Esempio n. 1
0
    def log_z(self, n=500, integration='simpson'):
        """
        Calculate the log partion function.
        """
        from numpy import pi, linspace, max
        from csb.numeric import log, exp

        if integration == 'simpson':
            from csb.numeric import simpson_2d
            x = linspace(0., 2 * pi, 2 * n + 1)
            dx = x[1] - x[0]

            f = -self.beta * self.energy(x)
            f_max = max(f)
            f -= f_max

            I = simpson_2d(exp(f))
            return log(I) + f_max + 2 * log(dx)

        elif integration == 'trapezoidal':

            from csb.numeric import trapezoidal_2d
            x = linspace(0., 2 * pi, n)
            dx = x[1] - x[0]

            f = -self.beta * self.energy(x)
            f_max = max(f)
            f -= f_max
            I = trapezoidal_2d(exp(f))
            return log(I) + f_max + 2 * log(dx)
        else:
            raise NotImplementedError(
                'Choose from trapezoidal and simpson-rule Integration')
Esempio n. 2
0
    def log_z(self, n=500, integration='simpson'):
        """
        Calculate the log partion function.
        """
        from numpy import pi, linspace, max
        from csb.numeric import log, exp

        if integration == 'simpson':
            from csb.numeric import simpson_2d
            x = linspace(0., 2 * pi, 2 * n + 1)
            dx = x[1] - x[0]

            f = -self.beta * self.energy(x)
            f_max = max(f)
            f -= f_max

            I = simpson_2d(exp(f))
            return log(I) + f_max + 2 * log(dx)

        elif integration == 'trapezoidal':

            from csb.numeric import trapezoidal_2d
            x = linspace(0., 2 * pi, n)
            dx = x[1] - x[0]

            f = -self.beta * self.energy(x)
            f_max = max(f)
            f -= f_max
            I = trapezoidal_2d(exp(f))
            return log(I) + f_max + 2 * log(dx)
        else:
            raise NotImplementedError(
                'Choose from trapezoidal and simpson-rule Integration')
Esempio n. 3
0
 def testExp(self):
     from csb.numeric import exp, EXP_MAX, EXP_MIN
     from numpy import exp as ref_exp
     
     x = np.linspace(EXP_MIN,
                     EXP_MAX, 100000)
     
     self.assertTrue((exp(x) == ref_exp(x)).all())
     self.assertEqual(exp(EXP_MAX + 10.), exp(EXP_MAX))
     self.assertEqual(exp(10. * EXP_MIN), exp(EXP_MIN))
Esempio n. 4
0
 def estimate_with_fixed_beta(self, data, beta):
     
     mu = median(data)
     v = mean((data - mu) ** 2)
     alpha = sqrt(v * exp(gammaln(1. / beta) - gammaln(3. / beta)))
 
     return mu, alpha
Esempio n. 5
0
 def log_prob(self, x):
     
     mu = self.mu
     beta = self.beta
     
     z = (x - mu) / beta
     return log(1. / beta) - z - exp(-z) 
Esempio n. 6
0
    def testTrapezoidal(self):
        from csb.numeric import trapezoidal, exp
        
        x = np.linspace(-10., 10, 1000)
        y = exp(-0.5 * x * x) / np.sqrt(2 * np.pi)

        self.assertAlmostEqual(trapezoidal(x, y), 1.0, 10)
Esempio n. 7
0
    def estimate_with_fixed_beta(self, data, beta):

        mu = median(data)
        v = mean((data - mu)**2)
        alpha = sqrt(v * exp(gammaln(1. / beta) - gammaln(3. / beta)))

        return mu, alpha
Esempio n. 8
0
    def log_prob(self, x):

        mu = self.mu
        beta = self.beta

        z = (x - mu) / beta
        return log(1. / beta) - z - exp(-z)
Esempio n. 9
0
    def testTruncatedGamma(self):
        alpha = 2.
        beta = 1.
        x_min = 0.1
        x_max = 5.

        x = truncated_gamma(10000, alpha, beta, x_min, x_max)

        self.assertTrue((x <= x_max).all())
        self.assertTrue((x >= x_min).all())

        hy, hx = density(x, 100)
        hx = 0.5 * (hx[1:] + hx[:-1])
        hy = hy.astype('d')

        with warnings.catch_warnings(record=True) as warning:
            warnings.simplefilter("always")

            hy /= (hx[1] - hx[0]) * hy.sum()

            self.assertLessEqual(len(warning), 1)

            if len(warning) == 1:
                warning = warning[0]
                self.assertEqual(warning.category, RuntimeWarning)
                self.assertTrue(
                    str(warning.message).startswith(
                        'divide by zero encountered'))

        x = numpy.linspace(x_min, x_max, 1000)
        p = (alpha - 1) * log(x) - beta * x
        p -= log_sum_exp(p)
        p = exp(p) / (x[1] - x[0])
Esempio n. 10
0
    def testTruncatedGamma(self):
        alpha = 2.
        beta = 1.
        x_min = 0.1
        x_max = 5.

        x = truncated_gamma(10000, alpha, beta, x_min, x_max)

        self.assertTrue((x <= x_max).all())
        self.assertTrue((x >= x_min).all())

        hy, hx = density(x, 100)
        hx = 0.5 * (hx[1:] + hx[:-1])
        hy = hy.astype('d')

        with warnings.catch_warnings(record=True) as warning:
            warnings.simplefilter("always")            
            
            hy /= (hx[1] - hx[0]) * hy.sum()
            
            self.assertLessEqual(len(warning), 1)
            
            if len(warning) == 1:
                warning = warning[0]
                self.assertEqual(warning.category, RuntimeWarning)
                self.assertTrue(str(warning.message).startswith('divide by zero encountered'))            

        x = numpy.linspace(x_min, x_max, 1000)
        p = (alpha - 1) * log(x) - beta * x
        p -= log_sum_exp(p)
        p = exp(p) / (x[1] - x[0])
Esempio n. 11
0
    def energy(self, raw_energies):

        from numpy import isinf
        
        if isinf(self.beta):
            m = (raw_energies >= self.e_max).astype('f')
            return - m * log(0.)
        else:
            x = 1 + exp(self.beta * (raw_energies - self.e_max))
            return log(x)
Esempio n. 12
0
    def energy(self, raw_energies):

        from numpy import isinf

        if isinf(self.beta):
            m = (raw_energies >= self.e_max).astype('f')
            return -m * log(0.)
        else:
            x = 1 + exp(self.beta * (raw_energies - self.e_max))
            return log(x)
Esempio n. 13
0
 def estimate_scales(self, beta=1.0):
     """
     Update scales from current model and samples
     @param beta: inverse temperature
     @type beta: float
     """
     from csb.numeric import log, log_sum_exp, exp
     s_sq = (self.sigma ** 2).clip(1e-300, 1e300)
     Z = (log(self.w) - 0.5 * (self.delta / s_sq + self.dimension * log(s_sq))) * beta
     self.scales = exp(Z.T - log_sum_exp(Z.T))
Esempio n. 14
0
 def evaluate(self, x):
     """
     Evaluate the probability of observing values C{x}.
     
     @param x: values
     @type x: array        
     @rtype: array
     """
     x = numpy.array(x)
     return exp(self.log_prob(x))
Esempio n. 15
0
 def evaluate(self, x):
     """
     Evaluate the probability of observing values C{x}.
     
     @param x: values
     @type x: array        
     @rtype: array
     """
     x = numpy.array(x)
     return exp(self.log_prob(x))      
 def estimate_scales(self, beta=1.0):
     """
     Update scales from current model and samples
     @param beta: inverse temperature
     @type beta: float
     """
     from csb.numeric import log, log_sum_exp, exp
     s_sq = (self.sigma**2).clip(1e-300, 1e300)
     Z = (log(self.w) - 0.5 *
          (self.delta / s_sq + self.dimension * log(s_sq))) * beta
     self.scales = exp(Z.T - log_sum_exp(Z.T))
Esempio n. 17
0
    def entropy(self, n=500):
        """
        Calculate the entropy of the model.

        @param n: number of integration points for numerical integration
        @type n: integer
        """
        from csb.numeric import trapezoidal_2d
        from numpy import pi, linspace, max
        from csb.numeric import log, exp

        x = linspace(0., 2 * pi, n)
        dx = x[1] - x[0]

        f = -self.beta * self.energy(x)
        f_max = max(f)

        log_z = log(trapezoidal_2d(exp(f - f_max))) + f_max + 2 * log(dx)
        average_energy = trapezoidal_2d(f * exp(f - f_max))\
                         * exp(f_max + 2 * log(dx) - log_z)

        return -average_energy + log_z
Esempio n. 18
0
    def entropy(self, n=500):
        """
        Calculate the entropy of the model.

        @param n: number of integration points for numerical integration
        @type n: integer
        """
        from csb.numeric import trapezoidal_2d
        from numpy import pi, linspace, max
        from csb.numeric import log, exp

        x = linspace(0., 2 * pi, n)
        dx = x[1] - x[0]

        f = -self.beta * self.energy(x)
        f_max = max(f)

        log_z = log(trapezoidal_2d(exp(f - f_max))) + f_max + 2 * log(dx)
        average_energy = trapezoidal_2d(f * exp(f - f_max))\
                         * exp(f_max + 2 * log(dx) - log_z)

        return -average_energy + log_z
Esempio n. 19
0
    def sample_beta(kappa, n=1):
        from numpy import arccos
        from csb.numeric import log, exp
        from numpy.random import random

        u = random(n)

        if kappa != 0.:
            x = clip(1 + 2 * log(u + (1 - u) * exp(-kappa)) / kappa, -1., 1.)
        else:
            x = 2 * u - 1

        if n == 1:
            return arccos(x)[0]
        else:
            return arccos(x)
Esempio n. 20
0
def inv_digamma_minus_log(y, tol=1e-10, n_iter=100):
    """
    Solve y = psi(alpha) - log(alpha) for alpha by fixed point
    integration.
    """
    if y >= -log(6.):
        x = 1 / (2 * (1 - exp(y)))
    else:
        x = 1.e-10
    for _i in range(n_iter):
        z = approx_psi(x) - log(x) - y
        if abs(z) < tol:
            break
        x -= x * z / (x * d_approx_psi(x) - 1)
        x = abs(x)
    return x
Esempio n. 21
0
    def estimate(self, context, data):
        """
        Generate samples from the posterior of alpha and beta.

        For beta the posterior is a gamma distribution and analytically
        acessible.

        The posterior of alpha can not be expressed analytically and is
        aproximated using adaptive rejection sampling.
        """
        pdf = GammaPrior()

        ## sufficient statistics

        a = numpy.mean(data)
        b = exp(numpy.mean(log(data)))
        v = numpy.std(data) ** 2
        n = len(data)

        beta = a / v
        alpha = beta * a
        samples = []

        for _i in range(self.n_samples):

            ## sample beta from Gamma distribution
            beta = numpy.random.gamma(n * alpha + context._hyper_beta.alpha,
                                      1 / (n * a + context._hyper_beta.beta))

            ## sample alpha with ARS
            logp = ARSPosteriorAlpha(n * log(beta * b)\
                                     - context.hyper_alpha.beta,
                                     context.hyper_alpha.alpha - 1., n)
            ars = csb.statistics.ars.ARS(logp)
            ars.initialize(logp.initial_values()[:2], z0=0.)
            alpha = ars.sample()

            if alpha is None:
                raise ValueError("ARS failed")

            samples.append((alpha, beta))

        pdf.alpha, pdf.beta = samples[-1]

        return pdf
Esempio n. 22
0
    def testSimpson2D(self):
        from csb.numeric import simpson_2d, exp
        from numpy import pi

        xx = np.linspace(-10., 10, 500)
        yy = np.linspace(-10., 10, 500)

        X, Y = np.meshgrid(xx, yy)
        x = np.array(list(zip(np.ravel(X), np.ravel(Y))))        

        # mean = np.zeros((2,))
        cov = np.eye(2)
        mu = np.ones(2)
        # D = 2
        q = np.sqrt(np.clip(np.sum((x - mu) * np.dot(x - mu, np.linalg.inv(cov).T), -1), 0., 1e308))
        f = exp(-0.5 * q ** 2) / ((2 * pi) * np.sqrt(np.abs(np.linalg.det(cov))))
        f = f.reshape((len(xx), len(yy)))
        I = simpson_2d(f) * (xx[1] - xx[0]) * (yy[1] - yy[0])

        self.assertTrue(abs(I - 1.) <= 1e-8)
Esempio n. 23
0
    def testTruncatedNormal(self):

        mu = 2.
        sigma = 1.
        x_min = -1.
        x_max = 5.

        x = truncated_normal(10000, mu, sigma, x_min, x_max)

        self.assertAlmostEqual(numpy.mean(x), mu, delta=1e-1)
        self.assertAlmostEqual(numpy.var(x), sigma, delta=1e-1)

        self.assertTrue((x <= x_max).all())
        self.assertTrue((x >= x_min).all())

        hy, hx = density(x, 100)
        hx = 0.5 * (hx[1:] + hx[:-1])
        hy = hy.astype('d')

        with warnings.catch_warnings(record=True) as warning:
            warnings.simplefilter("always")

            hy /= (hx[1] - hx[0]) * hy.sum()

            self.assertLessEqual(len(warning), 1)

            if len(warning) == 1:
                warning = warning[0]
                self.assertEqual(warning.category, RuntimeWarning)
                self.assertTrue(
                    str(warning.message).startswith(
                        'divide by zero encountered'))

        x = numpy.linspace(mu - 5 * sigma, mu + 5 * sigma, 1000)

        p = -0.5 * (x - mu)**2 / sigma**2
        p -= log_sum_exp(p)
        p = exp(p) / (x[1] - x[0])
Esempio n. 24
0
    def testTruncatedNormal(self):

        mu = 2.
        sigma = 1.
        x_min = -1.
        x_max = 5.

        x = truncated_normal(10000, mu, sigma, x_min, x_max)

        self.assertAlmostEqual(numpy.mean(x), mu, delta=1e-1)
        self.assertAlmostEqual(numpy.var(x), sigma, delta=1e-1)

        self.assertTrue((x <= x_max).all())
        self.assertTrue((x >= x_min).all())

        hy, hx = density(x, 100)
        hx = 0.5 * (hx[1:] + hx[:-1])
        hy = hy.astype('d')
        
        with warnings.catch_warnings(record=True) as warning:
            warnings.simplefilter("always")        
            
            hy /= (hx[1] - hx[0]) * hy.sum()
            
            self.assertLessEqual(len(warning), 1)
            
            if len(warning) == 1:
                warning = warning[0]
                self.assertEqual(warning.category, RuntimeWarning)
                self.assertTrue(str(warning.message).startswith('divide by zero encountered'))
            
        x = numpy.linspace(mu - 5 * sigma, mu + 5 * sigma, 1000)

        p = -0.5 * (x - mu) ** 2 / sigma ** 2
        p -= log_sum_exp(p)
        p = exp(p) / (x[1] - x[0])
Esempio n. 25
0
 def __call__(self, raw_energies):
     return exp(-self.energy(raw_energies))
Esempio n. 26
0
 def __call__(self, raw_energies):
     return exp(-self.energy(raw_energies))
Esempio n. 27
0
 def prob(self, x, y):
     """
     Return the probability of the configurations x cross y.
     """
     from csb.numeric import exp
     return exp(-self.beta * self(x, y))
Esempio n. 28
0
 def prob(self, x, y):
     """
     Return the probability of the configurations x cross y.
     """
     from csb.numeric import exp
     return exp(-self.beta * self(x, y))