This package is considered a duplicate. The official version of this package is found at:https://sparrow410.r-universe.dev/forecastsuite

Package: forecastsuite 1.0.2

Mukul Maheshwari

forecastsuite: Multi-Model Time Series Forecasting Toolkit and Local App

Fits, compares and visualizes univariate time series forecasts through an extensible model registry built largely on the 'forecast' package: AutoRegressive Integrated Moving Average (ARIMA) and Seasonal ARIMA (SARIMA) models (Hyndman and Khandakar (2008) <doi:10.18637/jss.v027.i03>), Error, Trend, Seasonal (ETS) exponential smoothing (Hyndman et al. (2002) <doi:10.1016/S0169-2070(01)00110-8>), Trigonometric seasonality, Box-Cox transformation, AutoRegressive Moving Average (ARMA) errors, Trend and Seasonal components (TBATS) models (De Livera, Hyndman and Snyder (2011) <doi:10.1198/jasa.2011.tm09771>), Neural Network AutoRegression (NNETAR) and Holt-Winters exponential smoothing (Winters (1960) <doi:10.1287/mnsc.6.3.324>), plus optional 'Prophet' models via the 'prophet' package (Taylor and Letham (2018) <doi:10.1080/00031305.2017.1380080>) and Long Short-Term Memory (LSTM) networks via the 'torch' package (Hochreiter and Schmidhuber (1997) <doi:10.1162/neco.1997.9.8.1735>). Also provides grouped series with bottom-up and top-down reconciliation, rolling-origin cross-validation, ensembles and residual diagnostics, following Hyndman and Athanasopoulos (2021) <https://otexts.com/fpp3/>, and a bundled local 'shiny' application exposing every model.

Authors:Mukul Maheshwari [aut, cre, cph]

forecastsuite_1.0.2.tar.gz
forecastsuite_1.0.2.zip(r-4.7-any)forecastsuite_1.0.2.zip(r-4.6-any)
forecastsuite_1.0.2.tar.gz(r-4.7-any)forecastsuite_1.0.2.tar.gz(r-4.6-any)
forecastsuite_1.0.2.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
forecastsuite/json (API)

# Install 'forecastsuite' in R:

install.packages('forecastsuite', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/sparrow410/forecast_dashboard/issues

On CRAN:

2.70 score 43 exports 87 dependencies

Last updated from:bba6f19b04. Checks:6 OK. Indexed: no.

Target	Result	Time
linux-devel	OK	292
source / vignettes	OK	238
linux-release	OK	252
windows-devel	OK	149
windows-release	OK	266
wasm-release	OK	141

Exports:always_zero_dates analyze_series build_cv_folds collapse_to_period compose_date_parts compute_forecast_bias compute_forecast_metrics compute_group_value_map compute_interval_coverage compute_multi_window_metrics compute_residual_diagnostics convert_months_to_horizon count_duplicate_periods decompose_series detect_anomalies detect_bias_drift ensemble_forecasts fixed_holiday_catalog get_model googlesheet_csv_url group_correlation_matrix holiday_contingency holiday_limitation_note holidays_with_data impute_anomalies list_models lstm_available plot_forecast_generic plot_model_comparison process_uploaded_data prophet_available read_google_sheet recommend_model reconcile_bottom_up reconcile_top_down register_model run_app run_backtest_leaderboard safe_compute_metrics split_by_group suggest_parameters suggest_parameters_for ts_frequency_for

Dependencies:askpass base64enc bslib cachem cli colorspace colourpicker commonmark cpp11 crosstalk curl data.table digest dplyr DT evaluate farver fastmap fontawesome forecast fracdiff fs generics ggplot2 glue gtable highr htmltools htmlwidgets httpuv httr isoband jquerylib jsonlite knitr labeling later lattice lazyeval lifecycle lmtest lubridate magrittr memoise mime miniUI nlme nnet openssl otel pillar pkgconfig plotly promises purrr R6 rappdirs RColorBrewer Rcpp RcppArmadillo rlang rmarkdown S7 sass scales shiny shinycssloaders shinyjs sourcetools stringi stringr sys tibble tidyr tidyselect timechange timeDate tinytex urca utf8 vctrs viridisLite withr xfun xtable yaml zoo

Getting started with forecastsuite

The bundled app | The registry API, without the app | End to end on a synthetic series | Analysis functions | Registering your own model

Rendered fromforecastsuite.Rmdusingknitr::rmarkdown

Last update: 2026-10-18
Started: 2026-10-18

Help page	Topics
Find calendar dates that are always zero or missing	always_zero_dates
Analyze a series' shape for model recommendation	analyze_series
Build rolling-origin (walk-forward) cross-validation folds	build_cv_folds
Collapse multiple rows sharing a period into one	collapse_to_period
Assemble a date from separate Year/Quarter/Month/Day columns	compose_date_parts
Signed forecast error (bias)	compute_forecast_bias
Compute MASE, sMAPE, and RMSE for a forecast	compute_forecast_metrics
Build a raw-value -> canonical-label map for a grouping column	compute_group_value_map
Empirical prediction-interval coverage	compute_interval_coverage
Score a forecast over several evaluation windows at once	compute_multi_window_metrics
Residual diagnostics for a forecast	compute_residual_diagnostics
Convert a forecast horizon in months to periods	convert_months_to_horizon
Count how many rows share a period	count_duplicate_periods
Seasonal decomposition of a series	decompose_series
Flag unusual points in a series	detect_anomalies
Check whether forecast bias is growing across the test window	detect_bias_drift
Combine several models' forecasts into one	ensemble_forecasts
Built-in fixed-date holiday catalog	fixed_holiday_catalog
Look up a registered model	get_model
Build a Google Sheets CSV export URL	googlesheet_csv_url
Pairwise correlation between grouped series	group_correlation_matrix
Run both holiday consistency checks at once	holiday_contingency
Holiday-limitation note for a model	holiday_limitation_note
Find declared holidays with non-zero data	holidays_with_data
Impute detected anomalies before fitting	impute_anomalies
List every registered model	list_models
Check whether the LSTM model is available	lstm_available
Plot a single model's forecast	plot_forecast_generic
Overlay several models' forecasts on one plot	plot_model_comparison
Turn an uploaded table into a ds/y forecasting series	process_uploaded_data
Check whether the Prophet model is available	prophet_available
Read a link-shared Google Sheet as a data frame	read_google_sheet
Rank registered models for a series	recommend_model
Bottom-up hierarchical reconciliation	reconcile_bottom_up
Top-down hierarchical reconciliation (historical proportions)	reconcile_top_down
Register a forecasting model	register_model
Launch the bundled local forecastsuite Shiny app	run_app
Multi-model rolling-origin backtest leaderboard	run_backtest_leaderboard
Compute forecast metrics, guarding against a too-short test set	safe_compute_metrics
Split a ds/y/group tibble into one tibble per group	split_by_group
Suggest starting hyperparameters for one model	suggest_parameters
Suggest starting hyperparameters for several models at once	suggest_parameters_for
Map an aggregation frequency to a ts() seasonal frequency	ts_frequency_for

Package: forecastsuite 1.0.2

forecastsuite: Multi-Model Time Series Forecasting Toolkit and Local App

Citation

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)