rulsif.py 文件源码

def getMedianDistanceBetweenSamples(self, sampleSet=None) :
        """
        Jaakkola's heuristic method for setting the width parameter of the Gaussian
        radial basis function kernel is to pick a quantile (usually the median) of
        the distribution of Euclidean distances between points having different
        labels.

        Reference:
        Jaakkola, M. Diekhaus, and D. Haussler. Using the Fisher kernel method to detect
        remote protein homologies. In T. Lengauer, R. Schneider, P. Bork, D. Brutlad, J.
        Glasgow, H.- W. Mewes, and R. Zimmer, editors, Proceedings of the Seventh
        International Conference on Intelligent Systems for Molecular Biology.
        """
        numrows = sampleSet.shape[0]
        samples = sampleSet

        G = sum((samples * samples), 1)
        Q = numpy.tile(G[:, None], (1, numrows))
        R = numpy.tile(G, (numrows, 1))

        distances = Q + R - 2 * numpy.dot(samples, samples.T)
        distances = distances - numpy.tril(distances)
        distances = distances.reshape(numrows**2, 1, order="F").copy()

        return numpy.sqrt(0.5 * numpy.median(distances[distances > 0]))