Learn R Programming

The 'offlineChange' R package

Detect Multiple Change Points from Time Series

Getting Started

First install the devtools package

install.packages("devtools")

library("devtools")

Then install this package

install_github('JieGroup/offlineChange')

Using This Package

To see the available function to use, type

ls("package:offlineChange")

A quick guide of package can be found here

Reference Papers

Ding, J., Xiang, Y., Shen, L., & Tarokh, V. (2017). Multiple change point analysis: Fast implementation and strong consistency. IEEE Transactions on Signal Processing, 65(17), 4495-4510. link

J. Ding, "Multi-window method for unsupervised learning," preprint, 2019.

Acknowledgment

This research is funded by the Defense Advanced Research Projects Agency (DARPA) under grant number HR00111890040.

Copy Link

Version

Install

install.packages('offlineChange')

Monthly Downloads

183

Version

0.0.4

License

GPL-3

Maintainer

Jiahuan Ye

Last Published

April 20th, 2020

Functions in offlineChange (0.0.4)

ChangePoints

Detect Number and Location of Change Points of Independent Data
GetMle

Estimate Coefficients
GetLogLik

Get Log Likelihood
ScorePlot

Plot score
ChangePointsPlot

Plot Peak Ranges of Change Points
OrderKmeansCpp

Detect Location of Change Points of Independent Data using Rcpp
OrderKmeans

Detect Location of Change Points of Independent Data
MultiWindow

Multi-window Change Points Detection
PriorRangeOrderKmeans

Detect Number and Location of Change Points of Independent Data with Prior Ranges
GetMleAr

Estimate Coefficients using ar Function
PriorRangeOrderKmeansCpp

Detect Location of Change Points of Independent Data with Prior Ranges using Rcpp
PeakRange

Peak Ranges Selection
RangeToPoint

Get Change Points from Peak Ranges