def __init__(self, dim=None, nIterMC=30):
Cached.__init__(self)
self._nIterMC = nIterMC
self._reuse = True
self._KiZo = None
self._tol = 1e-6
if dim is not None:
self.initialize(dim)
def __init__(self, y, W=None, Wstar=None):
"""
Args:
y: phenotype vector [N, 1]
W: fixed effect design [N, K]
Wstar: out-of-sample fixed effect design for predictions [No, K]
"""
Cached.__init__(self)
self.y = y
self.W = W
self.Wstar = Wstar
self.setFIinv(None)
self._set_relay(None)
def __init__(self, Y, W, Wstar=None):
"""
Args:
Y: phenotype matrix [N, 1]
W: fixed effect design [N, K]
Wstar: out-of-sample fixed effect design for predictions [No, K]
"""
Cached.__init__(self)
self.Y = Y
self.W = W
self.B = sp.zeros((self._K,1))
self.Wstar = Wstar
self.setFIinv(None)
def __init__(self, Y, W, Wstar=None):
"""
Args:
Y: phenotype matrix [N, 1]
W: fixed effect design [N, K]
Wstar: out-of-sample fixed effect design for predictions [No, K]
"""
Cached.__init__(self)
self.Y = Y
self.W = W
self.B = sp.zeros((self._K, 1))
self.Wstar = Wstar
self.setFIinv(None)
def __init__(self, mean, covar):
"""
covar: Limix covariance function
mean: Limix linear Mean function
"""
Cached.__init__(self)
if not issubclass(type(mean), MeanBase):
raise TypeError('Parameter mean must have MeanBase inheritance.')
if not issubclass(type(covar), Covariance):
raise TypeError('Parameter covar must have Covariance '
'inheritance.')
self.covar = covar
self.mean = mean
self.Areml = cov_reml(self)
self._observe()
def __init__(self, mean, covar):
"""
covar: Limix covariance function
mean: Limix linear Mean function
"""
Cached.__init__(self)
if not issubclass(type(mean), MeanBase):
raise TypeError('Parameter mean must have MeanBase inheritance.')
if not issubclass(type(covar), Covariance):
raise TypeError('Parameter covar must have Covariance '
'inheritance.')
self.covar = covar
self.mean = mean
self.Areml = cov_reml(self)
self._observe()
def __init__(self,dim=None):
Cached.__init__(self)
if dim is not None:
self.initialize(dim)
