def test_gpkronprod(self):
# initialize
covar_c = linear.LinearCF(n_dimensions=self.n_latent)
covar_r = linear.LinearCF(n_dimensions=self.n_dimensions)
X0_c = SP.random.randn(self.n_tasks, self.n_latent)
lik = likelihood_base.GaussIsoLik()
gp = gp_kronprod.KronProdGP(covar_c=covar_c,
covar_r=covar_r,
likelihood=lik)
gp.setData(Y=self.Ykronprod['train'], X_r=self.X['train'])
hyperparams = {
'lik': SP.array([0.5]),
'X_c': X0_c,
'covar_r': SP.array([0.5]),
'covar_c': SP.array([0.5]),
'X_r': self.X['train']
}
# check predictions, likelihood and gradients
gp.predict(hyperparams, Xstar_r=self.X['test'], debugging=True)
gp._LML_covar(hyperparams, debugging=True)
gp._LMLgrad_covar(hyperparams, debugging=True)
gp._LMLgrad_lik(hyperparams, debugging=True)
gp._LMLgrad_x(hyperparams, debugging=True)
# optimize
hyperparams = {
'lik': SP.array([0.5]),
'X_c': X0_c,
'covar_r': SP.array([0.5]),
'covar_c': SP.array([0.5])
}
opts = {'gradcheck': True}
hyperparams_opt, lml_opt = optimize_base.opt_hyper(gp,
hyperparams,
opts=opts)
Kest = covar_c.K(hyperparams_opt['covar_c'])
# check predictions, likelihood and gradients
gp._invalidate_cache(
) # otherwise debugging parameters are not up to date!
gp.predict(hyperparams_opt, debugging=True, Xstar_r=self.X['test'])
gp._LML_covar(hyperparams_opt, debugging=True)
gp._LMLgrad_covar(hyperparams_opt, debugging=True)
gp._LMLgrad_lik(hyperparams_opt, debugging=True)
gp._LMLgrad_x(hyperparams_opt, debugging=True)
def test_gplvm(self):
covar = linear.LinearCF(n_dimensions=self.n_latent)
lik = likelihood_base.GaussIsoLik()
prior = priors.GaussianPrior(key='X', theta=SP.array([1.]))
gp = gplvm.GPLVM(covar=covar, likelihood=lik, prior=prior)
X0 = SP.random.randn(self.n_tasks, self.n_latent)
X0 = self.Xlatent
covar.X = X0
gp.setData(Y=self.Ylatent)
# gradient with respect to X
hyperparams = {
'covar': SP.array([0.5]),
'lik': SP.array([0.5]),
'X': X0
}
LML = gp.LML(hyperparams)
LMLgrad = gp.LMLgrad(hyperparams)
LMLgrad_x = SP.zeros((self.n_tasks, self.n_latent))
W = gp.get_covariances(hyperparams)['W']
for d in xrange(self.n_latent):
for n in xrange(self.n_tasks):
Knd_grad = covar.Kgrad_x(hyperparams['covar'], d, n)
LMLgrad_x[n, d] = 0.5 * (W * Knd_grad).sum()
LMLgrad_x += prior.LMLgrad(hyperparams)['X']
assert SP.allclose(
LMLgrad['X'],
LMLgrad_x), 'ouch, gradient with respect to X is wrong'
# optimize
opts = {'gradcheck': True}
hyperparams_opt, lml_opt = optimize_base.opt_hyper(gp,
hyperparams,
opts=opts)
Ktrue = SP.dot(self.Xlatent, self.Xlatent.T)
covar.X = hyperparams_opt['X']
Kest = covar.K(hyperparams_opt['covar'])
# gradient with respect to X
LML = gp.LML(hyperparams_opt)
LMLgrad = gp.LMLgrad(hyperparams_opt)
LMLgrad_x = SP.zeros((self.n_tasks, self.n_latent))
W = gp.get_covariances(hyperparams_opt)['W']
for d in xrange(self.n_latent):
for n in xrange(self.n_tasks):
Knd_grad = covar.Kgrad_x(hyperparams_opt['covar'], d, n)
LMLgrad_x[n, d] = 0.5 * (W * Knd_grad).sum()
LMLgrad_x += prior.LMLgrad(hyperparams_opt)['X']
assert SP.allclose(
LMLgrad['X'],
LMLgrad_x), 'ouch, gradient with respect to X is wrong'
def measure_runtime(env,N,D,n_reps=10,time_out=10000):
opts = {'messages':False}
out_dir = os.path.join(env['out_dir'],'simulations_runtime')
if not os.path.exists(out_dir):
os.makedirs(out_dir)
t_fast = SP.zeros(n_reps)
t_slow = SP.zeros(n_reps)
lml_fast = SP.zeros(n_reps)
lml_slow = SP.zeros(n_reps)
for i in range(n_reps):
# load data
var_signal = 0.5
data,RV = load_simulations(env,var_signal,N,D,i)
# initialize
covar_c = lowrank.LowRankCF(n_dimensions=RV['n_c'])
covar_r = linear.LinearCF(n_dimensions=RV['n_r'])
covar_s = lowrank.LowRankCF(n_dimensions=RV['n_sigma'])
covar_o = fixed.FixedCF(n_dimensions=RV['n_r'])
X = data.getX(standardized=False)
Y = data.getY(standardized=False).T
hyperparams,Ifilter,bounds = initialize.init('GPkronsum_LIN',Y.T,X,RV)
covar_r.X = X
covar_o.X = X
covar_o._K = SP.eye(RV['N'])
covar_s.X = hyperparams['X_s']
covar_c.X = hyperparams['X_c']
kgp_fast = gp_kronsum.KronSumGP(covar_r=covar_r,covar_c=covar_c,covar_s=covar_s,covar_o=covar_o)
kgp_fast.setData(Y=Y)
# measure time
signal.signal(signal.SIGALRM,handler)
signal.alarm(time_out)
try:
t_start = time.clock()
hyperparams_opt,lmltrain = opt.opt_hyper(kgp_fast,hyperparams,Ifilter=Ifilter,bounds=bounds,opts=opts)
t_stop = time.clock()
signal.alarm(0)
t_fast[i] = t_stop - t_start
lml_fast[i] = lmltrain
except Exception, e:
print e
t_slow += time_out
break
def sim_linear_kernel(X=None, N=None, n_dim=None, theta=None):
"""
simulate positive definite kernel
"""
if X == None:
X = SP.random.randn(N, n_dim)
else:
N = X.shape[0]
n_dim = X.shape[1]
if theta == None:
theta = SP.random.randn(1)
cf = linear.LinearCF(n_dim)
cf.X = X
K = cf.K(theta)
return K, X
def init_GPkronprod(Y, X_r, n_c):
"""
init parameters for kron(C + sigma I,R) + sigma*I
"""
# build linear kernel with the features
covar0_r = SP.array([0])
covar_r = linear.LinearCF(n_dimensions=X_r.shape[1])
covar_r.X = X_r
R = covar_r.K(covar0_r)
var_R = utils.getVariance(R)
cov = SP.cov(Y)
# split into likelihood and noise terms
ratio = SP.random.rand(3)
ratio /= ratio.sum()
lik0 = ratio[0] * SP.diag(cov).min()
covar0_c = ratio[1] * SP.diag(cov).min()
# remaining variance is assigned to latent factors
if n_c > 1:
X0_c = SP.zeros((Y.shape[0], n_c))
ratio = SP.random.rand(n_c)
ratio /= ratio.sum()
for i in range(n_c):
# split further up
X0_c[:, i] = SP.sign(SP.random.rand) * SP.sqrt(
ratio[i] * (SP.diag(cov) - lik0 - covar0_c))
else:
X0_c = SP.sign(
SP.random.rand) * SP.sqrt(SP.diag(cov) - lik0 - covar0_c)
X0_c = SP.reshape(X0_c, (X0_c.shape[0], n_c))
# check if variance of initial values match observed variance
assert SP.allclose(SP.diag(cov), (X0_c**2).sum(1) + lik0 +
covar0_c), 'ouch, something is wrong'
# bring in correct format and transform as neccessary
covar0_c = 0.5 * SP.log(SP.array([1. / var_R, covar0_c]))
lik0 = 0.5 * SP.log(SP.array([lik0]))
return X0_c, covar0_c, lik0, covar0_r
def test_linear(self):
theta = SP.array([SP.random.randn()**2])
theta_hat = SP.exp(2 * theta)
_K = SP.dot(self.Xtrain, self.Xtrain.T)
_Kcross = SP.dot(self.Xtrain, self.Xtest.T)
cov = linear.LinearCF(n_dimensions=self.n_dimensions)
cov.X = self.Xtrain
cov.Xcross = self.Xtest
K = cov.K(theta)
Kcross = cov.Kcross(theta)
Kgrad_x = cov.Kgrad_x(theta, 0)
Kgrad_theta = cov.Kgrad_theta(theta, 0)
assert SP.allclose(K,
theta_hat * _K), 'ouch covariance matrix is wrong'
assert SP.allclose(Kgrad_theta, 2 * theta_hat *
_K), 'ouch, gradient with respect to theta is wrong'
assert SP.allclose(Kcross, theta_hat *
_Kcross), 'ouch, cross covariance is wrong'
# gradient with respect to latent factors
# for each entry
for i in range(self.n_dimensions):
for j in range(self.n_train):
Xgrad = SP.zeros(self.Xtrain.shape)
Xgrad[j, i] = 1
_Kgrad_x = theta_hat * (SP.dot(Xgrad, self.Xtrain.T) +
SP.dot(self.Xtrain, Xgrad.T))
Kgrad_x = cov.Kgrad_x(theta, i, j)
assert SP.allclose(
Kgrad_x, _Kgrad_x
), 'ouch, gradient with respect to x is wrong for entry [%d,%d]' % (
i, j)
break
# save
fn_out = os.path.join(out_dir,'results_runtime_signal%03d_N%d_D%d.hdf5'%(var_signal*1E3,N,D))
f = h5py.File(fn_out,'w')
f['t_fast'] = t_fast
f['t_slow'] = t_slow
f['lml_fast'] = lml_fast
f['lml_slow'] = lml_slow
f.close()
for i in range(n_reps):
# initialize
data,RV = load_simulations(env,var_signal,N,D,i)
covar_c = lowrank.LowRankCF(n_dimensions=RV['n_c'])
covar_r = linear.LinearCF(n_dimensions=RV['n_r'])
covar_s = lowrank.LowRankCF(n_dimensions=RV['n_sigma'])
covar_o = fixed.FixedCF(n_dimensions=RV['n_r'])
X = data.getX(standardized=False)
Y = data.getY(standardized=False).T
hyperparams,Ifilter,bounds = initialize.init('GPkronsum_LIN',Y.T,X,RV)
covar_r.X = X
covar_o.X = X
covar_o._K = SP.eye(RV['N'])
covar_s.X = hyperparams['X_s']
covar_c.X = hyperparams['X_c']
kgp_slow = gp_kronsum_naive.KronSumGP(covar_r=covar_r,covar_c=covar_c,covar_s=covar_s,covar_o=covar_o)
kgp_slow.setData(Y=Y)
# measure time
signal.signal(signal.SIGALRM,handler)
def init_GPkronsum(Y, X_r, n_c, n_sigma):
"""
init parameters for kron(C + sigmaI,R) + kron(Sigma + sigmaI,Omega)
input:
Y task matrix
X_r feature matrxi
n_c number of hidden factors in C
n_sigma number of hidden factors in Sigma
"""
n_t, n_s = Y.shape
n_f = X_r.shape[1]
# build linear kernel with the features
covar_r = linear.LinearCF(n_dimensions=n_f)
covar_r.X = X_r
covar0_r = SP.array([0])
R = covar_r.K(covar0_r)
var_R = utils.getVariance(R)
# initialize hidden factors
X0_c = SP.zeros((n_t, n_c))
X0_sigma = SP.zeros((n_t, n_sigma))
# observed variance
var = Y.var(1)
var0 = SP.copy(var)
# assign parts of the variance to individual effects
ratio = SP.random.rand(3)
ratio /= ratio.sum()
covar0_c = ratio[0] * var.min()
covar0_sigma = ratio[1] * var.min()
# remaining variance is assigned to latent factors
var -= covar0_c
var -= covar0_sigma
for i in range(n_t):
signal = SP.random.rand() * var[i]
if n_c == 1:
X0_c[i] = SP.sign(SP.random.rand()) * SP.sqrt(signal)
else:
ratio = SP.random.rand(n_c)
ratio /= ratio.sum()
for j in range(n_c):
X0_c[i,
j] = SP.sign(SP.random.rand) * SP.sqrt(ratio[j] * signal)
if n_sigma == 1:
X0_sigma[i] = SP.sign(SP.random.rand()) * SP.sqrt(var[i] - signal)
else:
ratio = SP.random.rand(n_sigma)
ratio /= ratio.sum()
for j in range(n_sigma):
X0_sigma[i, j] = SP.sign(SP.random.rand) * SP.sqrt(
ratio[j] * (var[i] - signal))
# check if variance of initial values match observed variance
assert SP.allclose(var0, (X0_c**2).sum(1).flatten() +
(X0_sigma**2).sum(1).flatten() + covar0_c +
covar0_sigma), 'ouch, something is wrong'
# bring in correct format and transform as neccessary
covar0_c = 0.5 * SP.log([1. / var_R, covar0_c])
covar0_sigma = 0.5 * SP.log([1, covar0_sigma])
X0_c = SP.reshape(X0_c, (X0_c.shape[0], n_c))
X0_sigma = SP.reshape(X0_sigma, (X0_sigma.shape[0], n_sigma))
return X0_c, X0_sigma, covar0_c, covar0_sigma, covar0_r
X_scaler.fit(X_train)
X_train = X_scaler.transform(X_train)
X_test = X_scaler.transform(X_test)
Y_scaler = StandardScaler()
Y_scaler.fit(Y_train)
Y_train = Y_scaler.transform(Y_train)
for b in range(len(basis_num)):
pca = PCA(n_components = basis_num[b])
Y_train_hat = pca.fit_transform(Y_train)
B = pca.components_.T
hyperparams, Ifilter, bounds = initialize.init('MTGPR', Y_train_hat.T, X_train,{})
covar_c = composite.SumCF(n_dimensions = Y_train_hat.shape[0])
covar_c.append_covar(linear.LinearCF(n_dimensions = Y_train_hat.shape[0]))
covar_c.append_covar(se.SqExpCF(n_dimensions = Y_train_hat.shape[0]))
covar_c.append_covar(DiagIsoCF(n_dimensions = Y_train_hat.shape[0]))
covar_c.X = Y_train_hat.T
covar_r = composite.SumCF(n_dimensions = X_train.shape[1])
covar_r.append_covar(linear.LinearCF(n_dimensions = X_train.shape[1]))
covar_r.append_covar(se.SqExpCF(n_dimensions = X_train.shape[1]))
covar_r.append_covar(DiagIsoCF(n_dimensions = X_train.shape[1]))
covar_r.X = X_train
likelihood = lik.GaussIsoLik()
gp = sMTGPR.sMTGPR(covar_r = covar_r, covar_c = covar_c, likelihood = likelihood, basis = B)
gp.setData(Y = Y_train, Y_hat = Y_train_hat, X = X_train)
import core.priors.priors as prior
import core.util.initialize as initialize
import matplotlib.pylab as PLT
if __name__ == "__main__":
# settings
n_latent = 1
n_tasks = 10
n_train = 100
n_features = 100
# initialize covariance functions
covar_c = lowrank.LowRankCF(n_dimensions=n_latent)
covar_s = lowrank.LowRankCF(n_dimensions=n_latent)
covar_r = linear.LinearCF(n_dimensions=n_train)
covar_o = diag.DiagIsoCF(n_dimensions=n_train)
# true parameters
X_c = SP.random.randn(n_tasks, n_latent)
X_s = SP.random.randn(n_tasks, n_latent)
X_r = SP.random.randn(n_train, n_features) #/SP.sqrt(n_dimensions)
R = SP.dot(X_r, X_r.T)
C = SP.dot(X_c, X_c.T)
Sigma = SP.dot(X_s, X_s.T)
K = SP.kron(C, R) + SP.kron(Sigma, SP.eye(n_train))
SP.all(SP.linalg.eigvals(K) >= 0)
y = SP.random.multivariate_normal(SP.zeros(n_tasks * n_train), K)
Y = SP.reshape(y, (n_train, n_tasks), order='F')
# initialization parameters
if (method == 'sMT_GPTR'):
basis_num = [b,b,b]
noise_basis_num = [nb,nb,nb]
Y_train = partial_fold(Y_train, mode=0, shape = [Y_train.shape[0],
control_fmri_data.shape[1],control_fmri_data.shape[2],control_fmri_data.shape[3]])
hyperparams, Ifilter, bounds = initialize.init('Zero', Y_train, X_train,{})
covar_c = list()
covar_s = list()
covar_r = list()
covar_o = list()
for i in range(Y_train.ndim-1):
n_dim = Y_train.shape[0] * np.prod(basis_num) / basis_num[i]
covar_c.append(composite.SumCF(n_dimensions = n_dim))
covar_c[i].append_covar(linear.LinearCF(n_dimensions = n_dim))
covar_c[i].append_covar(se.SqExpCF(n_dimensions = n_dim))
covar_c[i].append_covar(DiagIsoCF(n_dimensions = n_dim))
n_dim = Y_train.shape[0] * np.prod(noise_basis_num) / noise_basis_num[i]
covar_s.append(composite.SumCF(n_dimensions = n_dim))
covar_s[i].append_covar(linear.LinearCF(n_dimensions = n_dim))
covar_s[i].append_covar(se.SqExpCF(n_dimensions = n_dim))
covar_s[i].append_covar(DiagIsoCF(n_dimensions = n_dim))
covar_r.append(composite.SumCF(n_dimensions = X_train.shape[1]))
covar_r[0].append_covar(linear.LinearCF(n_dimensions = X_train.shape[1]))
covar_r[0].append_covar(se.SqExpCF(n_dimensions = X_train.shape[1]))
covar_r[0].append_covar(DiagIsoCF(n_dimensions = X_train.shape[1]))
covar_r[0].X = X_train
covar_o.append(DiagIsoCF(n_dimensions = X_train.shape[1]))
covar_o[0].X = X_train
def test_gpbase(self):
covar = linear.LinearCF(n_dimensions=self.n_dimensions)
n_train = self.X['train'].shape[0]
theta = 1E-1
prior_cov = priors.GaussianPrior(key='covar', theta=SP.array([1.]))
prior_lik = priors.GaussianPrior(key='lik', theta=SP.array([1.]))
prior = priors.PriorList([prior_cov, prior_lik])
lik = likelihood_base.GaussIsoLik()
gp = gp_base.GP(covar_r=covar, likelihood=lik, prior=prior)
gp.setData(Y=self.Yuni['train'], X=self.X['train'])
# log likelihood and gradient derivation
hyperparams = {'covar': SP.array([0.5]), 'lik': SP.array([0.5])}
LML = gp.LML(hyperparams)
LMLgrad = gp.LMLgrad(hyperparams)
K = covar.K(hyperparams['covar']) + lik.K(hyperparams['lik'], n_train)
Kgrad_covar = covar.Kgrad_theta(hyperparams['covar'], 0)
Kgrad_lik = lik.Kgrad_theta(hyperparams['lik'], n_train, 0)
KinvY = LA.solve(K, self.Yuni['train'])
_LML = self.n_train / 2 * SP.log(2 * SP.pi) + 0.5 * SP.log(
LA.det(K)) + 0.5 * (self.Yuni['train'] *
KinvY).sum() + prior.LML(hyperparams)
LMLgrad_covar = 0.5 * SP.trace(LA.solve(
K, Kgrad_covar)) - 0.5 * SP.dot(KinvY.T, SP.dot(
Kgrad_covar, KinvY))
LMLgrad_covar += prior_cov.LMLgrad(hyperparams)['covar']
LMLgrad_lik = 0.5 * SP.trace(LA.solve(K, Kgrad_lik)) - 0.5 * SP.dot(
KinvY.T, SP.dot(Kgrad_lik, KinvY))
LMLgrad_lik += prior_lik.LMLgrad(hyperparams)['lik']
assert SP.allclose(
LML, _LML), 'ouch, marginal log likelihood does not match'
assert SP.allclose(
LMLgrad['covar'], LMLgrad_covar
), 'ouch, gradient with respect to theta does not match'
assert SP.allclose(
LMLgrad['lik'],
LMLgrad_lik), 'ouch, gradient with respect to theta does not match'
# predict
Ystar = gp.predict(hyperparams, self.X['test'])
Kstar = covar.Kcross(hyperparams['covar'])
_Ystar = SP.dot(Kstar.T, LA.solve(K, self.Yuni['train'])).flatten()
assert SP.allclose(Ystar, _Ystar), 'ouch, predictions, do not match'
# optimize
opts = {'gradcheck': True, 'messages': False}
hyperparams_opt, lml_opt = optimize_base.opt_hyper(gp,
hyperparams,
opts=opts)
# log likelihood and gradient derivation
LML = gp.LML(hyperparams_opt)
LMLgrad = gp.LMLgrad(hyperparams_opt)
K = covar.K(hyperparams_opt['covar']) + lik.K(hyperparams_opt['lik'],
n_train)
Kgrad_covar = covar.Kgrad_theta(hyperparams_opt['covar'], 0)
Kgrad_lik = lik.Kgrad_theta(hyperparams_opt['lik'], n_train, 0)
KinvY = LA.solve(K, self.Yuni['train'])
_LML = self.n_train / 2 * SP.log(2 * SP.pi) + 0.5 * SP.log(
LA.det(K)) + 0.5 * (self.Yuni['train'] *
KinvY).sum() + prior.LML(hyperparams_opt)
LMLgrad_covar = 0.5 * SP.trace(LA.solve(
K, Kgrad_covar)) - 0.5 * SP.dot(KinvY.T, SP.dot(
Kgrad_covar, KinvY))
LMLgrad_covar += prior_cov.LMLgrad(hyperparams_opt)['covar']
LMLgrad_lik = 0.5 * SP.trace(LA.solve(K, Kgrad_lik)) - 0.5 * SP.dot(
KinvY.T, SP.dot(Kgrad_lik, KinvY))
LMLgrad_lik += prior_lik.LMLgrad(hyperparams_opt)['lik']
assert SP.allclose(
LML, _LML), 'ouch, marginal log likelihood does not match'
assert SP.allclose(
LMLgrad['covar'], LMLgrad_covar
), 'ouch, gradient with respect to theta does not match'
assert SP.allclose(
LMLgrad['lik'],
LMLgrad_lik), 'ouch, gradient with respect to theta does not match'
# predict
Ystar = gp.predict(hyperparams_opt, self.X['test'])
Kstar = covar.Kcross(hyperparams_opt['covar'])
_Ystar = SP.dot(Kstar.T, LA.solve(K, self.Yuni['train'])).flatten()
assert SP.allclose(Ystar, _Ystar), 'ouch, predictions, do not match'
# Normalization
X_scaler = StandardScaler()
X_scaler.fit(X_train)
X_train = X_scaler.transform(X_train)
X_test = X_scaler.transform(X_test)
Y_scaler = StandardScaler()
Y_scaler.fit(Y_train)
Y_train = Y_scaler.transform(Y_train)
################################# GP_base Approach ########################
if (method == 'base' or method == 'all'):
for i in range(n_tasks):
hyperparams, Ifilter, bounds = initialize.init(
'GPbase_LIN', Y_train[:, i].T, X_train, None)
covariance = linear.LinearCF(n_dimensions=X_train.shape[0])
likelihood = lik.GaussIsoLik()
gp = gp_base.GP(covar=covariance, likelihood=likelihood)
gp.setData(Y=Y_train[:, i:i + 1], X_r=X_train)
# Training: optimize hyperparameters
hyperparams_opt, lml_opt = optimize_base.opt_hyper(
gp, hyperparams, bounds=bounds, Ifilter=Ifilter)
# Testing
results_base['Y_pred'][s, :, i], results_base['Y_pred_cov'][
s, :, i] = gp.predict(hyperparams_opt, Xstar_r=X_test)
results_base['s_n2'][s, i] = np.exp(2 * hyperparams_opt['lik'])
results_base['Y_pred'][s, :, :] = Y_scaler.inverse_transform(
results_base['Y_pred'][s, :, :])
results_base['Y_pred_cov'][
def run(methods, data, opts, f):
"""
run methods
"""
# load data
X_r = data.getX(standardized=opts['standardizedX'], maf=opts['maf'])
Y = data.getY(standardized=opts['standardizedY']).T
n_s, n_f = X_r.shape
n_t = Y.shape[1]
# indices for cross-validation
r = SP.random.permutation(n_s)
Icv = SP.floor(((SP.ones((n_s)) * opts['nfolds']) * r) / n_s)
if 'CV_GPbase_LIN' in methods:
print 'do cross-validation with GPbase'
t_start = time.time()
covariance = linear.LinearCF(n_dimensions=n_f)
likelihood = lik.GaussIsoLik()
gp = gp_base.GP(covar=covariance, likelihood=likelihood)
Ypred = SP.zeros(Y.shape)
YpredCV = SP.zeros(Y.shape)
lml_test = SP.zeros((n_t, opts['nfolds']))
for i in range(n_t):
for j in range(opts['nfolds']):
LG.info('Train Pheno %d' % i)
LG.info('Train Fold %d' % j)
Itrain = Icv != j
Itest = Icv == j
y = SP.reshape(Y[:, i], (n_s, 1))
cv_idx = (j + 1) % opts['nfolds']
RV = run_optimizer('GPbase_LIN',
gp,
opts=opts,
Y=y[Itrain],
X_r=X_r[Itrain],
Icv=Icv[Itrain],
cv_idx=cv_idx)
lml_test[i, j] = RV['lml_test']
Ypred[Itest, i] = gp.predict(RV['hyperparams_opt'], X_r[Itest])
YpredCV[Icv == cv_idx, i] = RV['Ypred']
lml_test = lml_test.sum(0)
t_stop = time.time()
r2 = (SP.corrcoef(Y.flatten(), Ypred.flatten())[0, 1])**2
print '... squared correlation coefficient: %.4f' % r2
RV = {
'Y': Y,
'Ypred': Ypred,
'r2': r2,
'time': t_stop - t_start,
'Icv': Icv,
'lml_test': lml_test,
'YpredCV': YpredCV
}
if f != None:
out = f.create_group('CV_GPbase_LIN')
utils.storeHashHDF5(out, RV)
if 'CV_GPpool_LIN' in methods:
print 'do cross-validation with GPpool'
t_start = time.time()
covar_c = linear.LinearCF(n_dimensions=1) # vector of 1s
covar_r = linear.LinearCF(n_dimensions=n_f)
likelihood = lik.GaussIsoLik()
gp = gp_kronprod.KronProdGP(covar_r=covar_r,
covar_c=covar_c,
likelihood=likelihood)
gp.setData(X_c=SP.ones((Y.shape[1], 1)))
Ypred = SP.zeros(Y.shape)
YpredCV = SP.zeros(Y.shape)
lml_test = SP.zeros(opts['nfolds'])
for j in range(opts['nfolds']):
LG.info('Train Fold %d' % j)
Itrain = Icv != j
Itest = Icv == j
cv_idx = (j + 1) % opts['nfolds']
RV = run_optimizer('GPpool_LIN',
gp,
opts=opts,
Y=Y[Itrain],
X_r=X_r[Itrain],
Icv=Icv[Itrain],
cv_idx=cv_idx)
Ypred[Itest] = gp.predict(RV['hyperparams_opt'], X_r[Itest])
YpredCV[Icv == cv_idx] = RV['Ypred']
lml_test[j] = RV['lml_test']
t_stop = time.time()
r2 = (SP.corrcoef(Y.flatten(), Ypred.flatten())[0, 1])**2
print '... squared correlation coefficient: %.4f' % r2
RV = {
'Y': Y,
'Ypred': Ypred,
'r2': r2,
'time': t_stop - t_start,
'Icv': Icv,
'lml_test': lml_test,
'YpredCV': YpredCV
}
if f != None:
out = f.create_group('CV_GPpool_LIN')
utils.storeHashHDF5(out, RV)
if 'CV_GPkronprod_LIN' in methods:
print 'do cross-validation with GPkronprod (linear kernel)'
t_start = time.time()
covar_c = lowrank.LowRankCF(n_dimensions=opts['n_c'])
covar_r = linear.LinearCF(n_dimensions=n_f)
likelihood = lik.GaussIsoLik()
Ypred = SP.zeros(Y.shape)
YpredCV = SP.zeros(Y.shape)
gp = gp_kronprod.KronProdGP(covar_r=covar_r,
covar_c=covar_c,
likelihood=likelihood)
lml_test = SP.zeros(opts['nfolds'])
for j in range(opts['nfolds']):
LG.info('Train Fold %d' % j)
Itrain = Icv != j
Itest = Icv == j
cv_idx = (j + 1) % opts['nfolds']
RV = run_optimizer('GPkronprod_LIN',
gp,
opts=opts,
Y=Y[Itrain],
X_r=X_r[Itrain],
Icv=Icv[Itrain],
cv_idx=cv_idx)
Ypred[Itest] = gp.predict(RV['hyperparams_opt'], X_r[Itest])
YpredCV[Icv == cv_idx] = RV['Ypred']
lml_test[j] = RV['lml_test']
t_stop = time.time()
r2 = (SP.corrcoef(Y.flatten(), Ypred.flatten())[0, 1])**2
print '... squared correlation coefficient: %.4f' % r2
RV = {
'Y': Y,
'Ypred': Ypred,
'r2': r2,
'time': t_stop - t_start,
'Icv': Icv,
'lml_test': lml_test,
'YpredCV': YpredCV
}
if f != None:
out = f.create_group('CV_GPkronprod_LIN')
utils.storeHashHDF5(out, RV)
if 'CV_GPkronsum_LIN' in methods:
print 'do cross-validation with GPkronsum (linear kernel)'
t_start = time.time()
Ypred = SP.zeros(Y.shape)
covar_c = lowrank.LowRankCF(n_dimensions=opts['n_c'])
covar_r = linear.LinearCF(n_dimensions=n_f)
covar_s = lowrank.LowRankCF(n_dimensions=opts['n_sigma'])
X_o = SP.zeros((Y.shape[0], 1))
covar_o = diag.DiagIsoCF(n_dimensions=1)
gp = gp_kronsum.KronSumGP(covar_r=covar_r,
covar_c=covar_c,
covar_s=covar_s,
covar_o=covar_o)
lml_test = SP.zeros(opts['nfolds'])
Ypred = SP.zeros(Y.shape)
YpredCV = SP.zeros(Y.shape)
for j in range(opts['nfolds']):
LG.info('Train Fold %d' % j)
Itrain = Icv != j
Itest = Icv == j
cv_idx = (j + 1) % opts['nfolds']
RV = run_optimizer('GPkronsum_LIN',
gp,
opts=opts,
Y=Y[Itrain],
X_r=X_r[Itrain],
Icv=Icv[Itrain],
cv_idx=cv_idx,
X_o=X_o[Itrain])
Ypred[Itest] = gp.predict(RV['hyperparams_opt'], X_r[Itest])
YpredCV[Icv == cv_idx] = RV['Ypred']
lml_test[j] = RV['lml_test']
t_stop = time.time()
r2 = (SP.corrcoef(Y.flatten(), Ypred.flatten())[0, 1])**2
print '... squared correlation coefficient: %.4f' % r2
RV = {
'Y': Y,
'Ypred': Ypred,
'r2': r2,
'time': t_stop - t_start,
'Icv': Icv,
'lml_test': lml_test,
'YpredCV': YpredCV
}
if f != None:
out = f.create_group('CV_GPkronsum_LIN')
utils.storeHashHDF5(out, RV)
return RV
