def __fitGP1d(theta,
g,
hyp1,
hyp2,
hypvarconst,
gvar=None,
dampalpha=None,
hypstarts=None,
hypinds=None):
return semPCGPwM.__fitGP1d(theta, g, hyp1, hyp2, hypvarconst, gvar,
dampalpha, hypstarts, hypinds)
def __PCs(fitinfo):
"""Apply PCA to reduce the dimension of f."""
return semPCGPwM.__PCs(fitinfo)
def __standardizef(fitinfo, offset=None, scale=None):
"""Standardizes f by creating offset, scale and fs."""
return semPCGPwM.__standardizef(fitinfo, offset, scale)
def __negloglikgrad(hyp, info):
return semPCGPwM.__negloglikgrad(hyp, info)
def __fitGPs(fitinfo, theta, numpcs, hyp1, hyp2, varconstant):
return semPCGPwM.__fitGPs(fitinfo, theta, numpcs, hyp1, hyp2, varconstant)
def predictlpdf(predinfo, f, return_grad=False, addvar=0):
return semPCGPwM.predictlpdf(predinfo, f, return_grad, addvar)
def predict(predinfo, fitinfo, x, theta, **kwargs):
return semPCGPwM.predict(predinfo, fitinfo, x, theta, **kwargs)