eigX = [(eigh(M, eigvals_only=True))[::-1] for M in X]
eigt = [(eigh(M, eigvals_only=True))[::-1] for M in Xtest]
print "TIMER eval_features", time.clock() - ttt
# Observations
y = T.ravel()
alpha = []
covmat = []
for theta0 in [10.0**i
for i in sp.linspace(-2, 5, 7)]: # sp.linspace(1,1, N_models):
# Setup a Gaussian Process model
ttt = time.clock()
gp = GaussianProcess(corr='absolute_exponential',
theta0=sp.asarray([theta0]),
nugget=1e-3,
verbose=True,
low_memory=False)
# Fit to data using Maximum Likelihood Estimation of the parameters
gp.fit(eigX, y)
print "TIMER teach", time.clock() - ttt
ttt = time.clock()
# # Make the prediction on training set
# y_pred, MSE = gp.predict(eigX, eval_MSE=True)
# sigma = sp.sqrt(MSE)
# print('\n training set:')
# print('MAE: %5.2f kcal/mol' % sp.absolute(y_pred-y).mean(axis=0))
# print('RMSE: %5.2f kcal/mol' % sp.square(y_pred-y).mean(axis=0)**.5)
# Make the prediction on test set
print "TIMER load_data", time.clock() - ttt
test_indices_rec = []
teach_indices_rec = []
alpha_predicted = []
alpha_target = []
energy_target = []
energy_error = []
# --------------------------------------------
# Setup a Gaussian Process once and for all so that parameters do not change
# --------------------------------------------
gp = GaussianProcess(corr='absolute_exponential', theta0=sp.asarray([theta0]),
nugget=nugget, verbose=True, normalise=normalise, do_features_projection=False, low_memory=False, metric=metric)
# --------------------------------------------
# Loop over different training sets of the same size
# --------------------------------------------
for iteration in range(Ndatabases):
# --------------------------------------------
# Pick Ntest configurations randomly
# --------------------------------------------
test_indices = list(sp.random.randint(0, high=dataset[target_property].size, size=Ntest))
db_indices = randint_norepeat(0, exclude=test_indices, high=dataset[target_property].size, size=Nteach)
teach_indices_rec.append(db_indices)
X = dataset['X'][test_indices + db_indices]
T = dataset[target_property][test_indices + db_indices]
print "\n", "-"*60, "\n"
# in this case, only sorted eigenvalues of Coulomb matrix
ttt = time.clock()
eigX = [(eigh(M, eigvals_only=True))[::-1] for M in X]
eigt = [(eigh(M, eigvals_only=True))[::-1] for M in Xtest]
print "TIMER eval_features", time.clock() - ttt
# Observations
y = T.ravel()
alpha = []
covmat = []
for theta0 in sp.linspace(0.01, 1, N_models):
# Setup a Gaussian Process model
ttt = time.clock()
gp = GaussianProcess(corr='absolute_exponential',
theta0=sp.asarray([theta0]),
nugget=1e-2,
verbose=True)
# Fit to data using Maximum Likelihood Estimation of the parameters
gp.fit(eigX, y)
print "TIMER teach", time.clock() - ttt
# # Make the prediction on training set
# y_pred, MSE = gp.predict(eigX, eval_MSE=True)
# sigma = sp.sqrt(MSE)
# print('\n training set:')
# print('MAE: %5.2f kcal/mol'%sp.abs(y_pred-y).mean(axis=0))
# print('RMSE: %5.2f kcal/mol'%sp.square(y_pred-y).mean(axis=0)**.5)
# Make the prediction on test set
y_pred, MSE = gp.predict(eigt, eval_MSE=True)
sigma = sp.sqrt(MSE)
