Example usage for org.apache.commons.math3.fitting WeightedObservedPoints toList

Introduction

In this page you can find the example usage for org.apache.commons.math3.fitting WeightedObservedPoints toList.

Prototype

public List<WeightedObservedPoint> toList() 

Source Link

Document

Gets a snapshot of the observed points.

Usage

From source file:com.cloudera.hts.utils.math.PolyFit.java

public static void main(String[] args) {

    double[] x = { -5.0, -4.0, -3.0, -2.0, 0, 2, 3, 4 };
    double[] y = { 21, 13, 7, 3, 1, 7, 13, 21 };

    WeightedObservedPoints obs = new WeightedObservedPoints();

    // Add points here; for instance,
    int i = 0;/*from   w w  w  . ja  va 2  s.c o m*/
    for (double xc : x) {

        WeightedObservedPoint point = new WeightedObservedPoint(xc, y[i], 1.0);
        obs.add(xc, y[i]);

        System.out.println(xc + " " + y[i]);

        i++;

    }

    // Instantiate a third-degree polynomial fitter.
    PolynomialCurveFitter fitter = PolynomialCurveFitter.create(2);

    // Retrieve fitted parameters (coefficients of the polynomial function).
    final double[] coeff = fitter.fit(obs.toList());

    System.out.println(Arrays.toString(coeff));

}

---

From source file:cn.edu.xmu.tidems.control.support.TideMSUtil.java

public static double[] polynomialFit(final double[] x, final double[] y, final int order) {

    if ((x == null) || (x.length == 0) || (y == null) || (y.length == 0)) {
        throw new IllegalArgumentException("Input arrays x/y  can't be null or empty.");
    }/*  w  ww .  j a  va  2s  .c  o  m*/
    if (x.length != y.length) {
        throw new IllegalArgumentException("The length of arrays x, y must be equal.");
    }
    if (order < 1) {
        throw new IllegalArgumentException("Order must be greater than 0.");
    }
    if (x.length <= order) {
        throw new IllegalArgumentException("The length of array must be greater than order.");
    }
    final WeightedObservedPoints obs = new WeightedObservedPoints();
    for (int i = 0; i < x.length; i++) {
        obs.add(x[i], y[i]);
    }
    final PolynomialCurveFitter fitter = PolynomialCurveFitter.create(order);
    final double[] coeff = fitter.fit(obs.toList());
    return coeff;
}

---

From source file:ardufocuser.starfocusing.Utils.java

public static double[] computeGaussianParams(int[][] image, int starCenterX, int starCenterY, int radius) {

    int min = computeMinMax(image, starCenterX - radius, starCenterY - radius, starCenterX + radius,
            starCenterY + radius)[0];/*from   w  w  w. j a v  a 2  s. c  om*/

    WeightedObservedPoints obs = new WeightedObservedPoints();
    for (int y = starCenterY - radius; y <= starCenterY + radius; y++) {
        for (int x = starCenterX - radius; x <= starCenterX + radius; x++) {
            double d = computeDistance(starCenterX, starCenterY, x, y);
            obs.add(d, image[x][y] - min);
        }
    }

    double[] parameters = GaussianCurveFitter.create()
            .withStartPoint(new double[] { image[starCenterX][starCenterY], 0.0, 1.0 }).fit(obs.toList());
    return parameters;
}

---

From source file:heizung.Heizkurve.java

public static PolynomialFunction getPolynomialFit(List<Point> pList) {
    PolynomialFunction result = null;//from   www . j  a  v a2s .c o  m
    if (pList == null) {
        return result;
    }
    try {

        final WeightedObservedPoints obs = new WeightedObservedPoints();
        for (Point p : pList) {
            obs.add(p.getX(), p.getY());
        }

        final ParametricUnivariateFunction function = new PolynomialFunction.Parametric();
        // Start fit from initial guesses that are far from the optimal
        // values.
        // final SimpleCurveFitter fitter =
        // SimpleCurveFitter.create(function,
        // new double[] { -1e20, 3e15, -5e25 });
        final SimpleCurveFitter fitter = SimpleCurveFitter.create(function,
                new double[] { -2e20, 1e15, -1e25 });
        // 2e2 ist 2*10^2 = 2*100
        final double[] best = fitter.fit(obs.toList());
        // System.out.println("Parameters: " + best.length);
        // funktion ausgeben
        result = new PolynomialFunction(best);
    } catch (Exception e) {
        // e.printStackTrace();
        System.out.println("PolynomialFunction: " + e);
    }
    return result;
}

---

From source file:net.sf.mzmine.chartbasics.HistogramChartFactory.java

/**
 * Performs Gaussian fit on XYSeries//from  w w w.  ja v a2 s .c o m
 * 
 * @param data the data
 * @param series the series index
 * @param gMin lower bound of Gaussian fit
 * @param gMax upper bound of Gaussian fit
 * @param sigDigits number of significant digits
 * @return double[] {normFactor, mean, sigma} as a result of
 *         GaussianCurveFitter.create().fit(obs.toList())
 */
public static double[] gaussianFit(XYDataset data, int series, double gMin, double gMax) {
    // gaussian fit
    WeightedObservedPoints obs = new WeightedObservedPoints();

    for (int i = 0; i < data.getItemCount(series); i++) {
        double x = data.getXValue(series, i);
        if (x >= gMin && x <= gMax)
            obs.add(x, data.getYValue(series, i));
    }
    return fitter.fit(obs.toList());
}

---

From source file:net.sf.mzmine.chartbasics.HistogramChartFactory.java

/**
 * Performs Gaussian fit on XYSeries/*from w  ww  .ja v  a2s.  co  m*/
 * 
 * @param series the data
 * @param gMin lower bound of Gaussian fit
 * @param gMax upper bound of Gaussian fit
 * @param sigDigits number of significant digits
 * @return double[] {normFactor, mean, sigma} as a result of
 *         GaussianCurveFitter.create().fit(obs.toList())
 */
public static double[] gaussianFit(XYSeries series, double gMin, double gMax) {
    // gaussian fit
    WeightedObservedPoints obs = new WeightedObservedPoints();

    for (int i = 0; i < series.getItemCount(); i++) {
        double x = series.getX(i).doubleValue();
        if (x >= gMin && x <= gMax)
            obs.add(x, series.getY(i).doubleValue());
    }

    return fitter.fit(obs.toList());
}

---

From source file:net.sf.mzmine.chartbasics.HistogramChartFactory.java

/**
 * Performs Gaussian fit on XYSeries//from  w  w  w . java  2s  .  c  om
 * 
 * @param data the data
 * @param gMin lower bound of Gaussian fit
 * @param gMax upper bound of Gaussian fit
 * @param sigDigits number of significant digits
 * @return double[] {normFactor, mean, sigma} as a result of
 *         GaussianCurveFitter.create().fit(obs.toList())
 */
public static double[] gaussianFit(List<DataPoint> data, double gMin, double gMax) {
    // gaussian fit
    WeightedObservedPoints obs = new WeightedObservedPoints();

    for (int i = 0; i < data.size(); i++) {
        double x = data.get(i).getMZ();
        if (x >= gMin && x <= gMax)
            obs.add(x, data.get(i).getIntensity());
    }
    try {
        return fitter.fit(obs.toList());
    } catch (Exception e) {
        e.printStackTrace();
        logger.error("Cannot fit Gaussian from {} to {}", gMin, gMax, e);
        return null;
    }
}

---

From source file:edu.harvard.we99.services.MathServiceImpl.java

/**
 *
 * @param points Required to be n arrays of size 2.
 *//*from  w  w w.  ja  v  a2 s. c o  m*/
@Override
public double[] fitCurve(double[][] points) {

    if (points.length == 0) {
        throw new WebApplicationException(Response.status(400).build());
    }

    // Create weighted points.
    WeightedObservedPoints obs = new WeightedObservedPoints();
    for (double[] point : points) {
        if (point.length != 2) {
            throw new WebApplicationException(Response.status(400).build());
        }
        obs.add(point[0], point[1]);
    }
    return fitter.fit(obs.toList());

}

---

From source file:eu.tango.energymodeller.energypredictor.CpuOnlyPolynomialEnergyPredictor.java

/**
 * This calculates the mathematical function that predicts the power
 * consumption given the cpu utilisation.
 *
 * @param host The host to get the function for
 * @return The mathematical function that predicts the power consumption
 * given the cpu utilisation.//from w ww. ja v  a  2s  . c om
 */
private PredictorFunction<PolynomialFunction> retrieveModel(Host host) {
    PredictorFunction<PolynomialFunction> answer;
    if (modelCache.containsKey(host)) {
        /**
         * A small cache avoids recalculating the regression so often.
         */
        return modelCache.get(host);
    }
    WeightedObservedPoints points = new WeightedObservedPoints();
    for (HostEnergyCalibrationData data : host.getCalibrationData()) {
        points.add(data.getCpuUsage(), data.getWattsUsed());
    }
    PolynomialCurveFitter fitter = PolynomialCurveFitter.create(2);
    final double[] best = fitter.fit(points.toList());
    PolynomialFunction function = new PolynomialFunction(best);
    double sse = getSumOfSquareError(function, points.toList());
    double rmse = getRootMeanSquareError(sse, points.toList().size());
    answer = new PredictorFunction<>(function, sse, rmse);
    modelCache.put(host, answer);
    return answer;
}

---

From source file:eu.tango.energymodeller.energypredictor.CpuAndAcceleratorEnergyPredictor.java

/**
 * This calculates the mathematical function that predicts the power
 * consumption given the cpu utilisation.
 *
 * @param host The host to get the function for
 * @return The mathematical function that predicts the power consumption
 * given the cpu utilisation.//  w  w  w. ja  va  2  s .  co  m
 */
private PredictorFunction<PolynomialFunction> retrieveCpuModel(Host host) {
    PredictorFunction<PolynomialFunction> answer;
    if (modelCache.containsKey(host)) {
        /**
         * A small cache avoids recalculating the regression so often.
         */
        return modelCache.get(host);
    }
    WeightedObservedPoints points = new WeightedObservedPoints();
    for (HostEnergyCalibrationData data : host.getCalibrationData()) {
        points.add(data.getCpuUsage(), data.getWattsUsed());
    }
    PolynomialCurveFitter fitter = PolynomialCurveFitter.create(2);
    final double[] best = fitter.fit(points.toList());
    PolynomialFunction function = new PolynomialFunction(best);
    double sse = getSumOfSquareError(function, points.toList());
    double rmse = getRootMeanSquareError(sse, points.toList().size());
    answer = new PredictorFunction<>(function, sse, rmse);
    modelCache.put(host, answer);
    return answer;
}

---

• «
• 1
• 2
• 3
• »