Repository files navigation

Given a likelihood provided by the user, this package applies it to agiven matrix dataset in order to find change points in the data thatmaximize the sum of the likelihoods of all the segments.

This package provides a handful of algorithms with different timecomplexities and assumption compromises so the user is able to choosethe best one for the problem at hand.

Install the package from CRAN:

install.packages("segmentr")

Sample code using the package to identify change points in the segments’averages:

require(segmentr)#> Loading required package: segmentrmake_segment<-function(n,p)matrix(rbinom(100*n,1,p),nrow=100)data<- cbind(make_segment(5,0.1), make_segment(10,0.9), make_segment(2,0.1))mean_lik<-function(X) abs(mean(X)-0.5)* ncol(X)^2segment(data,likelihood=mean_lik,algorithm="hieralg")#> Segments (total of 3):#>#> 1:5#> 6:15#> 16:17

For an in depth step-by-step, please checkvignette("segmentr").

The work behind this package is available as awebbook.

This package is part of a Master’s degree research thesis atIME-USP, withFlorenciaLeonardias thesis adviser.

The algorithms in this package are based on apaper by Bruno M. de Castro andFlorenciaLeonardi.

Theberlin sample dataset was provided by© DeutscherWetterdienst and put together with therdwd package byBerryBoessenkool. Checkmake_berlin.Rfor the script that builds the dataset.