Package 'tsfgrnn'

Create a ggplot object from a grnnForecast object

Description

It uses an object of class grnnForecast to create a ggplot object that plots a time series and its forecast using GRNN regression.

Usage

## S3 method for class 'grnnForecast'
autoplot(object, ...)

Arguments

object	An object of class grnnForecast.
...	additional parameter, see details.

Details

Commonly used parameters are:

• highlight. A character string indicating what elements should be highlighted. Possible values are "none" and "points". The default value is "none".

Value

The ggplot object representing a plotting with the forecast.

Examples

pred <- grnn_forecasting(USAccDeaths, h = 12, lags = 1:12, sigma = 50)
library(ggplot2)
autoplot(pred)

---

Examples of a GRNN model

Description

It shows the examples of the model associated to a grnnForecast object.

Usage

grnn_examples(forecast)

Arguments

forecast

A grnnForecast object.

Value

A matrix including the features and targets of the examples associated with the model of a grnnForecast object.

Examples

pred <- grnn_forecasting(ts(1:8), h = 1, lags = 1:2)
grnn_examples(pred)

---

Time series forecasting using GRNN regression

Description

It applies GRNN regression to forecast the future values of a time series. The lags used as autoregressive variables are set with the lags parameter. If the user does not set the lags, these values are selected automatically.

Usage

grnn_forecasting(
  timeS,
  h,
  lags = NULL,
  sigma = "ROLLING",
  msas = c("recursive", "MIMO"),
  transform = c("additive", "multiplicative", "none")
)

Arguments

timeS	A numeric vector or time series of class ts.
h	A positive integer. Number of periods for forecasting.
lags	An integer vector in increasing order expressing the lags used as autoregressive variables. If NULL (the default) the lags are selected in a fast, heuristic way. It is also possible to use the values "FS" and "BE", in which case, the lags are selected using forward selection or backward elimination respectively. These techniques are feature selection approaches.
sigma	A positive real value or a character value. The smoothing parameter in GRNN regression. Two character values are possible, "ROLLING" (the default) and "FIXED", in which case the parameter is chosen using an optimization tool with rolling origin evaluation or fixed origin evaluation.
msas	A string indicating the Multiple-Step Ahead Strategy used when more than one value is predicted. It can be "MIMO" or "recursive" (the default).
transform	A character value indicating whether the training samples are transformed. If the time series has a trend it is recommended. By default is "additive" (additive transformation). It is also possible a multiplicative transformation or no transformation.

Value

An object of class "grnnForecast". The function summary can be used to obtain or print a summary of the results. An object of class "gnnForecast" is a list containing at least the following components:

call	the matched call.
msas	the Multi-Step Ahead Strategy.
prediction	a time series with the forecast.
model	an object of class "grnnModel" with the GRNN model

References

F. Martinez et al. (2022). "Strategies for time series forecasting with generalized regression neural networks", Neurocomputing, 491, pp. 509–521.

Examples

pred <- grnn_forecasting(USAccDeaths, h = 12, lags = 1:12)
plot(pred)

---

Training examples and their corresponding weights used in a prediction

Description

It shows the input vector and the weights of the training examples used in a prediction associated with a "grnnForecast" object.

Usage

grnn_weights(forecast)

Arguments

forecast

A grnnForecast object.

Value

A list including the input vectors used in GRNN regression and the training examples, with their weights, used in the prediction.

Examples

pred <- grnn_forecasting(UKgas, h = 4, lags = 1:4, msas = "MIMO")
grnn_weights(pred)

---

Plot an example used in a prediction of a grnnForecast object

Description

This function is useful to see how the forecast has been computed. An ordinal specifying the order of the weight has to be supplied and the function plots the training pattern associated with that ordinal.

Usage

plot_example(forecast, position, h = 1)

Arguments

forecast	The grnnForecast object.
position	An integer. It is an ordinal number indicating what training pattern to plot. For instance, if position is 1 it means that the training pattern with the greatest weight should be plotted. If position is 2 the training pattern with the second greatest weight is plotted and so on.
h	An integer. This value is only useful when the recursive strategy is being used. It indicates the forecasting horizon

Value

A ggplot object representing an example used in the prediction.

Examples

pred <- grnn_forecasting(USAccDeaths, h = 12, lags = 1:12, sigma = 50)
library(ggplot2)
plot_example(pred, 1)

---

Plot the prediction for a test set

Description

It plots the forecast associated with a test set generated with the function rolling_origin.

Usage

## S3 method for class 'grnnForecastRO'
plot(x, h = NULL, ...)

Arguments

x	the object obtained from a call to rolling_origin.
h	an integer. The forecasting horizon. If NULL (the default), the maximum forecasting horizon of all the test sets is used.
...	Other plotting parameters to affect the plot.

Value

None

---

Predict method for GRNN models for time series forecasting.

Description

Predicted values based on a GRNN model for time series forecasting.

Usage

## S3 method for class 'grnnForecast'
predict(object, h, ...)

Arguments

object	a grnnForecast object obtained by a call to the grnn_forecasting function.
h	an integer. The forecasting horizon.
...	further arguments passed to or from other methods.

Details

If the models uses the MIMO strategy for multiple-step ahead prediction, the forecasting horizon is fixed to the model forecasting horizon.

Value

a grnnForecast object with the prediction and information about the GRNN model, see the documentation of grnn_forecasting for the structure of grnnForecast objects.

Examples

pred <- grnn_forecasting(UKgas, h = 4, msas = "MIMO")
new_pred <- predict(pred, h = 4)
print(new_pred$prediction)
plot(new_pred) # To see a plot with the forecast

---

Assessing forecasting accuracy with rolling origin

Description

It uses the model and the time series associated with a grnnForecast object to assess the forecasting accuracy of the model using the last h values of the time series to build test sets applying a rolling origin evaluation.

Usage

rolling_origin(grnnf, h = NULL, rolling = TRUE)

Arguments

grnnf	A grnnForecast object.
h	A positive integer. The forecast horizon. If NULL (the default) the prediction horizon of the gnnForecast object is used.
rolling	A logical. If TRUE (the default), forecasting horizons from 1 to h are used. Otherwise, only horizon h is used.

Details

This function assesses the forecast accuracy of the model used by the grnnForecast object. It uses h different test and training sets. The first test set consists of the last h values of the time series (the training set is formed by the previous values). The next test set consists of the last $h - 1$ values of the time series and so on (the last test set is formed by the last value of the time series).

Value

A list containing at least the following fields:

test_sets	a matrix containing the test sets used in the evaluation. Every row contains a different test set.
predictions	The predictions for the test sets.
errors	The errors for the test sets.
global_accu	Different measures of accuracy applied to all the errors.
h_accu	Different measures of accuracy applied to all the errors for every forecasting horizon.

Examples

pred <- grnn_forecasting(UKgas, h = 4, lags = 1:4)
ro <- rolling_origin(pred)
print(ro$global_accu)

---