Learn R Programming

gratis

The R package gratis (previously known as tsgeneration) provides efficient algorithms for generating time series with diverse and controllable characteristics.

Installation

CRAN version

install.packages("gratis")

Development version

You can install the development version of gratis package from GitHub Repository with:

devtools::install_github("ykang/gratis")

Usage

Tutorial video

Watch this YouTube video provided by Prof. Rob Hyndman.

Load the package

library(gratis)
library(feasts)

Generate diverse time series

set.seed(1)
mar_model(seasonal_periods=12) %>%
  generate(length=120, nseries=2) %>%
  autoplot(value)

Generate mutiple seasonal time series

mar_model(seasonal_periods=c(24, 24*7)) %>%
  generate(length=24*7*10, nseries=12) %>%
  autoplot(value)

Generate time series with controllable features

library(dplyr)
# Function to return spectral entropy, and ACF at lags 1 and 2
# given a numeric vector input
my_features <- function(y) {
  c(tsfeatures::entropy(y), acf = acf(y, plot = FALSE)$acf[2:3, 1, 1])
}
# Produce series with entropy = 0.5, ACF1 = 0.9 and ACF2 = 0.8
df <- generate_target(
  length = 60, feature_function = my_features, target = c(0.5, 0.9, 0.8)
)
df %>%
 as_tibble() %>%
 group_by(key) %>%
 summarise(value = my_features(value),
           feature=c("entropy","acf1", "acf2"),
           .groups = "drop")
#> # A tibble: 30 × 3
#>    key       value feature
#>    <chr>     <dbl> <chr>
#>  1 Series 1  0.533 entropy
#>  2 Series 1  0.850 acf1
#>  3 Series 1  0.735 acf2
#>  4 Series 10 0.478 entropy
#>  5 Series 10 0.880 acf1
#>  6 Series 10 0.764 acf2
#>  7 Series 2  0.507 entropy
#>  8 Series 2  0.890 acf1
#>  9 Series 2  0.899 acf2
#> 10 Series 3  0.454 entropy
#> # … with 20 more rows
autoplot(df)

Web application

You can also run the time series generation procedure in a shiny app

app_gratis()

Or visit our online Shiny APP

See also

References

License

This package is free and open source software, licensed under GPL-3.

Acknowledgements

Feng Li and Yanfei Kang are supported by the National Natural Science Foundation of China (No. 11501587 and No. 11701022 respectively). Rob J Hyndman is supported by the Australian Centre of Excellence in Mathematical and Statistical Frontiers.

Copy Link

Version

Install

install.packages('gratis')

Monthly Downloads

684

Version

1.0.7

License

GPL-3

Issues

Pull Requests

Stars

Forks

Maintainer

Feng Li

Last Published

April 10th, 2024

Functions in gratis (1.0.7)

generate.mar

Generate a tsibble of synthetic data from a Mixture Autoregressive model
mar_model

Specify parameters for a Mixture Autoregressive model
app_gratis

Web Application to generate time series with controllable features.
pi_coefficients

Compute pi coefficients of an AR process from SARIMA coefficients.
generate_msts

Generate multiple seasonal time series from random parameter spaces of the mixture autoregressive (MAR) models.
generate_ts_with_target

Generating time series with controllable features.
arima_model

Specify parameters for an ARIMA model
gratis-package

gratis: GeneRAting TIme Series with diverse and controllable characteristics
ets_model

Specify parameters for an ETS model
generate_ts

Generate time series from random parameter spaces of the mixture autoregressive (MAR) models.
rmixnorm

Generate random variables from a mixture of multivariate normal distributions
simulate_target

Generating time series with controllable features using MAR models
rmixnorm_ts

Simulate autoregressive random variables from mixture of normal
simulate.mar

Generate synthetic data from a Mixture Autoregressive model
reexports

Objects exported from other packages