Package gov.nih.mipav.model.algorithms
Class FitExponential
java.lang.Object
gov.nih.mipav.model.algorithms.NLConstrainedEngine
gov.nih.mipav.model.algorithms.NLFittedFunction
gov.nih.mipav.model.algorithms.FitExponential
FitExponential -fits an array of points to an exponential of the type y = a0 + a1*exp(a2*x).
- Version:
- 0.9
- Author:
- William Gandler
- See Also:
-
Field Summary
Fields inherited from class gov.nih.mipav.model.algorithms.NLFittedFunction
chisq, EPSILON, MAX_ITR, MIN_ITR, xSeries, yDataFitted, ySeriesFields inherited from class gov.nih.mipav.model.algorithms.NLConstrainedEngine
a, absoluteConvergence, analyticalJacobian, bl, bounds, bu, ctrlMat, dyda, gues, internalScaling, iters, jacobian, maxIterations, nPts, outputMes, param, parameterConvergence, relativeConvergence, residuals, secondAllowed, stdv, tolerance -
Constructor Summary
ConstructorsConstructorDescriptionFitExponential - test constructor, builds and test function.FitExponential(int nPoints, double[] xData, double[] yData) FitExponential.FitExponential(int nPoints, float[] xData, float[] yData) Constructs new fit exponential. -
Method Summary
Modifier and TypeMethodDescriptionprotected voidCalculates chi squaredprotected voidCalculates yDataFittedvoidDisplay results of displaying exponential fitting parameters.voiddriver()Starts the analysis.voidfitToFunction(double[] a, double[] residuals, double[][] covarMat) Fit to function - a0 + a1*exp(a2*x).protected Jama.MatrixCalculates the residuals for a given function, not implemented since some functions might prefer to only use a subset of data points, or not use yDataFitted if working during an iterationprivate voidtestData()Test data to test fitting of exponential.Methods inherited from class gov.nih.mipav.model.algorithms.NLFittedFunction
getChisq, getFittedY, getMedianMethods inherited from class gov.nih.mipav.model.algorithms.NLConstrainedEngine
dumpTestResults, fitToTestFunction, getChiSquared, getExitStatus, getIterations, getParameters, getResiduals, statusMessage
-
Constructor Details
-
FitExponential
public FitExponential()FitExponential - test constructor, builds and test function. -
FitExponential
public FitExponential(int nPoints, double[] xData, double[] yData) FitExponential.- Parameters:
nPoints- number of points in the functionxData- DOCUMENT ME!yData- DOCUMENT ME!
-
FitExponential
public FitExponential(int nPoints, float[] xData, float[] yData) Constructs new fit exponential.- Parameters:
nPoints- Number of points in the functionxData- DOCUMENT ME!yData- DOCUMENT ME!
-
-
Method Details
-
driver
public void driver()Starts the analysis. For some reason a guess with the wrong sign for a2 will not converge. Therefore, try both sign and take the one with the lowest chi-squared value.- Overrides:
driverin classNLConstrainedEngine
-
displayResults
public void displayResults()Display results of displaying exponential fitting parameters.- Specified by:
displayResultsin classNLFittedFunction
-
fitToFunction
public void fitToFunction(double[] a, double[] residuals, double[][] covarMat) Fit to function - a0 + a1*exp(a2*x).- Specified by:
fitToFunctionin classNLConstrainedEngine- Parameters:
a- The best guess parameter values.residuals- ymodel - yData.covarMat- The derivative values of y with respect to fitting parameters.
-
testData
private void testData()Test data to test fitting of exponential. -
calculateFittedY
protected void calculateFittedY()Description copied from class:NLFittedFunctionCalculates yDataFitted- Specified by:
calculateFittedYin classNLFittedFunction
-
generateResiduals
protected Jama.Matrix generateResiduals()Description copied from class:NLFittedFunctionCalculates the residuals for a given function, not implemented since some functions might prefer to only use a subset of data points, or not use yDataFitted if working during an iteration- Specified by:
generateResidualsin classNLFittedFunction- Returns:
-
calculateChiSq
protected void calculateChiSq()Description copied from class:NLFittedFunctionCalculates chi squared- Specified by:
calculateChiSqin classNLFittedFunction
-