coverage.py 文件源码

def gamma(self,samples):
        """
        Sampling from a Gamma distribution with mean 1

        The parameterization with alpha and beta is more common in Bayesian statistics,
        where the gamma distribution is used as a conjugate prior distribution
        for various types of inverse scale (aka rate) parameters, such as the
        lambda of an exponential distribution or a Poisson distribution[4]  or for
        t hat matter, the beta of the gamma distribution itself.
        (The closely related inverse gamma distribution is used as a conjugate
        prior for scale parameters, such as the variance of a normal distribution.)
        shape, scale = 2., 2. # mean=4, std=2*sqrt(2)

        (Wikipedia: https://en.wikipedia.org/wiki/Gamma_distribution)

        s = np.random.gamma(shape, scale, 1000)
        E|x| = k.theta (alpha*theta)
        If i want a specific mean, theta=E|x|/alpha
        ------------------------------------------------------------------------

        - samples: number of values that will be returned.
        """
        shape=float(self.__params[0]*1.0)
        theta=float(self.__params[1]*1.0)
        distro=gamma(a=shape,scale=theta)
        f=distro.rvs(size=samples)
        return f