, pen.value, test.stat,
	    msl, nquantiles, dist.cpts, ang.cpts)

Arguments

Details

This function takes all the input required for the cpt.geo class and enters it into an object.

This function is exported for developer use only. It does not perform any checks on inputs and is simply a convenience function for converting the output of the worker functions into a nice format for the cpt.geo class.

Value

An object of class cpt.geo filled with the given attributes.

Author(s)

Thomas Grundy

See Also

geomcp,plot-methods,cpt.geo

Examples

#This function should only be used by developers, see its use in geomcp.

Class "cpt.geo"

Description

A class for cpt.geo objects.

Objects from the Class

Objects can be created by calls of the form new("cpt.geo", ...).

new('cpt.geo',...):

Creates a new object with class cpt.geo

Slots

data.set:

Object of class "matrix", original data set to be analyzed for changepoints

distance:

Object of class "numeric", distance mapping of each time vector.

angle:

Object of class "numeric", angle mapping of each time vector.

penalty:

Object of class "character", type of penalty used as a text string.

pen.value:

Object of class "numeric", numeric value of penalty used.

test.stat:

Object of class "character", test statistic used for the analysis.

msl:

Object of class "numeric", minimum segment length (no. of observations between changepoints).

nquantiles:

Object of class "numeric", number of quantiles used in the empirical distribution.

dist.cpts:

Object of class "numeric", changepoint locations in the distances.

ang.cpts:

Object of class "numeric", changepoint locations in the angles.

date:

Object of class "character", date the analysis was run.

version:

Object of class "character", version number of the package when analysis was run.

Methods

ang.cpts

signature(object = "cpt.geo"): retrieves ang.cpts slot.

ang.cpts<-

signature(object = "cpt.geo"): replaces ang.cpts slot.

angle

signature(object = "cpt.geo"): retrieves angle slot.

angle<-

signature(object = "cpt.geo"): replaces angle slot.

data.set

signature(object = "cpt.geo"): retrieves data.set slot.

data.set<-

signature(object = "cpt.geo"): replaces data.set slot.

dist.cpts

signature(object = "cpt.geo"): retrieves dist.cpts slot.

dist.cpts<-

signature(object = "cpt.geo"): replaces dist.cpts slot.

distance

signature(object = "cpt.geo"): retrieves distance slot.

distance<-

signature(object = "cpt.geo"): replaces distance slot.

msl

signature(object = "cpt.geo"): retrieves msl slot.

msl<-

signature(object = "cpt.geo"): replaces msl slot.

nquantiles

signature(object = "cpt.geo"): retrieves nquantiles slot.

nquantiles<-

signature(object = "cpt.geo"): replaces nquantiles slot.

pen.value

signature(object = "cpt.geo"): retrieves pen.value slot.

pen.value<-

signature(object = "cpt.geo"): replaces pen.value slot.

penalty

signature(object = "cpt.geo"): retrieves penalty slot.

penalty<-

signature(object = "cpt.geo"): replaces penalty slot.

plot

signature(object = "cpt.geo"): returns an object from ggplot of the distance and angle mappings.

show

signature(object = "cpt.geo"): prints details of the cpt.geo object including a summary.

summary

signature(object = "cpt.geo"): prints a summary of the cpt.geo object.

test.stat

signature(object = "cpt.geo"): retrieves test.stat slot.

test.stat<-

signature(object = "cpt.geo"): replaces test.stat slot.

Author(s)

Thomas Grundy

See Also

geomcp,plot-methods,ggplot

Examples

showClass("cpt.geo")	#shows the structure of the cpt.geo class.

x=new('cpt.geo')	#creates a new object with the cpt.geo class defaults
dist.cpts(x)		#retrieves the dist.cpts slot from x
dist.cpts(x) <- c(50,100) #replaces the dist.cpts slot from x with c(50,100)

Generic Function - data.set

Description

Generic Function

Usage

data.set(object)

Arguments

Details

Generic function

Value

n by p matrix containing the data set.

Author(s)

Thomas Grundy

See Also

data.set-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
data.set(x)	#retrieves the data.set slot from x.

~~ Methods for Function data.set<- ~~

Description

~~ Methods for function data.set<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the data.set slot in an object of class cpt.geo.

Generic Function - data.set<-

Description

Generic Function

Usage

data.set(object) <- value

Arguments

Details

Generic function.

Value

n by p Matrix of data set.

Author(s)

Thomas Grundy

See Also

data.set<–methods

Examples

x <- new('cpt.geo')
data.set(x) <- matrix(rnorm(100*10),ncol=10,nrow=100)

~~ Methods for Function data.set ~~

Description

~~ Methods for function data.set ~~

Methods

signature(object = "cpt.geo")

Retrieves data.set slot from an object of class cpt.geo.

Generic Function - dist.cpts

Description

Generic Function

Usage

dist.cpts(object)

Arguments

Details

Generic function

Value

Numeric vector of changepoints in distances.

Author(s)

Thomas Grundy

See Also

dist.cpts-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
dist.cpts(x)	#retrieves the dist.cpts slot from x.

~~ Methods for Function dist.cpts<- ~~

Description

~~ Methods for function dist.cpts<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the dist.cpts slot in an object of class cpt.geo.

Generic Function - dist.cpts<-

Description

Generic function

Usage

dist.cpts(object) <- value

Arguments

Details

Generic function.

Value

Numeric vector of changepoints in distances.

Author(s)

Thomas Grundy

See Also

dist.cpts<–methods

Examples

x <- new('cpt.geo')
dist.cpts(x) <- c(50,100)

~~ Methods for Function dist.cpts ~~

Description

~~ Methods for function dist.cpts ~~

Methods

signature(object = "cpt.geo")

Retrieves dist.cpts slot from an object of class cpt.geo.

Generic Function - distance

Description

Generic Function

Usage

distance(object)

Arguments

Details

Generic function

Value

Numeric vector of changepoints in distances.

Author(s)

Thomas Grundy

See Also

distance-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
distance(x)	#retrieves the distance slot from x.

~~ Methods for Function distance<- ~~

Description

~~ Methods for function distance<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the distance slot in an object of class cpt.geo.

Generic Function - distance<-

Description

Generic function

Usage

distance(object) <- value

Arguments

Details

Generic function.

Value

Numeric vector of changepoints in distances.

Author(s)

Thomas Grundy

See Also

distance<–methods

Examples

x <- new('cpt.geo')
distance(x) <- rnorm(100)

~~ Methods for Function distance ~~

Description

~~ Methods for function distance ~~

Methods

signature(object = "cpt.geo")

Retrieves distance slot from an object of class cpt.geo.

Euclidean distance mapping

Description

Calculates the Euclidean distance of each time vector to the reference vector. Note data points are not translated in this function and error checking is not performed!

Usage

distance.mapping(X,ref.vec.value=rep(1,length(X[1,])))

Arguments

Details

This function calculates the Euclidean distance between each time vector and the reference vector. Note the translation within geomcp happens outside of the function.

Value

A vector of length n is returned with the distance mapping for each time point.

Author(s)

Thomas Grundy

See Also

geomcp

Examples

X <- rbind(matrix(rnorm(100*50,2),ncol=50),matrix(rnorm(100*50,2.5),ncol=50))
ref.vec.value <- rep(1,50)
ans <- distance.mapping(X,ref.vec.value)
ans

Multivariate changepoint detection via two geometric mappings

Description

Implements the GeomCP algorithm (Grundy et al. 2020). This algorithm performs two geometric mappings on multivariate time series based on the Euclidean distance and principle angle between each time vector and a pre-specified reference vector. The univariate changepoint detection method PELT, (Killick et al. 2012), is then performed on the two mappings to identify changepoints which correspond to those in the original multivariate time series.

Usage

geomcp(X, penalty = "MBIC", pen.value = 0, test.stat = "Normal", msl = 2,
       nquantiles = 1,MAD=FALSE,ref.vec='Default',ref.vec.value=0)

Arguments

Details

This function centralizes all time vectors using the given reference vector and then performs the distance and angle mappings from the reference vector. The univariate changepoint method PELT is then used to detect changepoints in the distance and angle mappings which correspond to changes in the multivariate time series.

Value

An object of S4 class "cpt.geo" is returned. The slots dist.cpts and ang.cpts return the changepoints identified in each measure.

Author(s)

Thomas Grundy

References

Grundy T, Killick R, Mihalyov G (2020). “High-dimensional changepoint detection via a geometrically inspired mapping.” Stat Comput, 0(0). doi:10.1007/s11222-020-09940-y.

Killick R, Fearnhead P, Eckley IA (2012). “Optimal detection of changepoints with a linear computational cost.” J. Am. Stat. Assoc., 107(500), 1590–1598.

See Also

cpt.geo,plot-methods

Examples

##Variance change in all series
set.seed(1)
X <- rbind(matrix(rnorm(100*50),ncol=50),matrix(rnorm(100*50,0,2),ncol=50))
ans <- geomcp(X)
summary(ans)
plot(ans)

##Mean change in 50% of series with a manual reference vector and non-parametric univariate 
##changepoint detection using 10 quantiles with a BIC penalty and min seg length of 5
set.seed(1)
Y <- rbind(matrix(rnorm(100*20),ncol=20),cbind(matrix(rnorm(100*10),ncol=10),
					       matrix(rnorm(100*10,1),ncol=10)))
res <- geomcp(Y,penalty='Manual',pen.value=30,test.stat='Empirical',nquantiles=10,ref.vec='Manual',
	      ref.vec.value=seq(1,10,length.out=20),msl=5)
summary(res)
plot(res)

##Different plot types for above example
#Plots mappings and changepoints
plot(res,plot.type='mappings') 
#Heatmap of data with changepoints not shown
plot(res,plot.type='full.data',changepoints=FALSE,scale.series=TRUE)
#Specific series with mappings and changepoints shown.
plot(res,plot.type='series',show.series=c(1,5,10),add.mappings=TRUE)

Generic Function - msl

Description

Generic Function

Usage

msl(object)

Arguments

Details

Generic function

Value

Numeric value of minimum segment length.

Author(s)

Thomas Grundy

See Also

msl-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
msl(x)	#retrieves the msl slot from x.

~~ Methods for Function msl<- ~~

Description

~~ Methods for function msl<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the msl slot in an object of class cpt.geo.

Generic Function - msl<-

Description

Generic function

Usage

msl(object) <- value

Arguments

Details

Generic function.

Value

Numeric value of minimum segment length.

Author(s)

Thomas Grundy

See Also

msl<–methods

Examples

x <- new('cpt.geo')
msl(x) <- 30

~~ Methods for Function msl ~~

Description

~~ Methods for function msl ~~

Methods

signature(object = "cpt.geo")

Retrieves msl slot from an object of class cpt.geo.

Generic Function - nquantiles

Description

Generic Function

Usage

nquantiles(object)

Arguments

Details

Generic function

Value

Numeric value of number of quantiles used in empirical likelihood.

Author(s)

Thomas Grundy

See Also

nquantiles-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
nquantiles(x) <- 10
nquantiles(x)	#retrieves the nquantiles slot from x.

~~ Methods for Function nquantiles<- ~~

Description

~~ Methods for function nquantiles<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the nquantiles slot in an object of class cpt.geo.

Generic Function - nquantiles<-

Description

Generic function

Usage

nquantiles(object) <- value

Arguments

Details

Generic function.

Value

Numeric value of number of quantiles used in empirical likelihood.

Author(s)

Thomas Grundy

See Also

nquantiles<–methods

Examples

x <- new('cpt.geo')
nquantiles(x) <- 10

~~ Methods for Function nquantiles ~~

Description

~~ Methods for function nquantiles ~~

Methods

signature(object = "cpt.geo")

Retrieves nquantiles slot from an object of class cpt.geo.

Generic Function - pen.value

Description

Generic Function

Usage

pen.value(object)

Arguments

Details

Generic function

Value

Numeric value of penalty used.

Author(s)

Thomas Grundy

See Also

pen.value-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
pen.value(x)	#retrieves the pen.value slot from x.

~~ Methods for Function pen.value<- ~~

Description

~~ Methods for function pen.value<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the pen.value slot in an object of class cpt.geo.

Generic Function - pen.value<-

Description

Generic function

Usage

pen.value(object) <- value

Arguments

Details

Generic function.

Value

Numeric value of the penalty used

Author(s)

Thomas Grundy

See Also

pen.value<–methods

Examples

x <- new('cpt.geo')
pen.value(x) <- 20

~~ Methods for Function pen.value ~~

Description

~~ Methods for function pen.value ~~

Methods

signature(object = "cpt.geo")

Retrieves pen.value slot from an object of class cpt.geo.

Generic Function - penalty

Description

Generic Function

Usage

penalty(object)

Arguments

Details

Generic function

Value

Character string of type of penalty used.

Author(s)

Thomas Grundy

See Also

penalty-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
penalty(x)	#retrieves the penalty slot from x.

~~ Methods for Function penalty<- ~~

Description

~~ Methods for function penalty<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the penalty slot in an object of class cpt.geo.

Generic Function - penalty<-

Description

Generic function

Usage

penalty(object) <- value

Arguments

Details

Generic function.

Value

Character string of type of penalty used.

Author(s)

Thomas Grundy

See Also

penalty<–methods

Examples

x <- new('cpt.geo')
penalty(x) <- 'Manual'

~~ Methods for Function penalty ~~

Description

~~ Methods for function penalty ~~

Methods

signature(object = "cpt.geo")

Retrieves penalty slot from an object of class cpt.geo.

~~ Methods for Function plot ~~

Description

~~ Methods for function plot ~~

Methods

signature(x='ANY')

Generic plot function, see graphics package using ?plot.

signature(x = "cpt.geo")

Plots the angle and distance mappings with changepoints as vertical lines. There are 3 different plotting options controlled using plot.type. Default is "mappings" which plots the distance and angle mappings; "full.data" produces a heatmap of all the series; "series" plots specific series. Use the argumentshow.series to give a vector containing the series to show in if plot.type is "series" and the logical argument add.mappings controls whether the mappings will also be shown. changepoints is a logical argument and controls whether the changepoints will be plotted or not. scale.series is a logical argument and controls whether the data should be scaled using the MAD transformation - this can be used with "full.data" or "series" plot types.

~~ Methods for Function show ~~

Description

~~ Methods for function show ~~

Methods

signature(object = "cpt.geo")

Prints out information contained within the object including a summary.

~~ Methods for Function summary ~~

Description

~~ Methods for function summary ~~

Methods

signature(object = "ANY")

Generic summary function, see back package description using ?summary.

signature(object = "cpt.geo")

Prints out a summary of the object to the terminal.

Generic Function - test.stat

Description

Generic Function

Usage

test.stat(object)

Arguments

Details

Generic function

Value

Character string of test statistic used.

Author(s)

Thomas Grundy

See Also

test.stat-methods

Examples

x <- new('cpt.geo')	#new cpt.geo object
test.stat(x)	#retrieves the test.stat slot from x.

~~ Methods for Function test.stat<- ~~

Description

~~ Methods for function test.stat<- ~~

Methods

signature(object = "cpt.geo")

Assigns the value following <- to the test.stat slot in an object of class cpt.geo.

Generic Function - test.stat<-

Description

Generic function

Usage

test.stat(object) <- value

Arguments

Details

Generic function.

Value

Character string of type of test statistic used.

Author(s)

Thomas Grundy

See Also

test.stat<–methods

Examples

x <- new('cpt.geo')
test.stat(x) <- 'Normal'

~~ Methods for Function test.stat ~~

Description

~~ Methods for function test.stat ~~

Methods

signature(object = "cpt.geo")

Retrieves test.stat slot from an object of class cpt.geo.