DynamicParameterEstimation (FsODE)

FsODE

Documentation for 0.0.2

DynamicParameterEstimation Type

Namespace: Altaxo.Calc.Regression
Assembly: AltaxoCore.Redist.dll
Base Type: obj

Algorithms to estimate the parameters of a dynamic difference equation.

Constructors

Constructor	Description
`DynamicParameterEstimation(numX, numY, backgroundOrder)` Full Usage: `DynamicParameterEstimation(numX, numY, backgroundOrder)` Parameters: numX : `int` - Number of history x samples to be taken into account for the parameter estimation (samples x[i], x[i-1]..x[i+1-numX]). numY : `int` - Number of history y samples to be taken into account for the parameter estimation (samples y[i-1], y[i-2]..x[i-numY]. backgroundOrder : `int` - Order of the background fit, i.e. components 1, i, i² are fitted additionally to x and y. A order of 0 fits a constant background, 1 a linear depencence, and so on. Set this parameter to -1 if you don't need a background fit.	Constructur for the dynamic parameter estimation. numX : `int` Number of history x samples to be taken into account for the parameter estimation (samples x[i], x[i-1]..x[i+1-numX]). numY : `int` Number of history y samples to be taken into account for the parameter estimation (samples y[i-1], y[i-2]..x[i-numY]. backgroundOrder : `int` Order of the background fit, i.e. components 1, i, i² are fitted additionally to x and y. A order of 0 fits a constant background, 1 a linear depencence, and so on. Set this parameter to -1 if you don't need a background fit.
`DynamicParameterEstimation(numX, numY, backgroundOrder, solver)` Full Usage: `DynamicParameterEstimation(numX, numY, backgroundOrder, solver)` Parameters: numX : `int` - Number of history x samples to be taken into account for the parameter estimation (samples x[i], x[i-1]..x[i+1-numX]). numY : `int` - Number of history y samples to be taken into account for the parameter estimation (samples y[i-1], y[i-2]..x[i-numY]. backgroundOrder : `int` - Order of the background fit, i.e. components 1, i, i² are fitted additionally to x and y. A order of 0 fits a constant background, 1 a linear depencence, and so on. Set this parameter to -1 if you don't need a background fit. solver : `IDynamicParameterEstimationSolver` - The solver to use with dynamic parameter estimation. Use the static getter methods DynamicParameterEstimation.SVDSolver or DynamicParameterEstimation.LUSolver to get a solver.	Constructur for the dynamic parameter estimation. numX : `int` Number of history x samples to be taken into account for the parameter estimation (samples x[i], x[i-1]..x[i+1-numX]). numY : `int` Number of history y samples to be taken into account for the parameter estimation (samples y[i-1], y[i-2]..x[i-numY]. backgroundOrder : `int` Order of the background fit, i.e. components 1, i, i² are fitted additionally to x and y. A order of 0 fits a constant background, 1 a linear depencence, and so on. Set this parameter to -1 if you don't need a background fit. solver : `IDynamicParameterEstimationSolver` The solver to use with dynamic parameter estimation. Use the static getter methods DynamicParameterEstimation.SVDSolver or DynamicParameterEstimation.LUSolver to get a solver.
`DynamicParameterEstimation(x, y, numX, numY, backgroundOrder)` Full Usage: `DynamicParameterEstimation(x, y, numX, numY, backgroundOrder)` Parameters: x : `IReadOnlyList<float>` - Vector of x values ("input values"). This parameter can be null (in this case only y values are taken into account). y : `IReadOnlyList<float>` - Vector of y values ("response values"). numX : `int` - Number of history x samples to be taken into account for the parameter estimation (samples x[i], x[i-1]..x[i+1-numX]). numY : `int` - Number of history y samples to be taken into account for the parameter estimation (samples y[i-1], y[i-2]..x[i-numY]. backgroundOrder : `int` - Order of the background fit, i.e. components 1, i, i² are fitted additionally to x and y. A order of 0 fits a constant background, 1 a linear depencence, and so on. Set this parameter to -1 if you don't need a background fit.	Calculates the dynamic parameter estimation in the constructor. x : `IReadOnlyList<float>` Vector of x values ("input values"). This parameter can be null (in this case only y values are taken into account). y : `IReadOnlyList<float>` Vector of y values ("response values"). numX : `int` Number of history x samples to be taken into account for the parameter estimation (samples x[i], x[i-1]..x[i+1-numX]). numY : `int` Number of history y samples to be taken into account for the parameter estimation (samples y[i-1], y[i-2]..x[i-numY]. backgroundOrder : `int` Order of the background fit, i.e. components 1, i, i² are fitted additionally to x and y. A order of 0 fits a constant background, 1 a linear depencence, and so on. Set this parameter to -1 if you don't need a background fit.

Instance members

Instance member	Description
`this.CalculateCrossPredictionError` Full Usage: `this.CalculateCrossPredictionError` Parameters: x : `IReadOnlyList<float>` - Vector of x data. y : `IReadOnlyList<float>` - Vector of y data. Returns: `float` The mean error between y prediction values and actual y values. Modifiers: abstract	With the already evalulated parameters (!), calculates the mean error for another piece of data. Please not that both vectors must have a length of at least _startingPoint+1, since the first _startingPoint samples are used for the history. x : `IReadOnlyList<float>` Vector of x data. y : `IReadOnlyList<float>` Vector of y data. Returns: `float` The mean error between y prediction values and actual y values.
`this.CalculateCrossPredictionError` Full Usage: `this.CalculateCrossPredictionError` Parameters: x : `IReadOnlyList<float>` - Vector of x data. y : `IReadOnlyList<float>` - Vector of y data. predictedOutput : `IVector<float>` - Vector to store the predicted y values. Can be null. Returns: `float` The mean error between y prediction values and actual y values. Modifiers: abstract	With the already evalulated parameters (!), calculates the mean error for another piece of data. Please not that both vectors must have a length of at least _startingPoint+1, since the first _startingPoint samples are used for the history. x : `IReadOnlyList<float>` Vector of x data. y : `IReadOnlyList<float>` Vector of y data. predictedOutput : `IVector<float>` Vector to store the predicted y values. Can be null. Returns: `float` The mean error between y prediction values and actual y values.
`this.CalculatePredictionError` Full Usage: `this.CalculatePredictionError` Returns: `float` The mean prediction error.i.e. Sqrt(Sum((y-yprediced)²)/N). Modifiers: abstract	Calculates the mean prediction error, i.e. Sqrt(Sum((y-yprediced)²)/N). Returns: `float` The mean prediction error.i.e. Sqrt(Sum((y-yprediced)²)/N).
`this.CalculatePredictionError` Full Usage: `this.CalculatePredictionError` Parameters: predictedOutput : `IVector<float>` - The resultant predicted output. If null, a temporary vector is allocated for calculation. Returns: `float` The mean prediction error.i.e. Sqrt(Sum((y-yprediced)²)/N). Modifiers: abstract	Calculates the mean prediction error, i.e. Sqrt(Sum((y-yprediced)²)). predictedOutput : `IVector<float>` The resultant predicted output. If null, a temporary vector is allocated for calculation. Returns: `float` The mean prediction error.i.e. Sqrt(Sum((y-yprediced)²)/N).
`this.CalculateSelfPredictionError` Full Usage: `this.CalculateSelfPredictionError` Returns: `float` The mean prediction error.i.e. Sqrt(Sum((y-yprediced)²)/N). Modifiers: abstract	Calculates the mean prediction error, i.e. Sqrt(Sum((y-yprediced)²)). Returns: `float` The mean prediction error.i.e. Sqrt(Sum((y-yprediced)²)/N).
`this.CalculateSelfPredictionError` Full Usage: `this.CalculateSelfPredictionError` Parameters: predictedOutput : `IVector<float>` Returns: `float` Modifiers: abstract	predictedOutput : `IVector<float>` Returns: `float`
`this.EstimateParameterByBurgsAlgorithm` Full Usage: `this.EstimateParameterByBurgsAlgorithm` Parameters: data : `IReadOnlyList<float>` m : `int` xms : `byref<float>`	data : `IReadOnlyList<float>` m : `int` xms : `byref<float>`
`this.GetFrequencyResponse` Full Usage: `this.GetFrequencyResponse` Parameters: fdt : `float` - Frequency. Must be given as f*dt, meaning the product of frequency and sample interval. Returns: `Complex` The complex frequency response at the given frequency. Modifiers: abstract	Calculates the frequency response for a given frequency. fdt : `float` Frequency. Must be given as f*dt, meaning the product of frequency and sample interval. Returns: `Complex` The complex frequency response at the given frequency.
`this.GetTransferFunction` Full Usage: `this.GetTransferFunction` Parameters: yValueBeforePulse : `float` - This is the y-value (not x!) before the pulse. If the `NumberOfY` is set to zero, this parameter is ignored, since no information about y for t<0 is neccessary. output : `IVector<float>` - Used to store the output result. Can be of arbitrary size. Modifiers: abstract	Gets the impulse response to a pulse at t=0, i.e. to x[0]==1, x[1]...x[n]==0. The background component is not taken into account. yValueBeforePulse : `float` This is the y-value (not x!) before the pulse. If the `NumberOfY` is set to zero, this parameter is ignored, since no information about y for t<0 is neccessary. output : `IVector<float>` Used to store the output result. Can be of arbitrary size.
`this.MakeEstimation` Full Usage: `this.MakeEstimation` Parameters: x : `IReadOnlyList<float>` - Vector of x values ("input values"). This parameter can be null when numX was set to 0 (in this case only y values are taken into account). y : `IReadOnlyList<float>` - Vector of y values ("response values").	Calculates the dynamic parameter estimation. x : `IReadOnlyList<float>` Vector of x values ("input values"). This parameter can be null when numX was set to 0 (in this case only y values are taken into account). y : `IReadOnlyList<float>` Vector of y values ("response values").
`this.OffsetX` Full Usage: `this.OffsetX`	"Moves" the sequence x in relation to sequence y. Normally, the y[i] is considered in dependence on x[i], x[i-1].. and so on. By setting the offset, the y[i] is considered in dependence on x[i-offset], x[x-offset-1]...
`this.Parameter` Full Usage: `this.Parameter` Returns: `float[]`	Resulting parameters of the estimation. Index 0..numX-1 are the parameters for x history. Following from numX to numX+numY-1 are the parameters for y, and at least there are the parameters for the background fit. Returns: `float[]`
`this.StartingPoint` Full Usage: `this.StartingPoint` Returns: `int`	Calculates and returns the starting point, i.e. the first index in the y array that can be used for the right side of the linear equation. The starting point increase when more x or y parameters are to evaluate, since more "history" samples are needed in this case. Returns: `int`

Static members

Static member	Description
`DynamicParameterEstimation.Extrapolate(yTraining, yPredValues, len, yOrder)` Full Usage: `DynamicParameterEstimation.Extrapolate(yTraining, yPredValues, len, yOrder)` Parameters: yTraining : `IReadOnlyList<float>` - Input vector of y values used to calculated the prediction coefficients. Input/output vector of y values to extrapolate. The fields beginning from 0 to len-1 must contain valid values used for initialization of the extrapolation. At the end of the procedure, the upper end (len .. yPredValues.Count-1 contain the extrapolated data. yPredValues : `IVector<float>` len : `int` - Number of valid input data points for extrapolation (not for the training data!). yOrder : `int` - Number of history samples used for prediction. Must be greater or equal to 1. Returns: `DynamicParameterEstimation`	Extrapolates y-values until the end of the vector by using linear prediction. yTraining : `IReadOnlyList<float>` Input vector of y values used to calculated the prediction coefficients. Input/output vector of y values to extrapolate. The fields beginning from 0 to len-1 must contain valid values used for initialization of the extrapolation. At the end of the procedure, the upper end (len .. yPredValues.Count-1 contain the extrapolated data. yPredValues : `IVector<float>` len : `int` Number of valid input data points for extrapolation (not for the training data!). yOrder : `int` Number of history samples used for prediction. Must be greater or equal to 1. Returns: `DynamicParameterEstimation`
`DynamicParameterEstimation.LUSolver` Full Usage: `DynamicParameterEstimation.LUSolver` Returns: `IDynamicParameterEstimationSolver`	Returns a fresh instance of a LU decomposition solver that can be used for parameter estimation. Returns: `IDynamicParameterEstimationSolver`
`DynamicParameterEstimation.QRSolver` Full Usage: `DynamicParameterEstimation.QRSolver` Returns: `IDynamicParameterEstimationSolver`	Returns a fresh instance of a QR decomposition solver that can be used for parameter estimation. Returns: `IDynamicParameterEstimationSolver`
`DynamicParameterEstimation.SVDSolver` Full Usage: `DynamicParameterEstimation.SVDSolver` Returns: `IDynamicParameterEstimationSolver`	Returns a fresh instance of a singular value decomposition solver that can be used for parameter estimation. Returns: `IDynamicParameterEstimationSolver`