Segment a time series using a genetic algorithm

Segmenting functions for various genetic algorithms

Usage

segment_cga(x, ...)

Arguments

x

A time series

...

arguments passed to changepointGA::GA()

Value

A cga object. This is just a changepointGA::GA() object with an additional slot for data (the original time series).

Details

segment_cga() uses the genetic algorithm in GA::ga() to "evolve" a random set of candidate changepoint sets, using the penalized objective function specified by penalty_fn. By default, the normal meanshift model is fit (see fit_meanshift_norm()) and the BIC penalty is applied.

Examples

# \donttest{
# Segment a time series using a genetic algorithm
res <- segment_cga(CET)
summary(res)
#>               Length  Class  Mode   
#> overbestfit         1 -none- numeric
#> overbestchrom       5 -none- numeric
#> bestfit         11185 -none- numeric
#> bestchrom     5603685 -none- numeric
#> count               1 -none- numeric
#> convg               1 -none- numeric
#> data              366 ts     numeric

# Segment a time series using changepointGA
x <- segment(CET, method = "cga")
summary(x)
#> 
#> ── Summary of tidycpt object ───────────────────────────────────────────────────
#> → y: Contains 366 observations, ranging from 6.86  to 11.18  .
#> ℹ Segmenter (class cga )
#> → A: Used the Genetic algorithm from the changepointGA  package.
#> → τ: Found 4 changepoint(s).
#> → f: Reported a fitness value of 641.45  using the BIC penalty.
#> ℹ Model
#> → M: Fit the arima  model.
#> → θ: Estimated 2 parameter(s), for each of 5 region(s).
changepoints(x)
#> [1]  32  40 265 329
# }