def __init__(self, statfunc=None, hyperpars={}, pars={}, name='prior'):
# Posterior hyper-parameters
self.hyperpars = []
for key in hyperpars.keys():
val = hyperpars[key]
param = Parameter(name, key, val, alwaysfrozen=True)
self.__dict__[key] = param
self.hyperpars.append(param)
# References to parameters in source model
self.pars = []
for key in pars.keys():
self.__dict__[key] = pars[key]
self.pars.append(pars[key])
self._statfuncset = False
self.statfunc = (lambda x: None)
if statfunc is not None:
self.statfunc = statfunc
self._statfuncset = True
Likelihood.__init__(self, name)
def __init__(self, statfunc=None, hyperpars={}, pars={}, name='prior'):
# Posterior hyper-parameters
self.hyperpars = []
for key in hyperpars.keys():
val = hyperpars[key]
param = Parameter(name, key, val, alwaysfrozen=True)
self.__dict__[key] = param
self.hyperpars.append(param)
# References to parameters in source model
self.pars = []
for key in pars.keys():
self.__dict__[key] = pars[key]
self.pars.append(pars[key])
self._statfuncset = False
self.statfunc = (lambda x: None)
if statfunc is not None:
self.statfunc = statfunc
self._statfuncset = True
Likelihood.__init__(self, name)
def __init__(self, gp_stat):
statname = 'GPStat'
self.gp_stat = gp_stat
Likelihood.__init__(self, statname)
def __init__(self, gp_stat):
statname = 'GPStat'
self.gp_stat = gp_stat
Likelihood.__init__(self, statname)
def __init__(self, name='fermi'):
Likelihood.__init__(self, name)
def __init__(self, fit):
sherpa_name = 'sherpa_stat'
self.fit = fit
Likelihood.__init__(self, sherpa_name)