def _initParams_regressOut(self, Ycc, X, varXX):
"""
initialize the gp parameters
1) the variance of Kcc as Ycc.var(0).mean()
2) X with the provided
3) variance of interaction (if label is True) will be set to ~0
4) residual to residual
"""
X *= SP.sqrt(varXX / (X**2).mean())
Y1 = self.Y - Ycc
a = SP.array([SP.sqrt(Ycc.var(0).mean())])
b = 1e-3 * SP.ones(1)
c = Y1.var(0).mean() - varXX
c = SP.maximum(1e-1, c)
c = SP.array([SP.sqrt(c)])
# gp hyper params
params = limix.CGPHyperParams()
if self.interaction:
params['covar'] = SP.concatenate(
[a, X.reshape(self.N * self.k, order='F'),
SP.ones(1), b])
else:
params['covar'] = SP.concatenate(
[a, X.reshape(self.N * self.k, order='F')])
params['lik'] = c
return params
def _initParams_fast(self):
"""
initialize the gp parameters
1) project Y on the known factor X0 -> Y0
average variance of Y0 is used to initialize the variance explained by X0
2) considers the residual Y1 = Y-Y0 (this equivals to regress out X0)
3) perform PCA on cov(Y1) and considers the first k PC for initializing X
4) the variance of all other PCs is used to initialize the noise
5) the variance explained by interaction is set to a small random number
"""
Xd = LA.pinv(self.X0)
Y0 = self.X0.dot(Xd.dot(self.Y))
Y1 = self.Y - Y0
YY = SP.cov(Y1)
S, U = LA.eigh(YY)
X = U[:, -self.k:] * SP.sqrt(S[-self.k:])
a = SP.array([SP.sqrt(Y0.var(0).mean())])
b = 1e-3 * SP.randn(1)
c = SP.array([SP.sqrt((YY - SP.dot(X, X.T)).diagonal().mean())])
# gp hyper params
params = limix.CGPHyperParams()
if self.interaction:
params['covar'] = SP.concatenate(
[a, X.reshape(self.N * self.k, order='F'),
SP.ones(1), b])
else:
params['covar'] = SP.concatenate(
[a, X.reshape(self.N * self.k, order='F')])
params['lik'] = c
return params
def setUp(self):
SP.random.seed(1)
#1. simulate
self.settings = {'K': 5, 'N': 100, 'D': 80}
self.simulation = self.simulate()
N = self.settings['N']
K = self.settings['K']
D = self.settings['D']
#2. setup GP
covar = dlimix_legacy.CCovLinearISO(K)
ll = dlimix_legacy.CLikNormalIso()
#create hyperparm
covar_params = SP.array([1.0])
lik_params = SP.array([1.0])
hyperparams = dlimix_legacy.CGPHyperParams()
hyperparams['covar'] = covar_params
hyperparams['lik'] = lik_params
hyperparams['X'] = self.simulation['X0']
#cretae GP
self.gp = dlimix_legacy.CGPbase(covar, ll)
#set data
self.gp.setY(self.simulation['Y'])
self.gp.setX(self.simulation['X0'])
self.gp.setParams(hyperparams)
pass
def _initParams_random(self):
"""
initialize the gp parameters randomly
"""
# gp hyper params
params = limix.CGPHyperParams()
if self.interaction:
params['covar'] = SP.concatenate(
[SP.randn(self.N * self.k + 1),
SP.ones(1),
SP.randn(1)])
else:
params['covar'] = SP.randn(self.N * self.k + 1)
params['lik'] = SP.randn(1)
return params
def _initParams_null(self, varX0X0, nois):
"""
initialize from null model
"""
X = 1e-3 * SP.randn(self.N, self.k)
a = SP.array([SP.sqrt(varX0X0)])
b = 1e-3 * SP.ones(1)
c = SP.array([SP.sqrt(nois)])
# gp hyper params
params = limix.CGPHyperParams()
if self.interaction:
params['covar'] = SP.concatenate(
[a, X.reshape(self.N * self.k, order='F'),
SP.ones(1), b])
else:
params['covar'] = SP.concatenate(
[a, X.reshape(self.N * self.k, order='F')])
params['lik'] = c
return params
def setUp(self):
SP.random.seed(1)
#1. simulate
self.settings = {'K': 5, 'N': 100, 'D': 80}
self.simulation = self.simulate()
N = self.settings['N']
K = self.settings['K']
D = self.settings['D']
#2. setup GP
K0 = SP.dot(self.simulation['S'], self.simulation['S'].T)
K0[:] = 0
covar1 = dlimix_legacy.CFixedCF(K0)
covar2 = dlimix_legacy.CCovLinearISO(K)
covar = dlimix_legacy.CSumCF()
covar.addCovariance(covar1)
covar.addCovariance(covar2)
ll = dlimix_legacy.CLikNormalIso()
#create hyperparm
covar_params = SP.array([0.0, 1.0])
lik_params = SP.array([0.1])
hyperparams = dlimix_legacy.CGPHyperParams()
hyperparams['covar'] = covar_params
hyperparams['lik'] = lik_params
hyperparams['X'] = self.simulation['X0']
#cretae GP
self.gp = dlimix_legacy.CGPbase(covar, ll)
#set data
self.gp.setY(self.simulation['Y'])
self.gp.setX(self.simulation['X0'])
self.gp.setParams(hyperparams)
pass
def train(self, rank=20, Kpop=True, LinearARD=False):
"""train panama module"""
if 0:
covar = limix_legacy.CCovLinearISO(rank)
ll = limix_legacy.CLikNormalIso()
X0 = sp.random.randn(self.N, rank)
X0 = PCA(self.Y, rank)[0]
X0 /= sp.sqrt(rank)
covar_params = sp.array([1.0])
lik_params = sp.array([1.0])
hyperparams = limix_legacy.CGPHyperParams()
hyperparams['covar'] = covar_params
hyperparams['lik'] = lik_params
hyperparams['X'] = X0
constrainU = limix_legacy.CGPHyperParams()
constrainL = limix_legacy.CGPHyperParams()
constrainU['covar'] = +5 * sp.ones_like(covar_params)
constrainL['covar'] = 0 * sp.ones_like(covar_params)
constrainU['lik'] = +5 * sp.ones_like(lik_params)
constrainL['lik'] = 0 * sp.ones_like(lik_params)
if 1:
covar = limix_legacy.CSumCF()
if LinearARD:
covar_1 = limix_legacy.CCovLinearARD(rank)
covar_params = []
for d in range(rank):
covar_params.append(1 / sp.sqrt(d + 2))
else:
covar_1 = limix_legacy.CCovLinearISO(rank)
covar_params = [1.0]
covar.addCovariance(covar_1)
for K in self.Ks:
covar.addCovariance(limix_legacy.CFixedCF(K))
covar_params.append(1.0)
ll = limix_legacy.CLikNormalIso()
X0 = PCA(self.Y, rank)[0]
X0 /= sp.sqrt(rank)
covar_params = sp.array(covar_params)
lik_params = sp.array([1.0])
hyperparams = limix_legacy.CGPHyperParams()
hyperparams['covar'] = covar_params
hyperparams['lik'] = lik_params
hyperparams['X'] = X0
constrainU = limix_legacy.CGPHyperParams()
constrainL = limix_legacy.CGPHyperParams()
constrainU['covar'] = +5 * sp.ones_like(covar_params)
constrainL['covar'] = -5 * sp.ones_like(covar_params)
constrainU['lik'] = +5 * sp.ones_like(lik_params)
gp = limix_legacy.CGPbase(covar, ll)
gp.setY(self.Y)
gp.setX(X0)
lml0 = gp.LML(hyperparams)
dlml0 = gp.LMLgrad(hyperparams)
gpopt = limix_legacy.CGPopt(gp)
gpopt.setOptBoundLower(constrainL)
gpopt.setOptBoundUpper(constrainU)
t1 = time.time()
gpopt.opt()
t2 = time.time()
#Kpanama
self.Xpanama = covar_1.getX()
if LinearARD:
self.Xpanama /= self.Xpanama.std(0)
self.Kpanama = covar_1.K()
# self.Kpanama/= self.Kpanama.diagonal().mean()
# Ktot
self.Ktot = covar_1.K()
for c_i in range(len(self.Ks)):
self.Ktot += covar.getCovariance(c_i + 1).K()
# self.Ktot/= self.Ktot.diagonal().mean()
#store variances
V = {}
if LinearARD:
V['LinearARD'] = covar_1.getParams()**2 * covar_1.getX().var(0)
else:
V['Kpanama'] = sp.array([covar_1.K().diagonal().mean()])
# if self.use_Kpop:
# V['Ks'] = sp.array([covar.getCovariance(c_i+1).K().diagonal().mean() for c_i in range(len(self.Ks))])
V['Ks'] = sp.array(
[covar.getCovariance(c_i + 1).K() for c_i in range(len(self.Ks))])
V['noise'] = gp.getParams()['lik']**2
self.varianceComps = V
# predictions
Ki = la.inv(ll.K() + covar.K())
self.Ypanama = sp.dot(covar_1.K(), sp.dot(Ki, self.Y))
self.LL = ll.K()