def _sample_noiseless(self, comp, vals):
def logprob(hypers):
mean = hypers[0]
amp2 = hypers[1]
noise = 1e-3
# This is pretty hacky, but keeps things sane.
if mean > np.max(vals) or mean < np.min(vals):
return -np.inf
if amp2 < 0:
return -np.inf
cov = (amp2 * (self.cov_func(self.ls, comp, None) +
1e-6*np.eye(comp.shape[0])) + noise*np.eye(comp.shape[0]))
chol = spla.cholesky(cov, lower=True)
solve = spla.cho_solve((chol, True), vals - mean)
lp = -np.sum(np.log(np.diag(chol)))-0.5*np.dot(vals-mean, solve)
# Roll in amplitude lognormal prior
lp -= 0.5*(np.log(np.sqrt(amp2))/self.amp2_scale)**2
return lp
hypers = util.slice_sample(np.array(
[self.mean, self.amp2, self.noise]), logprob, compwise=False)
self.mean = hypers[0]
self.amp2 = hypers[1]
self.noise = 1e-3
def _sample_ls(self, comp, vals):
def logprob(ls):
if np.any(ls < 0) or np.any(ls > self.max_ls):
return -np.inf
cov = (self.amp2 * (self.cov_func(ls, comp, None) +
1e-6*np.eye(comp.shape[0])) + self.noise*np.eye(comp.shape[0]))
chol = spla.cholesky(cov, lower=True)
solve = spla.cho_solve((chol, True), vals - self.mean)
lp = (-np.sum(np.log(np.diag(chol))) -
0.5*np.dot(vals-self.mean, solve))
return lp
self.ls = util.slice_sample(self.ls, logprob, compwise=True)
