Unified tidy changepoint detection with ggplot2 visualisation.
Details
ggchangepoint provides a consistent S3 result class (ggcpt)
for changepoint detection results, broom-style methods
(tidy(), glance(), augment()), ggplot2
integration via autoplot() and composable geoms
(geom_changepoint(), geom_cpt_segment(),
geom_cpt_ci(), stat_changepoint()), and a unified dispatcher
cpt_detect() that supports over thirty methods.
**Detection engines.** cpt_detect() currently dispatches to 31
methods across five families (run cpt_methods() for the live
table with installation status):
Penalised/optimal: PELT, BinSeg, SegNeigh, AMOC (changepoint); FPOP (fpop); the CROPS penalty path (
cpt_crops()); fastcpd (fastcpd, incl. AR/ARMA/GARCH); change-in-slope via CPOP (cpop).Multiscale/search: WBS (wbs), WBS2 and TGUH (breakfast), NOT (not), MOSUM incl. multiscale (mosum), Isolate-Detect (IDetect), SMUCE/HSMUCE with confidence intervals (stepR).
Nonparametric/kernel: NP (changepoint.np), E-Divisive/E-Agglo (ecp), kernel running statistics (kcpRS), NP-MOJO (CptNonPar), sequential CPM (cpm), self-normalisation (SNSeg).
Bayesian: Barry-Hartigan posterior (bcp), online BOCPD (ocp), BEAST model averaging (Rbeast).
Multivariate/high-dimensional and regression: sparse projection (InspectChangepoint), online ocd (ocd), geometric mapping (changepoint.geo), Bai-Perron breaks with CIs (strucchange), broken-line regression (segmented), changepoints-vs-autocorrelation model selection (EnvCpt), drift+AR robust detection (DeCAFS).
**Key features.** Every detector returns a ggcpt object with a stable
tibble(cp, cp_value) contract (plus engine extras such as
ci_lower/ci_upper and posterior_prob). Visualise any
result directly with autoplot() (confidence intervals, fitted
signals, multivariate facets), the Bayesian displays
(ggcpt_posterior(), ggcpt_runlength()), or interactively
via ggcpt_interactive(). Compare methods with
ggcpt_compare(); run panels of series with cpt_batch();
quantify uncertainty with cpt_stability(); sweep penalties with
cpt_crops(). Evaluate accuracy with cpt_metrics() and
ggcpt_eval(); simulate ground-truth data with
cpt_simulate() and the canonical test signals; and cite the
methodology behind any result with cpt_cite().
Author
Maintainer: Youzhi Yu yuyouzhi666@icloud.com