scalation
API
Generated with
scalation/scalation/scalation.modeling/scalation.modeling.forecasting/scalation.modeling.forecasting.multivar

scalation.modeling.forecasting.multivar

package scalation.modeling.forecasting.multivar

Members list

Type members

Classlikes

class AR_Star(y: MatrixD, hh: Int, fname: Array[String], tRng: Range, hparam: HyperParameter) extends Diagnoser, ForecastTensor

The AR_Star object is used to make an array of Auto-Regressive models, e.g., one for each variable in a multi-variate time series.

The AR_Star object is used to make an array of Auto-Regressive models, e.g., one for each variable in a multi-variate time series.

Value parameters

fname

the feature/variable names

hh

the maximum forecasting horizon (h = 1 to hh)

hparam

the hyper-parameters (defaults to `AR.hp')

tRng

the time range, if relevant (time index may suffice)

y

the response/output matrix (multi-variate time series data)

Attributes

Companion
object
Supertypes
class Diagnoser
trait Fit
trait FitM
class Object
trait Matchable
class Any
Show all
object AR_Star

The AR_Star object is used to make an array of Auto-Regressive models, e.g., one for each variable in a multi-variate time series.

The AR_Star object is used to make an array of Auto-Regressive models, e.g., one for each variable in a multi-variate time series.

Attributes

Companion
class
Supertypes
class Object
trait Matchable
class Any
Self type
AR_Star.type
trait ForecastTensor(y: MatrixD, hh: Int, tRng: Range)

The ForecastTensor trait provides a common framework for holding forecasts over time and multiple horizons.

The ForecastTensor trait provides a common framework for holding forecasts over time and multiple horizons.

Value parameters

hh

the maximum forecasting horizon (h = 1 to hh)

tRng

the time vector, if relevant (index as time may suffice)

y

the multi-variate time series data matrix [y_tj]

Attributes

Supertypes
class Object
trait Matchable
class Any
Known subtypes
class AR_Star
class VAR
class RandomWalk_Star(y: MatrixD, hh: Int, fname: Array[String], tRng: Range, hparam: HyperParameter) extends Diagnoser, ForecastTensor

The RandomWalk_Star class is used to make an array of random walk models, e.g., one for each variable in a multi-variate time series.

The RandomWalk_Star class is used to make an array of random walk models, e.g., one for each variable in a multi-variate time series.

Value parameters

fname

the feature/variable names

hh

the maximum forecasting horizon (h = 1 to hh)

hparam

the hyper-parameters (none => use null)

tRng

the time range, if relevant (time index may suffice)

y

the response/output matrix (multi-variate time series data)

Attributes

Companion
object
Supertypes
class Diagnoser
trait Fit
trait FitM
class Object
trait Matchable
class Any
Show all
object RandomWalk_Star

The RandomWalk_Star companion object is used to make an array of random walk models, e.g., one for each variable in a multi-variate time series.

The RandomWalk_Star companion object is used to make an array of random walk models, e.g., one for each variable in a multi-variate time series.

Attributes

Companion
class
Supertypes
class Object
trait Matchable
class Any
Self type
class VAR(x: MatrixD, y: MatrixD, hh: Int, fname: Array[String], tRng: Range, hparam: HyperParameter, bakcast: Boolean) extends Diagnoser, ForecastTensor, Model

The VAR class provides multi-variate time series analysis capabilities for VAR models. VAR models are similar to ARX models, except that the exogenous variables are treated as endogenous variables and are themselves forecasted. Potentially having more up-to-date forecasted values feeding into multi-horizon forecasting can improve accuracy, but may also lead to compounding of forecast errors. Given multi-variate time series data stored in matrix y, its next value y_t = combination of last p vector values of y.

The VAR class provides multi-variate time series analysis capabilities for VAR models. VAR models are similar to ARX models, except that the exogenous variables are treated as endogenous variables and are themselves forecasted. Potentially having more up-to-date forecasted values feeding into multi-horizon forecasting can improve accuracy, but may also lead to compounding of forecast errors. Given multi-variate time series data stored in matrix y, its next value y_t = combination of last p vector values of y.

y_t = b dot x_t + e_t

where y_t is the value of y at time t and e_t is the residual/error term.

Value parameters

bakcast

whether a backcasted value is prepended to the time series (defaults to false)

fname

the feature/variable names

hh

the maximum forecasting horizon (h = 1 to hh)

hparam

the hyper-parameters (defaults to MakeMatrix4TS.hp)

tRng

the time range, if relevant (time index may suffice)

x

the input lagged time series data

y

the response/output matrix (multi-variate time series data)

Attributes

Companion
object
Supertypes
trait Model
class Diagnoser
trait Fit
trait FitM
class Object
trait Matchable
class Any
Show all
object VAR

The VAR object supports regression for Multivariate Time Series data. Given a response matrix y, a predictor matrix x is built that consists of lagged y vectors. Additional future response vectors are built for training. y_t = b dot x where x = [y_{t-1}, y_{t-2}, ... y_{t-lag}].

The VAR object supports regression for Multivariate Time Series data. Given a response matrix y, a predictor matrix x is built that consists of lagged y vectors. Additional future response vectors are built for training. y_t = b dot x where x = [y_{t-1}, y_{t-2}, ... y_{t-lag}].

Attributes

Companion
class
Supertypes
class Object
trait Matchable
class Any
Self type
VAR.type
final class aR_StarTest

Attributes

Supertypes
class Object
trait Matchable
class Any
final class aR_StarTest2

Attributes

Supertypes
class Object
trait Matchable
class Any
final class aR_StarTest3

Attributes

Supertypes
class Object
trait Matchable
class Any
final class forecastTensorTest

Attributes

Supertypes
class Object
trait Matchable
class Any
final class forecastTensorTest2

Attributes

Supertypes
class Object
trait Matchable
class Any
final class randomWalk_StarTest

Attributes

Supertypes
class Object
trait Matchable
class Any
final class randomWalk_StarTest2

Attributes

Supertypes
class Object
trait Matchable
class Any
final class randomWalk_StarTest3

Attributes

Supertypes
class Object
trait Matchable
class Any
final class vARTest

Attributes

Supertypes
class Object
trait Matchable
class Any
final class vARTest2

Attributes

Supertypes
class Object
trait Matchable
class Any
final class vARTest3

Attributes

Supertypes
class Object
trait Matchable
class Any
final class vARTest4

Attributes

Supertypes
class Object
trait Matchable
class Any
final class vARTest5

Attributes

Supertypes
class Object
trait Matchable
class Any
final class vARTest6

Attributes

Supertypes
class Object
trait Matchable
class Any

Value members

Concrete methods

def aR_StarTest(): Unit

The aR_StarTest main function tests the AR_Star class on real data: Forecasting COVID-19 using In-Sample Testing (In-ST). Test forecasts (h = 1 to hh steps ahead forecasts).

The aR_StarTest main function tests the AR_Star class on real data: Forecasting COVID-19 using In-Sample Testing (In-ST). Test forecasts (h = 1 to hh steps ahead forecasts).

runMain scalation.modeling.multivar.forecasting2.aR_StarTest

Attributes

def aR_StarTest2(): Unit

The aR_StarTest2 main function tests the AR_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts). This version explicitly uses an array of AR models.

The aR_StarTest2 main function tests the AR_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts). This version explicitly uses an array of AR models.

runMain scalation.modeling.forecasting2.multivar.aR_StarTest2

Attributes

def aR_StarTest3(): Unit

The aR_StarTest3 main function tests the AR_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts).

The aR_StarTest3 main function tests the AR_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts).

runMain scalation.modeling.forecasting2.multivar.aR_StarTest3

Attributes

def forecastTensorTest(): Unit

The forecastTensorTest3 main function tests the RandomWalk class on real data: Forecasting COVID-19 using In-Sample Testing (In-ST). Test forecasts (h = 1 to hh steps ahead forecasts).

The forecastTensorTest3 main function tests the RandomWalk class on real data: Forecasting COVID-19 using In-Sample Testing (In-ST). Test forecasts (h = 1 to hh steps ahead forecasts).

runMain scalation.modeling.forecasting2.forecastTensorTest

Attributes

def forecastTensorTest2(): Unit

The forecastTensorTest2 main function tests the RandomWalk class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts).

The forecastTensorTest2 main function tests the RandomWalk class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts).

runMain scalation.modeling.forecasting2.forecastTensorTest2

Attributes

def randomWalk_StarTest(): Unit

The randomWalk_StarTest main function tests the RandomWalk_Star class on real data: Forecasting COVID-19 using In-Sample Testing (In-ST). Test forecasts (h = 1 to hh steps ahead forecasts).

The randomWalk_StarTest main function tests the RandomWalk_Star class on real data: Forecasting COVID-19 using In-Sample Testing (In-ST). Test forecasts (h = 1 to hh steps ahead forecasts).

runMain scalation.modeling.forecasting2.multivar.randomWalk_StarTest

Attributes

def randomWalk_StarTest2(): Unit

The randomWalk_StarTest2 main function tests the RandomWalk_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts). This version explicitly uses an array of RandomWalk models.

The randomWalk_StarTest2 main function tests the RandomWalk_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts). This version explicitly uses an array of RandomWalk models.

runMain scalation.modeling.forecasting2.multivar.randomWalk_StarTest2

Attributes

def randomWalk_StarTest3(): Unit

The randomWalk_StarTest3 main function tests the RandomWalk_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts).

The randomWalk_StarTest3 main function tests the RandomWalk_Star class on real data: Forecasting COVID-19 using Train-n-Test Split (TnT) with Rolling Validation. Test forecasts (h = 1 to hh steps ahead forecasts).

runMain scalation.modeling.forecasting2.multivar.randomWalk_StarTest3

Attributes

def vARTest(): Unit

The vARTest main function tests the VAR class. This test is used to CHECK that the buildMatrix4TS method (@see apply) is working correctly. May get NaN for some maximum lags (p) due to multi-collinearity.

The vARTest main function tests the VAR class. This test is used to CHECK that the buildMatrix4TS method (@see apply) is working correctly. May get NaN for some maximum lags (p) due to multi-collinearity.

runMain scalation.modeling.forecasting.multivar.vARTest

Attributes

def vARTest2(): Unit

The vARTest2 main function tests the VAR class on real data: Forecasting Gas Furnace Data. Performs In-Sample Testing.

The vARTest2 main function tests the VAR class on real data: Forecasting Gas Furnace Data. Performs In-Sample Testing.

runMain scalation.modeling.forecasting.multivar.vARTest2

Attributes

def vARTest3(): Unit

The vARTest3 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Performs In-Sample Testing. Goal: Find the variable that works best with "new_deaths"

The vARTest3 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Performs In-Sample Testing. Goal: Find the variable that works best with "new_deaths"

runMain scalation.modeling.forecasting.multivar.vARTest3

Attributes

def vARTest4(): Unit

The vARTest4 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Performs In-Sample Testing. Goal: Find the four variables that works best with "new_deaths"

The vARTest4 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Performs In-Sample Testing. Goal: Find the four variables that works best with "new_deaths"

runMain scalation.modeling.forecasting.multivar.vARTest4

Attributes

def vARTest5(): Unit

The vARTest5 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Does TnT Testing on endogenous and exogenous variables. Determine the terms to include in the model using Stepwise on In-Sample.

The vARTest5 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Does TnT Testing on endogenous and exogenous variables. Determine the terms to include in the model using Stepwise on In-Sample.

runMain scalation.modeling.forecasting.multivar.vARTest5

Attributes

def vARTest6(): Unit

The vARTest6 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Does Rolling Validation on variables. Determine the terms to include in the model using Stepwise on In-Sample.

The vARTest6 main function tests the VAR class on real data: Forecasting COVID-19 Weekly Data. Does Rolling Validation on variables. Determine the terms to include in the model using Stepwise on In-Sample.

runMain scalation.modeling.forecasting.multivar.vARTest6

Attributes

Generated with