Package 'fable.binary'

Neural Network Binary Time Series Forecasts

Description

Feed-forward neural networks with a single hidden layer and lagged inputs for forecasting univariate binary time series.

Usage

BINNET(formula, n_nodes = NULL, n_networks = 20, scale_inputs = TRUE, ...)

Arguments

formula	Model specification (see "Specials" section).
n_nodes	Number of nodes in the hidden layer. Default is half of the number of external regressors plus 1.
n_networks	Number of networks to fit with different random starting weights. These are then averaged when producing forecasts.
scale_inputs	If TRUE, inputs are scaled by subtracting the column means and dividing by their respective standard deviations.
...	Other arguments passed to ⁠\link[nnet]{nnet}⁠.

Details

A feed-forward neural network is fitted with a single hidden layer containing size nodes.

Exogenous regressors are used as inputs. A total of repeats networks are fitted, each with random starting weights. These are then averaged when computing forecasts.

Value

A model specification.

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year")))

---

Extract fitted values from a fable model

Description

Extracts the fitted values.

Usage

## S3 method for class 'BINNET'
fitted(object, ...)

Arguments

object	Fitted model
...	Other arguments ignored

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year"))) |>
  fitted()

---

Extract fitted values from a fable model

Description

Extracts the fitted values.

Usage

## S3 method for class 'LOGISTIC'
fitted(object, ...)

Arguments

object	Fitted model
...	Other arguments ignored

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year"))) |>
  fitted()

---

Forecast a model from the fable package

Description

Produces forecasts from a trained model.

Usage

## S3 method for class 'BINNET'
forecast(object, new_data, specials = NULL, simulate = TRUE, times = 5000, ...)

Arguments

object	A model for which forecasts are required.
new_data	A tsibble containing the time points and exogenous regressors to produce forecasts for.
specials	(passed by fabletools::forecast.mdl_df()).
simulate	If TRUE, then forecast distributions are computed using simulation from a Bernoulli model.
times	The number of sample paths to use in estimating the forecast distribution when simulate = TRUE.
...	Other arguments passed to methods

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year"))) |>
  forecast(times = 10)

---

Forecast a model from the fable package

Description

Produces forecasts from a trained model.

Usage

## S3 method for class 'LOGISTIC'
forecast(
  object,
  new_data,
  specials = NULL,
  simulate = FALSE,
  times = 5000,
  ...
)

Arguments

object	A model for which forecasts are required.
new_data	A tsibble containing the time points and exogenous regressors to produce forecasts for.
specials	(passed by fabletools::forecast.mdl_df()).
simulate	If TRUE, then forecast distributions are computed using simulation from a Bernoulli model.
times	The number of sample paths to use in estimating the forecast distribution when simulate = TRUE.
...	Other arguments passed to methods

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year"))) |>
  forecast(h = "2 years")

---

Generate new data from a fable model

Description

Simulates future paths from a dataset using a fitted model.

Usage

## S3 method for class 'BINNET'
generate(x, new_data, specials = NULL, ...)

Arguments

x	An object.
new_data	A tsibble containing the time points and exogenous regressors to produce forecasts for.
specials	(passed by fabletools::generate.mdl_df()).
...	Other arguments passed to methods

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year"))) |>
  generate()

---

Generate new data from a fable model

Description

Simulates future paths from a dataset using a fitted model.

Usage

## S3 method for class 'LOGISTIC'
generate(x, new_data, specials, ...)

Arguments

x	An object.
new_data	A tsibble containing the time points and exogenous regressors to produce forecasts for.
specials	(passed by fabletools::generate.mdl_df()).
...	Other arguments passed to methods

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year"))) |>
  generate()

---

Glance a BINNET model

Description

Construct a single row summary of the BINNET model. Contains the variance of residuals (sigma2).

Usage

## S3 method for class 'BINNET'
glance(x, ...)

Arguments

x	model or other R object to convert to single-row data frame
...	Other arguments ignored

Value

A one row tibble summarising the model's fit.

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year"))) |>
  glance()

---

Glance a LOGISTIC

Description

Construct a single row summary of the LOGISTIC model.

Usage

## S3 method for class 'LOGISTIC'
glance(x, ...)

Arguments

x	model or other R object to convert to single-row data frame
...	other arguments passed to methods

Details

Contains the R squared (r_squared), variance of residuals (sigma2), the log-likelihood (log_lik), and information criterion (AIC, AICc, BIC).

Value

A one row tibble summarising the model's fit.

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year"))) |>
  glance()

---

Fit a linear model with time series components

Description

The model formula will be handled using stats::model.matrix(), and so the the same approach to include interactions in stats::lm() applies when specifying the formula. In addition to stats::lm(), it is possible to include common_xregs in the model formula, such as trend(), season(), and fourier().

Usage

LOGISTIC(formula)

Arguments

formula

Model specification.

Value

A model specification.

Specials

xreg

Exogenous regressors can be included in a LOGISTIC model without explicitly using the xreg() special. Common exogenous regressor specials as specified in common_xregs can also be used. These regressors are handled using stats::model.frame(), and so interactions and other functionality behaves similarly to stats::lm().

xreg(...)

...	Bare expressions for the exogenous regressors (such as log(x))

See Also

stats::lm(), stats::model.matrix() Forecasting: Principles and Practices, Time series regression models (chapter 6)

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year")))

---

Daily rainfall in Melbourne, Australia

Description

A dataset containing daily rainfall amounts from 1 January 2000 to 31 December 2011.

Usage

melb_rain

Format

A tsibble data frame with 4322 rows and 3 variables.

Source

Australian Bureau of Meteorology. http://www.bom.gov.au/climate/data/

---

Refit a BINNET model

Description

Applies a fitted BINNET model to a new dataset.

Usage

## S3 method for class 'BINNET'
refit(object, new_data, specials = NULL, reestimate = FALSE, ...)

Arguments

object	A model for which forecasts are required.
new_data	A tsibble containing the time points and exogenous regressors to produce forecasts for.
specials	(passed by fabletools::forecast.mdl_df()).
reestimate	If TRUE, the networks will be initialized with random starting weights to suit the new data. If FALSE, for every network the best individual set of weights found in the pre-estimation process is used as the starting weight vector.
...	Other arguments passed to methods

Value

A refitted model.

---

Refit a LOGISTIC

Description

Applies a fitted LOGISTIC to a new dataset.

Usage

## S3 method for class 'LOGISTIC'
refit(object, new_data, specials = NULL, reestimate = FALSE, ...)

Arguments

object	A fitted model object.
new_data	A tsibble containing the time points and exogenous regressors for which a refit is required.
specials	A list of special functions used in the model, (passed by fabletools::forecast.mdl_df).
reestimate	If TRUE, the networks will be initialized with random starting weights to suit the new data. If FALSE, for every network the best individual set of weights found in the pre-estimation process is used as the starting weight vector.
...	Other arguments passed to methods

---

Extract residuals from a fable model.

Description

Extracts the residuals.

Usage

## S3 method for class 'BINNET'
residuals(object, ...)

Arguments

object	Fitted model
...	Other arguments ignored

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year"))) |>
  residuals()

---

Extract residuals from a fable model.

Description

Extracts the residuals.

Usage

## S3 method for class 'LOGISTIC'
residuals(
  object,
  type = c("deviance", "innovation", "pearson", "working", "response", "partial"),
  ...
)

Arguments

object	Fitted model
type	the type of residuals which should be returned. alternatives are: "deviance" (default), "pearson", "working", "response", and "partial". Can be abbreviated.
...	Other arguments ignored

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year"))) |>
  residuals(type = "deviance")

---

Tidy a fable model

Description

Returns the coefficients from the model in a tibble format.

Usage

## S3 method for class 'BINNET'
tidy(x, ...)

Arguments

x	An object to be converted into a tidy tibble::tibble().
...	Additional arguments to tidying method.

Examples

melb_rain |>
  model(nn = BINNET(Wet ~ fourier(K = 1, period = "year"))) |>
  tidy()

---

Tidy a fable model

Description

Returns the coefficients from the model in a tibble format.

Usage

## S3 method for class 'LOGISTIC'
tidy(x, ...)

Arguments

x	An object to be converted into a tidy tibble::tibble().
...	Additional arguments to tidying method.

Examples

melb_rain |>
  model(logistic = LOGISTIC(Wet ~ fourier(K = 5, period = "year"))) |>
  tidy()

---