def test_alternate_samplers(self):
# this used to fail for psipy, since it does not support alternative
# samplers
interface.mcmc(data, nsamples=25, sampler="MetropolisHastings")
interface.mcmc(data, nsamples=25, sampler="GenericMetropolis")
self.assertRaises(sfu.PsignifitException, interface.mcmc, data,
sampler="DoesNotExist")
def test_alternate_samplers(self):
# this used to fail for psipy, since it does not support alternative
# samplers
interface.mcmc(data, nsamples=25, sampler="MetropolisHastings")
interface.mcmc(data, nsamples=25, sampler="GenericMetropolis")
self.assertRaises(sfu.PsignifitException,
interface.mcmc,
data,
sampler="DoesNotExist")
def test_old_doctest(self):
x = [float(2*k) for k in xrange(6)]
k = [34,32,40,48,50,48]
n = [50]*6
d = [[xx,kk,nn] for xx,kk,nn in zip(x,k,n)]
priors = ('Gauss(0,1000)','Gauss(0,1000)','Beta(3,100)')
stepwidths = (1.,1.,0.01)
sfr.setSeed(1)
(estimates, deviance, posterior_predictive_data,
posterior_predictive_deviances, posterior_predictive_Rpd,
posterior_predictive_Rkd, logposterior_ratios, accept_rate) = interface.mcmc(d,nsamples=10000,priors=priors,stepwidths=stepwidths)
self.assertAlmostEqual( np.mean(estimates[:,0]), 2.5463976926832483)
self.assertAlmostEqual( np.mean(estimates[:,1]), 7.335732619111738,
places=3)
def test_old_doctest(self):
x = [float(2 * k) for k in xrange(6)]
k = [34, 32, 40, 48, 50, 48]
n = [50] * 6
d = [[xx, kk, nn] for xx, kk, nn in zip(x, k, n)]
priors = ('Gauss(0,1000)', 'Gauss(0,1000)', 'Beta(3,100)')
stepwidths = (1., 1., 0.01)
sfr.setSeed(1)
(estimates, deviance, posterior_predictive_data,
posterior_predictive_deviances, posterior_predictive_Rpd,
posterior_predictive_Rkd, logposterior_ratios,
accept_rate) = interface.mcmc(d,
nsamples=10000,
priors=priors,
stepwidths=stepwidths)
self.assertAlmostEqual(np.mean(estimates[:, 0]), 2.5463976926832483)
self.assertAlmostEqual(np.mean(estimates[:, 1]),
7.335732619111738,
places=3)
def test_basic(self):
interface.mcmc(data)
def test_basic(self):
interface.mcmc(data)
def test_stepwidth(self):
interface.mcmc(data, nsamples=25, stepwidths=[0.1, 0.2, 0.3])
def test_nafc(self):
interface.mcmc(data, nsamples=25, nafc=23)
def test_core(self):
interface.mcmc(data, nsamples=25, core='ab')
def test_prior(self):
priors = ('Gauss(0,10)', 'Gamma(2,3)', 'Uniform(1,5)')
interface.mcmc(data, nsamples=25, priors=priors)
def test_nafc(self):
interface.mcmc(data,nsamples=25, nafc=23)
def test_nsamples(self):
interface.mcmc(data, nsamples=666)
def test_start(self):
interface.mcmc(data,nsamples=25, start=[0.1,0.2,0.3])
def test_sigmoid(self):
interface.mcmc(data, nsamples=25, sigmoid='gumbel_r')
def test_stepwidth(self):
interface.mcmc(data, nsamples=25, stepwidths=[0.1, 0.2, 0.3])
def test_prior(self):
priors = ('Gauss(0,10)', 'Gamma(2,3)', 'Uniform(1,5)')
interface.mcmc(data, nsamples=25, priors=priors)
def test_core(self):
interface.mcmc(data, nsamples=25, core='ab')
def test_nsamples(self):
interface.mcmc(data,nsamples=666)
def test_start(self):
interface.mcmc(data, nsamples=25, start=[0.1, 0.2, 0.3])
def test_sigmoid(self):
interface.mcmc(data,nsamples=25, sigmoid='gumbel_r')
def sample ():
boots = interface.bootstrap ( d, priors=priors, nsamples=1500-2*k )
mape = interface.mapestimate ( d, priors=priors )
mcmc = interface.mcmc ( d, start=(4,2,.02), priors=priors, nsamples = 1500-2*k )
diag = interface.diagnostics ( d, (4,1,.02) )
return float(os.popen ( "ps -C python -o rss" ).readlines()[1])/1024