fastcpd0.14.6 package

Fast Change Point Detection via Sequential Gradient Descent

fastcpd_ar

Find change points efficiently in AR(pp) models

fastcpd_arima

Find change points efficiently in ARIMA(pp, dd, qq) models

fastcpd_arma

Find change points efficiently in ARMA(pp, qq) models

fastcpd_binomial

Find change points efficiently in logistic regression models

fastcpd_family

Wrapper functions for fastcpd

fastcpd_garch

Find change points efficiently in GARCH(pp, qq) models

fastcpd_lasso

Find change points efficiently in penalized linear regression models

fastcpd_lm

Find change points efficiently in linear regression models

fastcpd_mean

Find change points efficiently in mean change models

fastcpd_meanvariance

Find change points efficiently in mean variance change models

fastcpd_poisson

Find change points efficiently in Poisson regression models

fastcpd_ts

Find change points efficiently in time series data

fastcpd_var

Find change points efficiently in VAR(pp) models

fastcpd_variance

Find change points efficiently in variance change models

fastcpd-class

An S4 class to store the output created with fastcpd()

fastcpd

Find change points efficiently

plot

Plot the data and the change points for a fastcpd object

print

Print the call and the change points for a fastcpd object

show

Show the available methods for a fastcpd object

summary

Show the summary of a fastcpd object

variance_arma

Variance estimation for ARMA model with change points

variance_lm

Variance estimation for linear models with change points

variance_mean

Variance estimation for mean change models

variance_median

Variance estimation for median change models

Implements fast change point detection algorithm based on the paper "Sequential Gradient Descent and Quasi-Newton's Method for Change-Point Analysis" by Xianyang Zhang, Trisha Dawn <https://proceedings.mlr.press/v206/zhang23b.html>. The algorithm is based on dynamic programming with pruning and sequential gradient descent. It is able to detect change points a magnitude faster than the vanilla Pruned Exact Linear Time(PELT). The package includes examples of linear regression, logistic regression, Poisson regression, penalized linear regression data, and whole lot more examples with custom cost function in case the user wants to use their own cost function.

  • Maintainer: Xingchi Li
  • License: GPL (>= 3)
  • Last published: 2024-11-05