Introduction | Time series forecasting with KNN regression | Multi-step ahead strategies | The Multiple Input Multiple Output strategy | The recursive strategy | Additional features | Combination and distance function | Combining several models with different k parameters | Forecasting time series with a trend | Automatic forecasting | Evaluating the model | Conclusions | References
Package: tsfknn 0.7.1
tsfknn: Time Series Forecasting Using Nearest Neighbors
Allows forecasting time series using nearest neighbors regression Francisco Martinez, Maria P. Frias, Maria D. Perez-Godoy and Antonio J. Rivera (2019) <doi:10.1007/s10462-017-9593-z>. When the forecasting horizon is higher than 1, two multi-step ahead forecasting strategies can be used. The model built is univariate and autoregressive, that is, it is only based on the observations of the time series. The nearest neighbors used in a prediction can be consulted and plotted.
Authors:
tsfknn_0.7.1.tar.gz
tsfknn_0.7.1.zip(r-4.7-x86_64)tsfknn_0.7.1.zip(r-4.7-arm64)tsfknn_0.7.1.zip(r-4.6-x86_64)tsfknn_0.7.1.zip(r-4.6-arm64)tsfknn_0.7.1.zip(r-4.5-x86_64)
tsfknn_0.7.1.tgz(r-4.6-x86_64)tsfknn_0.7.1.tgz(r-4.6-arm64)tsfknn_0.7.1.tgz(r-4.5-x86_64)tsfknn_0.7.1.tgz(r-4.5-arm64)
tsfknn_0.7.1.tar.gz(r-4.7-arm64)tsfknn_0.7.1.tar.gz(r-4.7-x86_64)tsfknn_0.7.1.tar.gz(r-4.6-arm64)tsfknn_0.7.1.tar.gz(r-4.6-x86_64)
tsfknn_0.7.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
tsfknn/json (API)
| # Install 'tsfknn' in R: |
| install.packages('tsfknn', repos = c('https://franciscomartinezdelrio.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/franciscomartinezdelrio/tsfknn/issues
Last updated from:86a5e945a1. Checks:15 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-arm64 | OK | 133 | ||
| linux-devel-x86_64 | OK | 178 | ||
| source / vignettes | OK | 189 | ||
| linux-release-arm64 | OK | 149 | ||
| linux-release-x86_64 | OK | 174 | ||
| macos-release-arm64 | OK | 119 | ||
| macos-release-x86_64 | OK | 363 | ||
| macos-oldrel-arm64 | OK | 124 | ||
| macos-oldrel-x86_64 | OK | 246 | ||
| windows-devel-arm64 | OK | 209 | ||
| windows-devel-x86_64 | OK | 148 | ||
| windows-release-arm64 | OK | 218 | ||
| windows-release-x86_64 | OK | 84 | ||
| windows-oldrel-x86_64 | OK | 119 | ||
| wasm-release | OK | 108 |
Exports:knn_examplesknn_forecastingn_training_examplesnearest_neighborsrolling_origin
Dependencies:clicpp11farverggplot2gluegtableisobandlabelinglifecycleR6RColorBrewerRcpprlangS7scalesvctrsviridisLitewithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Create a ggplot object from a knnForecast object | autoplot.knnForecast |
| Training set associated to a model | knn_examples |
| Time series forecasting using KNN regression | knn_forecasting |
| Number of training examples | n_training_examples |
| Nearest neighbors associated with predictions | nearest_neighbors |
| Plot a prediction of a test set | plot.knnForecastRO |
| Predict method for KNN models for time series forecasting. | predict.knnForecast |
| Assessing forecasting accuracy with rolling origin | rolling_origin |