package forecaster
The forecaster
package contains classes, traits and objects for forecaster.
- See also
DiffTest
for testing of the 'diff' and 'undiff' methods.
- Alphabetic
- By Inheritance
- forecaster
- Error
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Type Members
- class AR extends ForecasterVec
The
AR
class provides basic time series analysis capabilities for Auto- Regressive 'AR'.The
AR
class provides basic time series analysis capabilities for Auto- Regressive 'AR'. In an 'AR(p)' model, 'p' refers to the order of the Auto-Regressive components of the model.AR
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = δ + Σ(φ_k y_t-k)
where 'δ' is a constant, 'φ' is the autoregressive coefficient vector, and 'e' is the noise vector. ----------------------------------------------------------------------------------
- class ARIMA extends ARMA
The
ARIMA
class provides basic time series analysis capabilities for Auto- Regressive 'AR' Integrated 'I' Moving-Average 'MA' models.The
ARIMA
class provides basic time series analysis capabilities for Auto- Regressive 'AR' Integrated 'I' Moving-Average 'MA' models. In an 'ARIMA(p, d, q)' model, 'p' and 'q' refer to the order of the Auto-Regressive and Moving-Average components of the model; 'd' refers to the order of differencing. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = δ + Σ(φ_i y_t-i) + Σ(θ_i e_t-i) + e_t
where 'δ' is a constant, 'φ' is the auto-regressive coefficient vector, 'θ' is the moving-average coefficient vector, and 'e' is the noise vector. ------------------------------------------------------------------------------ If 'd > 0', then the time series must be differenced first before applying the above model. ------------------------------------------------------------------------------
- class ARMA extends ForecasterVec
The
ARMA
class provides basic time series analysis capabilities for Auto- Regressive 'AR' and Moving-Average 'MA' models.The
ARMA
class provides basic time series analysis capabilities for Auto- Regressive 'AR' and Moving-Average 'MA' models. In an 'ARMA(p, q)' model, 'p' and 'q' refer to the order of the Auto-Regressive and Moving-Average components of the model. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = δ + Σ(φ_i y_t-i) + Σ(θ_i e_t-i) + e_t
where 'δ' is a constant, 'φ' is the auto-regressive coefficient vector, 'θ' is the moving-average coefficient vector, and 'e' is the noise vector. ------------------------------------------------------------------------------
- class AR_1 extends ForecasterVec with NoFeatureSelectionF
The
AR_1
class provides basic time series analysis capabilities for Auto- Regressive 'AR'.The
AR_1
class provides basic time series analysis capabilities for Auto- Regressive 'AR'. In an 'AR_1' model, 1 refers to the order of the Auto-Regressive components of the model.AR_1
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = c + Σ(φ_k y_t-k)
where 'c' is a constant, 'φ' is the autoregressive coefficient vector, and 'e' is the noise vector. ----------------------------------------------------------------------------------
- class AR_2 extends ForecasterVec with NoFeatureSelectionF
The
AR_2
class provides basic time series analysis capabilities for Auto- Regressive 'AR'.The
AR_2
class provides basic time series analysis capabilities for Auto- Regressive 'AR'. In an 'AR_2' model, 1 refers to the order of the Auto-Regressive components of the model.AR_2
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = c + Σ(φ_k y_t-k)
where 'c' is a constant, 'φ' is the autoregressive coefficient vector, and 'e' is the noise vector. ----------------------------------------------------------------------------------
- class ELM_3L1_4TS extends ELM_3L1 with ForecasterMat
The
ELM_3L1_4TS
class uses multiple regression to fit the lagged data.The
ELM_3L1_4TS
class uses multiple regression to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (exclusive) are added before delegating the problem to theRegression
class. A constant term for intercept can be added (@see 'allForms' method) but must not include intercept (column of ones) in initial data matrix. - class ExpSmoothing extends ForecasterVec with NoFeatureSelectionF
The
ExpSmoothing
class provide very basic time series analysis capabilities of Exponential Smoothing models.The
ExpSmoothing
class provide very basic time series analysis capabilities of Exponential Smoothing models.ExpSmoothing
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior/smoothed values of 'y':y_t = s_t-1 + α (s_t-1 - s_t-2)
where vector 's' is the smoothed version of vector 'y' and 'α in [0, 1]' is the smoothing parameter. Trend and seasonality can be factored into the model with two additional smoothing parameters 'β' and 'γ', respectively.
- trait ForecasterMat extends AnyRef
The
ForecasterMat
trait add the 'forecast' method toPredictorMat
subclasses facilitating the adaption of predictive modeling techniques such asRegression
for use in forecasting, viz.The
ForecasterMat
trait add the 'forecast' method toPredictorMat
subclasses facilitating the adaption of predictive modeling techniques such asRegression
for use in forecasting, viz.Regression4TS
. Note: for forecasting, cross-validation needs to be of the rolling-validation form.- See also
the 'crossValidate' method in
RollingValidation
- abstract class ForecasterVec extends Fit with Predictor
The
ForecasterVec
abstract class provides a common framework for several forecasters.The
ForecasterVec
abstract class provides a common framework for several forecasters. Note, the 'train' method must be called first followed by 'eval'. - class KPSS_Stationarity extends UnitRoot
The
KPSS
class provides capabilities of performing KPSS test to determine if a time series is stationary around a deterministic trend.The
KPSS
class provides capabilities of performing KPSS test to determine if a time series is stationary around a deterministic trend. This code is translated from the C++ code found in- See also
github.com/olmallet81/URT.
- class KalmanFilter extends AnyRef
The
KalmanFilter
class is used to fit state-space models.The
KalmanFilter
class is used to fit state-space models.x_t = F x_t-1 + G u_t + w_t (State Equation) z_t = H x_t + v_t (Observation/Measurement Equation)
- class MA extends ForecasterVec
The
MA
class provides basic time series analysis capabilities for 'MA' models.The
MA
class provides basic time series analysis capabilities for 'MA' models. In an 'MA(q)' model, 'q' refers to the order of the Moving-Average component of the model.MA
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on the noise/residuals/shocks:y_t = c + Σ(θ_i e_t-i) + e_t
where 'c' is a constant, 'θ' is the moving-average parameters vector, and 'e' is the noise vector. ------------------------------------------------------------------------------
- class MA_1 extends ForecasterVec with NoFeatureSelectionF
The
MA_1
class provides basic time series analysis capabilities for 'MA_1' models.The
MA_1
class provides basic time series analysis capabilities for 'MA_1' models. In an 'MA_1' model, 1 refers to the order of the Moving-Average component of the model.MA_1
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on the noise/residuals/shocks:y_t = c + θ e_t-i + e_t
where 'c' is a constant, 'θ' is the moving-average parameters vector, and 'e' is the noise vector. ------------------------------------------------------------------------------
- class MovingAverage extends ForecasterVec with NoFeatureSelectionF
The
MovingAverage
class provides basic time series analysis capabilities.The
MovingAverage
class provides basic time series analysis capabilities. For a 'MovingAverage' model with the time series data stored in vector 'y', the next value 'y_t = y(t)' may be predicted based on the mean of prior values of 'y' and its noise:y_t = mean (y_t-1, ..., y_t-q) + e_t
where 'e' is the noise vector and 'q' is the number of prior values used to compute the mean.
- class MovingAverageD extends ForecasterVec with NoFeatureSelectionF
The
MovingAverageD
class provides basic time series analysis capabilities.The
MovingAverageD
class provides basic time series analysis capabilities. For a 'MovingAverageD' model with the time series data stored in vector 'y', the next value 'y_t = y(t)' may be predicted based on the mean of prior values of 'y' and its noise:y_t = mean (y_t-1, ..., y_t-q) + e_t
where 'e' is the noise vector and 'q' is the number of prior values used to compute the mean.
- class NeuralNet_3L1_4TS extends NeuralNet_3L1 with ForecasterMat
The
NeuralNet_3L1_4TS
class uses a neural network to fit the lagged data.The
NeuralNet_3L1_4TS
class uses a neural network to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (inclusive) are added before delegating the problem to theNeuralNet_3L1
class. A constant term for intercept can be added (@see 'allForms' method) but must not include intercept (column of ones) in initial data matrix. - class NeuralNet_3L1_4TSy extends NeuralNet_3L1 with ForecasterMat
The
NeuralNet_3L1_4TSy
class uses a neural network to fit the lagged data.The
NeuralNet_3L1_4TSy
class uses a neural network to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (inclusive) are added before delegating the problem to theNeuralNet_3L1
class. A constant term for intercept can be added (@see 'allForms' method). - trait NoFeatureSelectionF extends AnyRef
The
NoFeatureSelection
trait is for modeling techniques that do not support feature selection (adding/remove variables from the model).The
NoFeatureSelection
trait is for modeling techniques that do not support feature selection (adding/remove variables from the model). For example,AR_1
only has one feature/predictor variable, so feature selection makes no sense for this modeling technique. Therefore the 'forwardSel' defined inForecasterVec
is set to throw an exception. - class NullModel extends ForecasterVec with NoFeatureSelectionF
The
NullModel
class provides basic time series analysis capabilities.The
NullModel
class provides basic time series analysis capabilities. For a 'NullModel' model with the time series data stored in vector 'y', the next value 'y_t = y(t)' may be predicted based on the prior value of 'y' and its noise:y_t = ym + e_t
where 'e' is the noise vector. Random Walk is a special case of AR(1) with the parameter set to one. ------------------------------------------------------------------------------
- class QuadRegression4TS extends QuadRegression with ForecasterMat
The
QuadRegression4TS
class uses multiple regression to fit the lagged data.The
QuadRegression4TS
class uses multiple regression to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (exclusive) are added before delegating the problem to theRegression
class. A constant term for intercept can be added (@see 'allForms' method) but must not include intercept (column of ones) in initial data matrix. - class QuadRegression4TSy extends QuadRegression with ForecasterMat
The
QuadRegression4TSy
class uses a neural network to fit the lagged data.The
QuadRegression4TSy
class uses a neural network to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (inclusive) are added before delegating the problem to theQuadRegression
class. A constant term for intercept can be added (@see 'allForms' method). - class QuadSpline extends ForecasterVec with NoFeatureSelectionF
The
QuadSpline
class fits quadratic splines to time-series data that are equally spaced in time.The
QuadSpline
class fits quadratic splines to time-series data that are equally spaced in time. A sliding window consisting of three data points is perfectly fit to a quadratic curve.y_t = a + bt + ct^2
Note, slope matching and smoothness issues are ignored.
- See also
wordsandbuttons.online/quadratic_splines_are_useful_too.html Any time point from t = 3 to the end of time series may be forecasted.
- class QuadXRegression4TS extends QuadXRegression with ForecasterMat
The
QuadXRegression4TS
class uses multiple regression to fit the lagged data.The
QuadXRegression4TS
class uses multiple regression to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (exclusive) are added before delegating the problem to theRegression
class. A constant term for intercept can be added (@see 'allForms' method) but must not include intercept (column of ones) in initial data matrix. - class QuadXRegression4TSy extends QuadXRegression with ForecasterMat
The
QuadXRegression4TSy
class uses a neural network to fit the lagged data.The
QuadXRegression4TSy
class uses a neural network to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (inclusive) are added before delegating the problem to theQuadXRegression
class. A constant term for intercept can be added (@see 'allForms' method). - class RandomWalk extends ForecasterVec with NoFeatureSelectionF
The
RandomWalk
class provides basic time series analysis capabilities.The
RandomWalk
class provides basic time series analysis capabilities. For a 'RandomWalk' model with the time series data stored in vector 'y', the next value 'y_t = y(t)' may be predicted based on the prior value of 'y' and its noise:y_t = y_t-1 + e_t
where 'e' is the noise vector. Random Walk is a special case of AR(1) with the parameter set to one. ------------------------------------------------------------------------------
- class Regression4TS extends Regression with ForecasterMat
The
Regression4TS
class uses multiple regression to fit the lagged data.The
Regression4TS
class uses multiple regression to fit the lagged data. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (inclusive) are added before delegating the problem to theRegression
class. A constant term for intercept can be added (@see 'allForms' method) but must not include intercept (column of ones) in initial data matrix. - class Regression4TSy extends Regression with ForecasterMat
The
Regression4TSy
class uses multiple regression on the lagged response variable.The
Regression4TSy
class uses multiple regression on the lagged response variable. Lag columns ranging from 'lag1' (inclusive) to 'lag2' (inclusive) are added before delegating the problem to theRegression
class. A constant term for intercept can be added (@see 'allForms' method).- See also
the
ExampleEcon4
object.
- class SARIMA extends ARIMA
The
SARIMA
class provides basic time series analysis capabilities for Auto- Regressive 'AR' Integrated 'I' Moving-Average 'MA' models.The
SARIMA
class provides basic time series analysis capabilities for Auto- Regressive 'AR' Integrated 'I' Moving-Average 'MA' models. In a 'SARIMA(p, d, q)' model, 'p' and 'q' refer to the order of the Auto-Regressive and Moving-Average components of the model; 'd' refers to the order of differencing. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = δ + Σ(φ_i y_t-i) + Σ(θ_i e_t-i) + e_t
where 'δ' is a constant, 'φ' is the auto-regressive coefficient vector, 'θ' is the moving-average coefficient vector, and 'e' is the noise vector. ------------------------------------------------------------------------------ If 'd > 0', then the time series must be differenced first before applying the above model. Seasonal differencing, auto-regressive and moving average factors can be incorporated into the model by applying seasonal differencing (possibly in addition to simple differencing) first, then add the seasonal auto-regressive and moving average terms, that rely on lagged values and errors, respectively, from one or more seasonal periods in the past, on the right hand side of the equation. ------------------------------------------------------------------------------
- class SARIMAX extends ForecasterVec
The
SARIMAX
class provides basic time series analysis capabilities for Auto- Regressive 'AR' Integrated 'I' Moving-Average 'MA' models.The
SARIMAX
class provides basic time series analysis capabilities for Auto- Regressive 'AR' Integrated 'I' Moving-Average 'MA' models. In an 'SARIMAX(p, d, q)' model, 'p' and 'q' refer to the order of the Auto-Regressive and Moving-Average components of the model; 'd' refers to the order of differencing.SARIMAX
models are often used for forecasting. Given time series data stored in vector 'y', its next value 'y_t = y(t)' may be predicted based on prior values of 'y' and its noise:y_t = c + Σ(φ_i y_t-i) + Σ(θ_i e_t-i) + βχ + e_t
where 'c' is a constant, 'φ' is the autoregressive coefficient vector, 'θ' is the moving-average coefficient vector, and 'e' is the noise vector. If 'd' > 0, then the time series must be differenced first before applying the above model. Seasonal differencing, autoregressive and moving average factors can be incorporated into the model by applying seasonal differencing (possibly in addition to simple differencing) first, then add the seasonal autoregressive and moving average terms, that rely on lagged values and errors, respectively, from one or more seasonal periods in the past, on the right hand side of the equation. Exogenous/External regressor may also be added to the right-hand size of the model in a similar manner to Regression models. ------------------------------------------------------------------------------
- class SimpleExpSmoothing extends ForecasterVec with NoFeatureSelectionF
The
SimpleExpSmoothing
class provide very basic time series analysis using Simple Exponential Smoothing models.The
SimpleExpSmoothing
class provide very basic time series analysis using Simple Exponential Smoothing models. The forecasted value is the weighted average the latest value and the previous smoothed value. The smoothing parameter 'α in [0, 1]' causes the contributions of older values to decay exponentially.- See also
Smoothing Equation in section 7.1. s_t = α y_t-1 + (1 - α) s_t-1 // smoothing equation yf_t = s_t // forecast equation where vector 's' is the smoothed version of vector 'y'.
- case class Stats(y_: VectoD, lags: Int) extends Product with Serializable
The
Stats
case class is used to hold basic statistical information: mean, variance, auto-covariance, and auto-correlation.The
Stats
case class is used to hold basic statistical information: mean, variance, auto-covariance, and auto-correlation. Note gamma0 (biased) does not equal the sample variance (unbiased)- y_
the response vector (time-series data) for the training/full dataset
- lags
the maximum number of lags
- abstract class UnitRoot extends AnyRef
The
UnitRoot
abstract class provides a common framework for various unit root testers for Time Series Stationarity.The
UnitRoot
abstract class provides a common framework for various unit root testers for Time Series Stationarity. This code is translated from the C++ code found in- See also
github.com/olmallet81/URT.
Value Members
- val BASE_DIR: String
The relative path for base directory
- def diff(y: VectoD, d: Int): Unit
Take the 'd'-th difference on vector/time-series 'y'.
Take the 'd'-th difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve).
- y
the vector/time-series to be differenced
- d
the order or number of differences to be taken
- def diff(y: VectoD): Unit
Take the '1'-st difference on vector/time-series 'y'.
Take the '1'-st difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve). Note, it stores the first value in the original times-series in the first position of the differenced vector.
- y
the vector/time-series to be differenced
- def diffinv(y: VectoD, d: Int): Unit
Take the 'd'-th inverse-difference on vector/time-series 'y'.
Take the 'd'-th inverse-difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve). Restores the original time-series if 'y(0)' holds first value in original time-series.
- y
the vector/time-series to be inverse-differenced
- d
the order or number of inverse-differences to be taken
- def diffinv(y: VectoD): Unit
Take the '1'-st inverse-difference on vector/time-series 'y'.
Take the '1'-st inverse-difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve). Restores the original time-series if 'y(0)' holds first value in original time-series.
- y
the vector/time-series to be inverse-differenced
- final def flaw(method: String, message: String): Unit
- Definition Classes
- Error
- def sdiff(y: VectoD, d: Int, s: Int): Unit
Take the 'd'-th seasonal difference on vector/time-series 'y'.
Take the 'd'-th seasonal difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve).
- y
the vector/time-series to be differenced
- d
the order or number of differences to be taken
- s
the seasonal period
- def sdiff(y: VectoD, s: Int): Unit
Take the '1'-st seasonal difference on vector/time-series 'y'.
Take the '1'-st seasonal difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve).
- y
the vector/time-series to be differenced
- s
the seasonal period
- def sdiffinv(y: VectoD, d: Int, s: Int): Unit
Take the 'd'-th seasonal inverse-difference on vector/time-series 'y'.
Take the 'd'-th seasonal inverse-difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve). Restores the original time-series if 'y(0)' holds first value in original time-series.
- y
the vector/time-series to be inverse-differenced
- d
the order or number of inverse-differences to be taken
- s
the seasonal period
- def sdiffinv(y: VectoD, s: Int): Unit
Take the '1'-st seasonal inverse-difference on vector/time-series 'y'.
Take the '1'-st seasonal inverse-difference on vector/time-series 'y'. For efficiency, this method is destructive of 'y' (make a copy to preserve). Restores the original time-series if 'y(0)' holds first value in original time-series.
- y
the vector/time-series to be inverse-differenced
- s
the seasonal period
- object AR
The
AR
companion object provides factory methods for theAR
class. - object ARIMA
Companion object for class
ARIMA
.Companion object for class
ARIMA
. Includes features related to differencing and automated order selection.- See also
www.jstatsoft.org/article/view/v027i03/v27i03.pdf
- object ARIMATest extends App
The
ARIMATest
object is used to test theARIMA
class.The
ARIMATest
object is used to test theARIMA
class. > runMain scalation.analytics.forcaster.ARIMATest - object ARIMATest2 extends App
The
ARIMATest2
object is used to test theARIMA
class.The
ARIMATest2
object is used to test theARIMA
class. > runMain scalation.analytics.forecaster.ARIMATest2 - object ARIMATest3 extends App
The
ARIMATest3
object is used to test theARIMA
class on real data: Forecasting lake levels.The
ARIMATest3
object is used to test theARIMA
class on real data: Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARIMATest3
- object ARIMATest4 extends App
The
ARIMATest4
object is used to test theARIMA
class.The
ARIMATest4
object is used to test theARIMA
class. > runMain scalation.analytics.forecaster.ARIMATest4 - object ARIMATest5 extends App
The
ARIMATest5
object is used to test theARIMA
class.The
ARIMATest5
object is used to test theARIMA
class. > runMain scalation.analytics.forecaster.ARIMATest5 - object ARIMATest6 extends App
The
ARIMATest6
object is used to test theARIMA
class on real data: Forecasting lake levels.The
ARIMATest6
object is used to test theARIMA
class on real data: Forecasting lake levels. Select the best number of lags.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARIMATest6
- object ARMA
The
ARMA
companion object maintains values for hyper-parameters. - object ARMATest extends App
The
ARMATest
object is used to test theARMA
class.The
ARMATest
object is used to test theARMA
class. > runMain scalation.analytics.forecaster.ARMATest - object ARMATest2 extends App
The
ARMATest2
object is used to test theARMA
class.The
ARMATest2
object is used to test theARMA
class. > runMain scalation.analytics.forecaster.ARMATest2 - object ARMATest3 extends App
The
ARMATest3
object is used to test theARMA
class on real data: Forecasting lake levels.The
ARMATest3
object is used to test theARMA
class on real data: Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARMATest3
- object ARMATest4 extends App
The
ARMATest4
object is used to test theARMA
class.The
ARMATest4
object is used to test theARMA
class. > runMain scalation.analytics.forecaster.ARMATest4 - object ARMATest5 extends App
The
ARMATest5
object is used to test theARMA
class.The
ARMATest5
object is used to test theARMA
class. > runMain scalation.analytics.forecaster.ARMATest5 - object ARMATest6 extends App
The
ARMATest6
object is used to test theARMA
class on real data: Forecasting lake levels.The
ARMATest6
object is used to test theARMA
class on real data: Forecasting lake levels. Select the best number of lags.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARMATest6
- object ARTest extends App
The
ARTest
object is used to test theAR
class on simulated data with uniformly distributed errors.The
ARTest
object is used to test theAR
class on simulated data with uniformly distributed errors. > runMain scalation.analytics.forecaster.ARTest - object ARTest2 extends App
The
ARTest2
object is used to test theAR
class on simulated data with normally distributed errors.The
ARTest2
object is used to test theAR
class on simulated data with normally distributed errors. The order 'p' hyper-parameter should be re-assigned (try 1, 2, 3, ...). > runMain scalation.analytics.forecaster.ARTest2 - object ARTest3 extends App
The
ARTest3
object is used to test theAR
class on real data: Forecasting lake levels.The
ARTest3
object is used to test theAR
class on real data: Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARTest3
- object ARTest4 extends App
The
ARTest4
object is used to test theAR
class on real data: Forecasting traffic flow.The
ARTest4
object is used to test theAR
class on real data: Forecasting traffic flow. The order hyper-parameter 'p' should be reassigned (try 1, 2, 3, ...). > runMain scalation.analytics.forecaster.ARTest4 - object ARTest5 extends App
The
ARTest5
object is used to test theAR
class on simulated data with normally distributed errors and the response exhibits a quadratic trend.The
ARTest5
object is used to test theAR
class on simulated data with normally distributed errors and the response exhibits a quadratic trend. Note: should have p <= n / 10 for reliable QoF results from ScalaTion (FIX). > runMain scalation.analytics.forecaster.ARTest5 - object ARTest6 extends App
The
ARTest6
object is used to test theAR
class on real data: Forecasting lake levels.The
ARTest6
object is used to test theAR
class on real data: Forecasting lake levels. Performs cross-validation.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARTest6
- object ARTest7 extends App
The
ARTest7
object is used to test theAR
class on real data: Generate an AR(2) process that results in rho1 being 0.The
ARTest7
object is used to test theAR
class on real data: Generate an AR(2) process that results in rho1 being 0.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARTest7
- object ARTest8 extends App
The
ARTest8
object is used to test theAR
class on real data: Forecasting lake levels.The
ARTest8
object is used to test theAR
class on real data: Forecasting lake levels. Select the best number of lags.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.ARTest8
- object AR_1
The
AR_1
companion object provides factory methods for theAR_1
class. - object AR_1Test extends App
The
AR_1Test
object is used to test theAR_1
class on simulated data with uniformly distributed errors.The
AR_1Test
object is used to test theAR_1
class on simulated data with uniformly distributed errors. > runMain scalation.analytics.forecaster.AR_1Test - object AR_1Test2 extends App
The
AR_1Test2
object is used to test theAR_1
class on simulated data with normally distributed errors.The
AR_1Test2
object is used to test theAR_1
class on simulated data with normally distributed errors. > runMain scalation.analytics.forecaster.AR_1Test2 - object AR_1Test3 extends App
The
AR_1Test3
object is used to test theAR_1
class on real data: Forecasting lake levels.The
AR_1Test3
object is used to test theAR_1
class on real data: Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.AR_1Test3
- object AR_1Test4 extends App
The
AR_1Test4
object is used to test theAR_1
class on real data: Forecasting traffic flow.The
AR_1Test4
object is used to test theAR_1
class on real data: Forecasting traffic flow. > runMain scalation.analytics.forecaster.AR_1Test4 - object AR_1Test5 extends App
The
AR_1Test5
object is used to test theAR_1
class on simulated data with normally distributed errors and the response exhibits a quadratic trend.The
AR_1Test5
object is used to test theAR_1
class on simulated data with normally distributed errors and the response exhibits a quadratic trend. > runMain scalation.analytics.forecaster.AR_1Test5 - object AR_1Test6 extends App
The
AR_1Test6
object is used to test theAR_1
class on real data: Forecasting lake levels.The
AR_1Test6
object is used to test theAR_1
class on real data: Forecasting lake levels. Performs cross-validation.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.AR_1Test6
- object AR_2
The
AR_2
companion object provides factory methods for theAR_2
class. - object AR_2Test extends App
The
AR_2Test
object is used to test theAR_2
class on simulated data with uniformly distributed errors.The
AR_2Test
object is used to test theAR_2
class on simulated data with uniformly distributed errors. > runMain scalation.analytics.forecaster.AR_2Test - object AR_2Test2 extends App
The
AR_2Test2
object is used to test theAR_2
class on simulated data with normally distributed errors.The
AR_2Test2
object is used to test theAR_2
class on simulated data with normally distributed errors. > runMain scalation.analytics.forecaster.AR_2Test2 - object AR_2Test3 extends App
The
AR_2Test3
object is used to test theAR_2
class on real data: Forecasting lake levels.The
AR_2Test3
object is used to test theAR_2
class on real data: Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.AR_2Test3
- object AR_2Test4 extends App
The
AR_2Test4
object is used to test theAR_2
class on real data: Forecasting traffic flow.The
AR_2Test4
object is used to test theAR_2
class on real data: Forecasting traffic flow. > runMain scalation.analytics.forecaster.AR_2Test4 - object AR_2Test5 extends App
The
AR_2Test5
object is used to test theAR_2
class on simulated data with normally distributed errors and the response exhibits a quadratic trend.The
AR_2Test5
object is used to test theAR_2
class on simulated data with normally distributed errors and the response exhibits a quadratic trend. > runMain scalation.analytics.forecaster.AR_2Test5 - object AR_2Test6 extends App
The
AR_2Test6
object is used to test theAR_2
class on real data: Forecasting lake levels.The
AR_2Test6
object is used to test theAR_2
class on real data: Forecasting lake levels. Performs cross-validation.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.AR_2Test6
- object DiffTest extends App
The
DiffTest
is used to test the 'diff' and 'diffinv' differencing functions in theforecaster
package object using 'square (k)'.The
DiffTest
is used to test the 'diff' and 'diffinv' differencing functions in theforecaster
package object using 'square (k)'. > runMain scalation.analytics.forecaster.DiffTest - object DiffTest2 extends App
The
DiffTest2
is used to test the 'diff' and 'diffinv' differencing functions in theforecaster
package object using Fibonacci Numbers 'fib(k)'.The
DiffTest2
is used to test the 'diff' and 'diffinv' differencing functions in theforecaster
package object using Fibonacci Numbers 'fib(k)'. > runMain scalation.analytics.forecaster.DiffTest2 - object DiffTest3 extends App
The
DiffTest3
is used to test the 'sdiff' and 'sdiffinv' seasonal differencing functions in the 'forecaster' package object using 'square (k)'.The
DiffTest3
is used to test the 'sdiff' and 'sdiffinv' seasonal differencing functions in the 'forecaster' package object using 'square (k)'. > runMain scalation.analytics.forecaster.DiffTest3 - object ELM_3L1_4TS extends ModelFactory
The
ELM_3L1_4TS
companion object provides factory functions and functions for creating functional forms. - object ELM_3L1_4TSTest extends App
The
ELM_3L1_4TSTest
object is used to test theELM_3L1_4TS
class.The
ELM_3L1_4TSTest
object is used to test theELM_3L1_4TS
class. > runMain scalation.analytics.forecaster.ELM_3L1_4TSTest - object ELM_3L1_4TSTest2 extends App
The
ELM_3L1_4TSTest2
object is used to test theELM_3L1_4TS
class.The
ELM_3L1_4TSTest2
object is used to test theELM_3L1_4TS
class. The 'x' matrix in one dimensional. > runMain scalation.analytics.forecaster.ELM_3L1_4TSTest2 - object ELM_3L1_4TSTest3 extends App
The
ELM_3L1_4TSTest3
object is used to test theELM_3L1_4TS
class.The
ELM_3L1_4TSTest3
object is used to test theELM_3L1_4TS
class. The 'x' matrix in two dimensional. > runMain scalation.analytics.forecaster.ELM_3L1_4TSTest3 - object ELM_3L1_4TSTest4 extends App
The
ELM_3L1_4TSTest4
object tests theELM_3L1_4TS
class using the AutoMPG dataset.The
ELM_3L1_4TSTest4
object tests theELM_3L1_4TS
class using the AutoMPG dataset. It illustrates using theRelation
class for reading the data from a .csv file "auto-mpg.csv". Assumes no missing values. It also combines feature selection with cross-validation and plots R2, R2 Bar and R^2 cv vs. the instance index. > runMain scalation.analytics.forecaster.ELM_3L1_4TSTest4 - object ELM_3L1_4TSTest5 extends App
The
ELM_3L1_4TSTest5
object testsELM_3L1_4TS
class using the following regression equation.The
ELM_3L1_4TSTest5
object testsELM_3L1_4TS
class using the following regression equation.y = b dot x = b_0 + b_1*x1 + b_2*x_2.
> runMain scalation.analytics.forecaster.ELM_3L1_4TSTest5
- object ExampleEcon extends App
The
ExampleEcon
object tests various prediction and forecasting techniques on daily economic/finance time-series data.The
ExampleEcon
object tests various prediction and forecasting techniques on daily economic/finance time-series data. > runMain scalation.analytics.forecaster.ExampleEcon - object ExampleEcon2 extends App
The
ExampleEcon2
object tests various prediction and forecasting techniques on daily economic/finance time-series data.The
ExampleEcon2
object tests various prediction and forecasting techniques on daily economic/finance time-series data. > runMain scalation.analytics.forecaster.ExampleEcon2 - object ExampleEcon2_SARIMA extends App
The
ExampleEcon2_SARIMA
object tests various prediction and forecasting techniques on daily economic/finance time-series data.The
ExampleEcon2_SARIMA
object tests various prediction and forecasting techniques on daily economic/finance time-series data. > runMain scalation.analytics.forecaster.ExampleEcon2_SARIMA - object ExampleEcon3 extends App
The
ExampleEcon3
object tests various prediction and forecasting techniques on daily economic/finance time-series data.The
ExampleEcon3
object tests various prediction and forecasting techniques on daily economic/finance time-series data. > runMain scalation.analytics.forecaster.ExampleEcon3 - object ExampleEcon4 extends App
The
ExampleEcon4
object tests various prediction and forecasting techniques on daily economic/finance time-series data.The
ExampleEcon4
object tests various prediction and forecasting techniques on daily economic/finance time-series data. > runMain scalation.analytics.forecaster.ExampleEcon4 - object ExpSmoothing
The
ExpSmoothing
companion object provides factory methods for theExpSmoothing
class. - object ExpSmoothingTest extends App
The
ExpSmoothingTest
object is used to test theExpSmoothing
class.The
ExpSmoothingTest
object is used to test theExpSmoothing
class. > runMain scalation.analytics.forecaster.ExpSmoothingTest - object ForecasterVec
The
ForecasterVec
companion object provides functions useful for forecasting models.The
ForecasterVec
companion object provides functions useful for forecasting models. It also contains a sample dataset. - object ForecasterVecTest extends App
The
ForecasterVecTest
object tests theForecasterVec
companion object.The
ForecasterVecTest
object tests theForecasterVec
companion object. > runMain scalation.analytics.forecaster.ForecasterVecTest - object ForecasterVecTest2 extends App
The
ForecasterVecTest2
object tests theForecasterVec
companion object and models/classes that extendForecasterVec
.The
ForecasterVecTest2
object tests theForecasterVec
companion object and models/classes that extendForecasterVec
. > runMain scalation.analytics.forecaster.ForecasterVecTest2 - object KPSS_Stationarity
The companion object for
KPSS
class, containing critical value coefficients needed in KPSS tests for Time Series Stationarity around a deterministic trend. - object KPSS_StationarityTest extends App
The
KPSS_StationarityTest
object is used to test theKPSS_Stationarity
class.The
KPSS_StationarityTest
object is used to test theKPSS_Stationarity
class. > runMain scalation.analytics.forecaster.KPSS_StationarityTest - object KalmanFilterTest extends App
The
KalmanFilterTest
object is used to test theKalmanFilter
class.The
KalmanFilterTest
object is used to test theKalmanFilter
class.- See also
en.wikipedia.org/wiki/Kalman_filter > runMain scalation.analytics.forecaster.KalmanFilterTest
- object MA
The
MA
companion object provides factory methods for theMA
class. - object MATest extends App
The
MATest
object is used to test theMA
class.The
MATest
object is used to test theMA
class. > runMain scalation.analytics.forecaster.MATest - object MATest2 extends App
The
MATest2
object is used to test theMA
class.The
MATest2
object is used to test theMA
class. > runMain scalation.analytics.forecaster.MATest2 - object MATest3 extends App
The
MATest3
object is used to test theMA
class.The
MATest3
object is used to test theMA
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.MATest3
- object MATest4 extends App
The
MATest4
object is used to test theMA
class.The
MATest4
object is used to test theMA
class. Forecasting traffic flow. > runMain scalation.analytics.forecaster.MATest4 - object MATest5 extends App
The
MATest5
object is used to test theMA
class.The
MATest5
object is used to test theMA
class. > runMain scalation.analytics.forecaster.MATest5 - object MATest6 extends App
The
MATest6
object is used to test theMA
class on real data: Forecasting lake levels.The
MATest6
object is used to test theMA
class on real data: Forecasting lake levels. Select the best number of lags.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.MATest6
- object MA_1
The
MA_1
companion object provides factory methods for theMA_1
class. - object MA_1Test extends App
The
MA_1Test
object is used to test theMA_1
class.The
MA_1Test
object is used to test theMA_1
class.y_t = c + θ e_{t-1} + e_t
> runMain scalation.analytics.forecaster.MA_1Test
- object MA_1Test2 extends App
The
MA_1Test2
object is used to test theMA_1
class on simulated data with normally distributed errors.The
MA_1Test2
object is used to test theMA_1
class on simulated data with normally distributed errors. > runMain scalation.analytics.forecaster.MA_1Test2 - object MA_1Test3 extends App
The
MA_1Test3
object is used to test theMA_1
class on real data: Forecasting lake levels.The
MA_1Test3
object is used to test theMA_1
class on real data: Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.MA_1Test3
- object MovingAverage
The
MovingAverage
companion object provides factory methods for theMovingAverage
class. - object MovingAverageD
The
MovingAverageD
companion object provides factory methods for theMovingAverageD
class. - object MovingAverageDTest extends App
The
MovingAverageDTest
object is used to test theMovingAverageD
class.The
MovingAverageDTest
object is used to test theMovingAverageD
class. > runMain scalation.analytics.forecaster.MovingAverageDTest - object MovingAverageDTest2 extends App
The
MovingAverageDTest2
object is used to test theMovingAverageD
class.The
MovingAverageDTest2
object is used to test theMovingAverageD
class. > runMain scalation.analytics.forecaster.MovingAverageDTest2 - object MovingAverageDTest3 extends App
The
MovingAverageDTest3
object is used to test theMovingAverageD
class.The
MovingAverageDTest3
object is used to test theMovingAverageD
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.MovingAverageDTest3
- object MovingAverageDTest4 extends App
The
MovingAverageDTest4
object is used to test theMovingAverageD
class.The
MovingAverageDTest4
object is used to test theMovingAverageD
class. > runMain scalation.analytics.forecaster.MovingAverageDTest4 - object MovingAverageDTest5 extends App
The
MovingAverageDTest5
object is used to test theMovingAverageD
class.The
MovingAverageDTest5
object is used to test theMovingAverageD
class. > runMain scalation.analytics.forecaster.MovingAverageDTest5 - object MovingAverageTest extends App
The
MovingAverageTest
object is used to test theMovingAverage
class.The
MovingAverageTest
object is used to test theMovingAverage
class. > runMain scalation.analytics.forecaster.MovingAverageTest - object MovingAverageTest2 extends App
The
MovingAverageTest2
object is used to test theMovingAverage
class.The
MovingAverageTest2
object is used to test theMovingAverage
class. > runMain scalation.analytics.forecaster.MovingAverageTest2 - object MovingAverageTest3 extends App
The
MovingAverageTest3
object is used to test theMovingAverage
class.The
MovingAverageTest3
object is used to test theMovingAverage
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.MovingAverageTest3
- object MovingAverageTest4 extends App
The
MovingAverageTest4
object is used to test theMovingAverage
class.The
MovingAverageTest4
object is used to test theMovingAverage
class. > runMain scalation.analytics.forecaster.MovingAverageTest4 - object MovingAverageTest5 extends App
The
MovingAverageTest5
object is used to test theMovingAverage
class.The
MovingAverageTest5
object is used to test theMovingAverage
class. > runMain scalation.analytics.forecaster.MovingAverageTest5 - object NeuralNet_3L1_4TS extends ModelFactory
The
NeuralNet_3L1_4TS
companion object provides factory functions and functions for creating functional forms. - object NeuralNet_3L1_4TSTest extends App
The
NeuralNet_3L1_4TSTest
object is used to test theNeuralNet_3L1_4TS
class.The
NeuralNet_3L1_4TSTest
object is used to test theNeuralNet_3L1_4TS
class. > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSTest - object NeuralNet_3L1_4TSTest2 extends App
The
NeuralNet_3L1_4TSTest2
object is used to test theNeuralNet_3L1_4TS
class.The
NeuralNet_3L1_4TSTest2
object is used to test theNeuralNet_3L1_4TS
class. The 'x' matrix in one dimensional. > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSTest2 - object NeuralNet_3L1_4TSTest3 extends App
The
NeuralNet_3L1_4TSTest3
object is used to test theNeuralNet_3L1_4TS
class.The
NeuralNet_3L1_4TSTest3
object is used to test theNeuralNet_3L1_4TS
class. The 'x' matrix in two dimensional. > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSTest3 - object NeuralNet_3L1_4TSTest4 extends App
The
NeuralNet_3L1_4TSTest4
object tests theNeuralNet_3L1_4TS
class using the AutoMPG dataset.The
NeuralNet_3L1_4TSTest4
object tests theNeuralNet_3L1_4TS
class using the AutoMPG dataset. It illustrates using theRelation
class for reading the data from a .csv file "auto-mpg.csv". Assumes no missing values. It also combines feature selection with cross-validation and plots R2, R2 Bar and R^2 cv vs. the instance index. > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSTest4 - object NeuralNet_3L1_4TSTest5 extends App
The
NeuralNet_3L1_4TSTest5
object testsNeuralNet_3L1_4TS
class using the following regression equation.The
NeuralNet_3L1_4TSTest5
object testsNeuralNet_3L1_4TS
class using the following regression equation.y = b dot x = b_0 + b_1*x1 + b_2*x_2.
> runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSTest5
- object NeuralNet_3L1_4TSy extends ModelFactory
The
NeuralNet_3L1_4TSy
companion object provides factory functions and functions for creating functional forms. - object NeuralNet_3L1_4TSyTest extends App
The
NeuralNet_3L1_4TSyTest
object is used to test theNeuralNet_3L1_4TSy
class.The
NeuralNet_3L1_4TSyTest
object is used to test theNeuralNet_3L1_4TSy
class. > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSTest - object NeuralNet_3L1_4TSyTest2 extends App
The
NeuralNet_3L1_4TSyTest2
object is used to test theNeuralNet_3L1_4TSy
class.The
NeuralNet_3L1_4TSyTest2
object is used to test theNeuralNet_3L1_4TSy
class. The order 'p' hyper-parameter should be re-assigned (try 1, 2, 3, ...). > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSyTest2 - object NeuralNet_3L1_4TSyTest3 extends App
The
NeuralNet_3L1_4TSyTest3
object is used to test theNeuralNet_3L1_4TSy
class.The
NeuralNet_3L1_4TSyTest3
object is used to test theNeuralNet_3L1_4TSy
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.NeuralNet_3L1_4TSyTest3
- object NullModel
The
NullModel
companion object provides factory methods for theNullModel
class. - object NullModelTest extends App
The
NullModelTest
object is used to test theNullModel
class.The
NullModelTest
object is used to test theNullModel
class. > runMain scalation.analytics.forecaster.NullModelTest - object NullModelTest2 extends App
The
NullModelTest2
object is used to test theNullModel
class.The
NullModelTest2
object is used to test theNullModel
class. The order 'p' hyper-parameter is re-assigned. > runMain scalation.analytics.forecaster.NullModelTest2 - object NullModelTest3 extends App
The
NullModelTest3
object is used to test theNullModel
class.The
NullModelTest3
object is used to test theNullModel
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.NullModelTest3
- object NullModelTest4 extends App
The
NullModelTest4
object is used to test theNullModel
class.The
NullModelTest4
object is used to test theNullModel
class. > runMain scalation.analytics.forecaster.NullModelTest4 - object NullModelTest5 extends App
The
NullModelTest5
object is used to test theNullModel
class.The
NullModelTest5
object is used to test theNullModel
class. > runMain scalation.analytics.forecaster.NullModelTest5 - object QuadRegression4TS extends ModelFactory
The
QuadRegression4TS
companion object provides factory functions and functions for creating functional forms. - object QuadRegression4TSTest extends App
The
QuadRegression4TSTest
object is used to test theQuadRegression4TS
class.The
QuadRegression4TSTest
object is used to test theQuadRegression4TS
class. > runMain scalation.analytics.forecaster.QuadRegression4TSTest - object QuadRegression4TSTest2 extends App
The
QuadRegression4TSTest2
object is used to test theQuadRegression4TS
class.The
QuadRegression4TSTest2
object is used to test theQuadRegression4TS
class. The 'x' matrix in one dimensional. > runMain scalation.analytics.forecaster.QuadRegression4TSTest2 - object QuadRegression4TSTest3 extends App
The
QuadRegression4TSTest3
object is used to test theQuadRegression4TS
class.The
QuadRegression4TSTest3
object is used to test theQuadRegression4TS
class. The 'x' matrix in two dimensional. > runMain scalation.analytics.forecaster.QuadRegression4TSTest3 - object QuadRegression4TSTest4 extends App
The
QuadRegression4TSTest4
object tests theQuadRegression4TS
class using the AutoMPG dataset.The
QuadRegression4TSTest4
object tests theQuadRegression4TS
class using the AutoMPG dataset. It illustrates using theRelation
class for reading the data from a .csv file "auto-mpg.csv". Assumes no missing values. It also combines feature selection with cross-validation and plots R2, R2 Bar and R^2 cv vs. the instance index. > runMain scalation.analytics.forecaster.QuadRegression4TSTest4 - object QuadRegression4TSTest5 extends App
The
QuadRegression4TSTest5
object testsQuadRegression4TS
class using the following regression equation.The
QuadRegression4TSTest5
object testsQuadRegression4TS
class using the following regression equation.y = b dot x = b_0 + b_1*x1 + b_2*x_2.
> runMain scalation.analytics.forecaster.QuadRegression4TSTest5
- object QuadRegression4TSy extends ModelFactory
The
QuadRegression4TSy
companion object provides factory functions and functions for creating functional forms. - object QuadRegression4TSyTest extends App
The
QuadRegression4TSyTest
object is used to test theQuadRegression4TSy
class.The
QuadRegression4TSyTest
object is used to test theQuadRegression4TSy
class. > runMain scalation.analytics.forecaster.QuadRegression4TSyTest - object QuadRegression4TSyTest2 extends App
The
QuadRegression4TSyTest2
object is used to test theQuadRegression4TSy
class.The
QuadRegression4TSyTest2
object is used to test theQuadRegression4TSy
class. The order 'p' hyper-parameter should be re-assigned (try 1, 2, 3, ...). > runMain scalation.analytics.forecaster.QuadRegression4TSyTest2 - object QuadRegression4TSyTest3 extends App
The
QuadRegression4TSyTest3
object is used to test theQuadRegression4TSy
class.The
QuadRegression4TSyTest3
object is used to test theQuadRegression4TSy
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.QuadRegression4TSyTest3
- object QuadSpline
The
QuadSpline
companion object provides factory methods for theQuadSpline
class. - object QuadSplineTest extends App
The
QuadSplineTest
object is used to test theQuadSpline
class.The
QuadSplineTest
object is used to test theQuadSpline
class. Forecasting Fibonacci numbers. > runMain scalation.analytics.forecaster.QuadSplineTest - object QuadSplineTest2 extends App
The
QuadSplineTest2
object is used to test theQuadSpline
class.The
QuadSplineTest2
object is used to test theQuadSpline
class. > runMain scalation.analytics.forecaster.QuadSplineTest2 - object QuadSplineTest3 extends App
The
QuadSplineTest3
object is used to test theQuadSpline
class.The
QuadSplineTest3
object is used to test theQuadSpline
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.QuadSplineTest3
- object QuadXRegression4TS extends ModelFactory
The
QuadXRegression4TS
companion object provides factory functions and functions for creating functional forms. - object QuadXRegression4TSTest extends App
The
QuadXRegression4TSTest
object is used to test theQuadXRegression4TS
class.The
QuadXRegression4TSTest
object is used to test theQuadXRegression4TS
class. > runMain scalation.analytics.forecaster.QuadXRegression4TSTest - object QuadXRegression4TSTest2 extends App
The
QuadXRegression4TSTest2
object is used to test theQuadXRegression4TS
class.The
QuadXRegression4TSTest2
object is used to test theQuadXRegression4TS
class. The 'x' matrix in one dimensional. > runMain scalation.analytics.forecaster.QuadXRegression4TSTest2 - object QuadXRegression4TSTest3 extends App
The
QuadXRegression4TSTest3
object is used to test theQuadXRegression4TS
class.The
QuadXRegression4TSTest3
object is used to test theQuadXRegression4TS
class. The 'x' matrix in two dimensional. > runMain scalation.analytics.forecaster.QuadXRegression4TSTest3 - object QuadXRegression4TSTest4 extends App
The
QuadXRegression4TSTest4
object tests theQuadXRegression4TS
class using the AutoMPG dataset.The
QuadXRegression4TSTest4
object tests theQuadXRegression4TS
class using the AutoMPG dataset. It illustrates using theRelation
class for reading the data from a .csv file "auto-mpg.csv". Assumes no missing values. It also combines feature selection with cross-validation and plots R2, R2 Bar and R^2 cv vs. the instance index. > runMain scalation.analytics.forecaster.QuadXRegression4TSTest4 - object QuadXRegression4TSTest5 extends App
The
QuadXRegression4TSTest5
object testsQuadXRegression4TS
class using the following regression equation.The
QuadXRegression4TSTest5
object testsQuadXRegression4TS
class using the following regression equation.y = b dot x = b_0 + b_1*x1 + b_2*x_2.
> runMain scalation.analytics.forecaster.QuadXRegression4TSTest5
- object QuadXRegression4TSy extends ModelFactory
The
QuadXRegression4TSy
companion object provides factory functions and functions for creating functional forms. - object QuadXRegression4TSyTest extends App
The
QuadXRegression4TSyTest
object is used to test theQuadXRegression4TSy
class.The
QuadXRegression4TSyTest
object is used to test theQuadXRegression4TSy
class. > runMain scalation.analytics.forecaster.QuadXRegression4TSyTest - object QuadXRegression4TSyTest2 extends App
The
QuadXRegression4TSyTest2
object is used to test theQuadXRegression4TSy
class.The
QuadXRegression4TSyTest2
object is used to test theQuadXRegression4TSy
class. The order 'p' hyper-parameter should be re-assigned (try 1, 2, 3, ...). > runMain scalation.analytics.forecaster.QuadXRegression4TSyTest2 - object QuadXRegression4TSyTest3 extends App
The
QuadXRegression4TSyTest3
object is used to test theQuadXRegression4TSy
class.The
QuadXRegression4TSyTest3
object is used to test theQuadXRegression4TSy
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.QuadXRegression4TSyTest3
- object RandomWalk
The
RandomWalk
companion object provides factory methods for theRandomWalk
class. - object RandomWalkTest extends App
The
RandomWalkTest
object is used to test theRandomWalk
class.The
RandomWalkTest
object is used to test theRandomWalk
class. > runMain scalation.analytics.forecaster.RandomWalkTest - object RandomWalkTest2 extends App
The
RandomWalkTest2
object is used to test theRandomWalk
class.The
RandomWalkTest2
object is used to test theRandomWalk
class. The order hyper-parameter 'p' is re-assigned. > runMain scalation.analytics.forecaster.RandomWalkTest2 - object RandomWalkTest3 extends App
The
RandomWalkTest3
object is used to test theRandomWalk
class.The
RandomWalkTest3
object is used to test theRandomWalk
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.RandomWalkTest3
- object RandomWalkTest4 extends App
The
RandomWalkTest4
object is used to test theRandomWalk
class.The
RandomWalkTest4
object is used to test theRandomWalk
class. Forecasting travel times. > runMain scalation.analytics.forecaster.RandomWalkTest4 - object RandomWalkTest5 extends App
The
RandomWalkTest5
object is used to test theRandomWalk
class.The
RandomWalkTest5
object is used to test theRandomWalk
class. Having a quadratic trend. > runMain scalation.analytics.forecaster.RandomWalkTest5 - object RandomWalkTest6 extends App
The
RandomWalkTest6
object is used to test theRandomWalk
class.The
RandomWalkTest6
object is used to test theRandomWalk
class. Using a Random Walk model on white noise. > runMain scalation.analytics.forecaster.RandomWalkTest6 - object Regression4TS extends ModelFactory
The
Regression4TS
companion object provides factory functions and functions for creating functional forms. - object Regression4TSTest extends App
The
Regression4TSTest
object is used to test theRegression4TS
class.The
Regression4TSTest
object is used to test theRegression4TS
class. > runMain scalation.analytics.forecaster.Regression4TSTest - object Regression4TSTest2 extends App
The
Regression4TSTest2
object is used to test theRegression4TS
class.The
Regression4TSTest2
object is used to test theRegression4TS
class. The 'x' matrix in one dimensional. > runMain scalation.analytics.forecaster.Regression4TSTest2 - object Regression4TSTest3 extends App
The
Regression4TSTest3
object is used to test theRegression4TS
class.The
Regression4TSTest3
object is used to test theRegression4TS
class. The 'x' matrix in two dimensional. > runMain scalation.analytics.forecaster.Regression4TSTest3 - object Regression4TSTest4 extends App
The
Regression4TSTest4
object tests theRegression4TS
class using the AutoMPG dataset.The
Regression4TSTest4
object tests theRegression4TS
class using the AutoMPG dataset. It illustrates using theRelation
class for reading the data from a .csv file "auto-mpg.csv". Assumes no missing values. It also combines feature selection with cross-validation and plots R2, R2 Bar and R^2 cv vs. the instance index. > runMain scalation.analytics.forecaster.Regression4TSTest4 - object Regression4TSTest5 extends App
The
Regression4TSTest5
object testsRegression4TS
class using the following regression equation.The
Regression4TSTest5
object testsRegression4TS
class using the following regression equation.y = b dot x = b_0 + b_1*x1 + b_2*x_2.
> runMain scalation.analytics.forecaster.Regression4TSTest5
- object Regression4TSy extends ModelFactory
The
Regression4TSy
companion object provides factory functions and functions for creating functional forms. - object Regression4TSyTest extends App
The
Regression4TSyTest
object is used to test theRegression4TSy
class.The
Regression4TSyTest
object is used to test theRegression4TSy
class. > runMain scalation.analytics.forecaster.Regression4TSyTest - object Regression4TSyTest2 extends App
The
Regression4TSyTest2
object is used to test theRegression4TSy
class.The
Regression4TSyTest2
object is used to test theRegression4TSy
class. The order 'p' hyper-parameter should be re-assigned (try 1, 2, 3, ...). > runMain scalation.analytics.forecaster.Regression4TSyTest2 - object Regression4TSyTest3 extends App
The
Regression4TSyTest3
object is used to test theRegression4TSy
class.The
Regression4TSyTest3
object is used to test theRegression4TSy
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.Regression4TSyTest3
- object RollingValidation
The
RollingValidation
object provides 'k'-fold rolling validations, e.g., for 'm = 1200' and 'k = 10', 'kt = 20':The
RollingValidation
object provides 'k'-fold rolling validations, e.g., for 'm = 1200' and 'k = 10', 'kt = 20':1: tr(ain) 0 until 800, te(st) 800 until 840 2: tr(ain) 40 until 840, te(st) 840 until 880 3: tr(ain) 80 until 880, te(st) 880 until 920 4: tr(ain) 120 until 920, te(st) 920 until 960 5: tr(ain) 160 until 960, te(st) 960 until 1000 6: tr(ain) 200 until 1000, te(st) 1000 until 1040 7: tr(ain) 240 until 1040, te(st) 1040 until 1080 8: tr(ain) 280 until 1080, te(st) 1080 until 1120 9: tr(ain) 320 until 1120, te(st) 1120 until 1160 10: tr(ain) 360 until 1160, te(st) 1160 until 1200
In rolling validation for this case, each training dataset has 800 instances, while each testing dataset has 40. Re-training occurs before every 'kt = 20' forecasts are made (2 re-trainings per testing dataset for this case).
- object RollingValidationTest extends App
The
RollingValidationTest
object is used to test the 'crossValidate' method in theRollingValidation
object.The
RollingValidationTest
object is used to test the 'crossValidate' method in theRollingValidation
object. > runMain scalation.analytics.forecaster.RollingValidationTest - object RollingValidationTest2 extends App
The
RollingValidationTest2
object is used to test the 'crossValidate2' method in theRollingValidation
object.The
RollingValidationTest2
object is used to test the 'crossValidate2' method in theRollingValidation
object. > runMain scalation.analytics.forecaster.RollingValidationTest2 - object SARIMA
Companion object for class
SARIMA
.Companion object for class
SARIMA
. Includes features related to differencing and automated order selection.- See also
www.jstatsoft.org/article/view/v027i03/v27i03.pdf
- object SARIMATest extends App
The
SARIMATest
object is used to test theSARIMA
class.The
SARIMATest
object is used to test theSARIMA
class. > runMain scalation.analytics.forecaster.SARIMATest - object SARIMATest2 extends App
The
SARIMATest2
object is used to test theSARIMA
class.The
SARIMATest2
object is used to test theSARIMA
class. > runMain scalation.analytics.forecaster.SARIMATest2 - object SARIMATest3 extends App
The
SARIMATest3
object is used to test theSARIMA
class.The
SARIMATest3
object is used to test theSARIMA
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.SARIMATest3
- object SARIMATest4 extends App
The
SARIMATest4
object is used to test theSARIMA
class.The
SARIMATest4
object is used to test theSARIMA
class. > runMain scalation.analytics.forecaster.SARIMATest4 - object SARIMATest5 extends App
The
SARIMATest5
object is used to test theSARIMA
class.The
SARIMATest5
object is used to test theSARIMA
class. > runMain scalation.analytics.forecaster.SARIMATest5 - object SARIMATest6 extends App
The
SARIMATest6
object is used to test theSARIMA
class on real data: Forecasting lake levels.The
SARIMATest6
object is used to test theSARIMA
class on real data: Forecasting lake levels. Select the best number of lags.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.SARIMATest6
- object SARIMAX
Companion object for class
SARIMAX
.Companion object for class
SARIMAX
. Includes features related to differencing and automated order selection.- See also
www.jstatsoft.org/article/view/v027i03/v27i03.pdf
- object SARIMAXTest extends App
The
SARIMAXTest
object is used to test theSARIMAX
class.The
SARIMAXTest
object is used to test theSARIMAX
class. > runMain scalation.analytics.forecaster.SARIMAXTest - object SARIMAXTest2 extends App
The
SARIMAXTest2
object is used to test theSARIMAX
class.The
SARIMAXTest2
object is used to test theSARIMAX
class. > runMain scalation.analytics.forecaster.SARIMAXTest2 - object SARIMAXTest3 extends App
The
SARIMAXTest3
object is used to test theSARIMAX
class.The
SARIMAXTest3
object is used to test theSARIMAX
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.SARIMAXTest3
- object SARIMAXTest4 extends App
The
SARIMAXTest4
object is used to test theSARIMAX
class.The
SARIMAXTest4
object is used to test theSARIMAX
class. > runMain scalation.analytics.forecaster.SARIMAXTest4 - object SimpleExpSmoothing
The
SimpleExpSmoothing
companion object provides factory methods for theSimpleExpSmoothing
class. - object SimpleExpSmoothingTest extends App
The
SimpleExpSmoothingTest
object is used to test theSimpleExpSmoothing
class.The
SimpleExpSmoothingTest
object is used to test theSimpleExpSmoothing
class. Test customized smoothing (call 'smooth') versus optimized smoothing (call 'train'). > runMain scalation.analytics.forecaster.SimpleExpSmoothingTest - object SimpleExpSmoothingTest2 extends App
The
SimpleExpSmoothingTest2
object is used to test theSimpleExpSmoothing
class.The
SimpleExpSmoothingTest2
object is used to test theSimpleExpSmoothing
class. Test rolling validation. > runMain scalation.analytics.forecaster.SimpleExpSmoothingTest2 - object SimpleExpSmoothingTest3 extends App
The
SimpleExpSmoothingTest3
object is used to test theSimpleExpSmoothing
class.The
SimpleExpSmoothingTest3
object is used to test theSimpleExpSmoothing
class. Forecasting lake levels.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.SimpleExpSmoothingTest3
- object SimpleExpSmoothingTest4 extends App
The
SimpleExpSmoothingTest4
object is used to test theSimpleExpSmoothing
class.The
SimpleExpSmoothingTest4
object is used to test theSimpleExpSmoothing
class. Forecasting lake levels for several values of the smoothing parameter α.- See also
cran.r-project.org/web/packages/fpp/fpp.pdf > runMain scalation.analytics.forecaster.SimpleExpSmoothingTest4
- object SimpleRollingValidation
The
SimpleRollingValidation
object provides '1'-fold rolling validations, e.g., for 'm = 1200' and 'k = 1', 'kt = 5':The
SimpleRollingValidation
object provides '1'-fold rolling validations, e.g., for 'm = 1200' and 'k = 1', 'kt = 5':1: tr(ain) 0 until 600, te(st) 600 until 1200
In rolling validation for this case, each retraining dataset has 600 instances, while the testing dataset has 600. Re-training occurs before every 'kt = 2' forecasts are made.
- object SimpleRollingValidationTest extends App
The
SimpleRollingValidationTest
object is used to test the 'crossValidate' method in theSimpleRollingValidation
object.The
SimpleRollingValidationTest
object is used to test the 'crossValidate' method in theSimpleRollingValidation
object. > runMain scalation.analytics.forecaster.SimpleRollingValidationTest - object SimpleRollingValidationTest2 extends App
The
SimpleRollingValidationTest2
object is used to test the 'crossValidate2' method in theSimpleRollingValidation
object.The
SimpleRollingValidationTest2
object is used to test the 'crossValidate2' method in theSimpleRollingValidation
object. > runMain scalation.analytics.forecaster.SimpleRollingValidationTest2