https://github.com/tdhock/penaltyLearning

Supervised machine learning for changepoint detection
https://github.com/tdhock/penaltyLearning

Last synced: 3 months ago
JSON representation

Supervised machine learning for changepoint detection

• Host: GitHub
• URL: https://github.com/tdhock/penaltyLearning
• Owner: tdhock
• Created: 2017-01-12T21:58:14.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2023-09-06T03:31:26.000Z (over 1 year ago)
• Last Synced: 2023-11-20T16:02:57.277Z (about 1 year ago)
• Language: R
• Homepage:
• Size: 4.92 MB
• Stars: 13
• Watchers: 1
• Forks: 7
• Open Issues: 2
• Metadata Files:
  • Readme: README.org

Awesome Lists containing this project

• awesome-time-series - penaltyLearning

README

        
Algorithms for supervised learning of penalty functions for

change-point detection

[[https://github.com/tdhock/penaltyLearning/actions][https://github.com/tdhock/penaltyLearning/workflows/R-CMD-check/badge.svg]]

This R package provides a practical implementation of the algorithms

described in our ICML'13 paper, [[http://jmlr.org/proceedings/papers/v28/hocking13.html][Learning Sparse Penalties for

Change-point Detection using Max Margin Interval Regression]]. This

package can be used to learn a penalty function for predicting highly

accurate changepoints in labeled data sets such as [[https://cran.r-project.org/package=neuroblastoma][neuroblastoma]]. The

main advantage of this method is increased accuracy, relative to

unsupervised methods (such as information criteria: AIC, BIC, etc). In

particular, since we have labels that indicate where there should and

should not be changepoints, we can use them to learn a highly accurate

penalty function which minimizes the number of incorrectly predicted

labels. The learned penalty function can be used for predicting the

number of changepoints in other data (even in data without labels).

** Installation

From CRAN:

#+BEGIN_SRC R

install.packages("penaltyLearning")

#+END_SRC

From GitHub:

#+BEGIN_SRC R

if(!require(devtools))install.packages("devtools")

devtools::install_github("tdhock/penaltyLearning")

#+END_SRC

** Usage

See my useR2017 tutorial on [[https://tdhock.github.io/change-tutorial/Supervised.html][Supervised changepoint detection]] [[[https://channel9.msdn.com/events/useR-international-R-User-conferences/useR-International-R-User-2017-Conference/Introduction-to-optimal-changepoint-detection-algorithms-II?term%253Dhocking][video]]],

which explains how to use penaltyLearning in detail. [[[https://github.com/tdhock/change-tutorial][GitHub repo with

links to additional course materials]]]