Package: lookout 2.0.2.9000
Sevvandi Kandanaarachchi
lookout: Leave One Out Kernel Density Estimates for Outlier Detection
Outlier detection using leave-one-out kernel density estimates and extreme value theory. The bandwidth for the kernel density estimates is computed from the edge lengths of the Euclidean minimum spanning tree of the data. Using the peak-over-threshold method, a generalized Pareto distribution is fitted to the negative log of the leave-one-out kernel density estimates to identify outliers. See Kandanaarachchi and Hyndman (2022) <doi:10.1080/10618600.2021.2000425> and Hyndman, Kandanaarachchi and Turner (2026) <doi:10.48550/arXiv.2603.22636>.
Authors:
lookout_2.0.2.9000.tar.gz
lookout_2.0.2.9000.zip(r-4.7-any)lookout_2.0.2.9000.zip(r-4.6-any)lookout_2.0.2.9000.zip(r-4.5-any)
lookout_2.0.2.9000.tgz(r-4.6-any)lookout_2.0.2.9000.tgz(r-4.5-any)
lookout_2.0.2.9000.tar.gz(r-4.7-any)lookout_2.0.2.9000.tar.gz(r-4.6-any)
lookout_2.0.2.9000.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
lookout/json (API)
| # Install 'lookout' in R: |
| install.packages('lookout', repos = c('https://robjhyndman.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/sevvandi/lookout/issues
Pkgdown/docs site:https://sevvandi.github.io
Last updated from:3ae6ac4024. Checks:9 OK. Indexed: no.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel | OK | 151 | ||
| source / vignettes | OK | 271 | ||
| linux-release | OK | 160 | ||
| macos-release | OK | 112 | ||
| macos-oldrel | OK | 101 | ||
| windows-devel | OK | 97 | ||
| windows-release | OK | 100 | ||
| windows-oldrel | OK | 86 | ||
| wasm-release | OK | 127 |
Exports:autoplotfind_tda_bwlookoutlookout_tsmvscalepersisting_outliers
Dependencies:clicpp11dbscanDEoptimRdplyrevdfarvergenericsggplot2gluegtableisobandlabelinglifecyclemagrittrmlpackpillarpkgconfigpurrrR6RColorBrewerRcppRcppArmadilloRcppEnsmallenrlangrobustbaseS7scalesstringistringrtibbletidyrtidyselectutf8vctrsviridisLitewithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Plots outliers identified by lookout algorithm. | autoplot.lookoutliers |
| Plots outlier persistence for a range of significance levels. | autoplot.persistingoutliers |
| Computes the bandwidth for lookout from the minimum spanning tree. | find_tda_bw |
| Identifies outliers using the algorithm lookout. | lookout |
| Identifies outliers in univariate time series using the algorithm lookout. | lookout_ts |
| Compute robust multivariate scaled data | mvscale |
| Computes outlier persistence for a range of significance values. | persisting_outliers |