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
y_pred, MSE = gp.predict(eigt, eval_MSE=True)
sigma = sp.sqrt(MSE)
print('\n test set:')
print('MAE: %5.2f kcal/mol' % sp.absolute(y_pred-Ttest.ravel()).mean(axis=0))
print('RMSE: %5.2f kcal/mol' %sp.square(y_pred-Ttest.ravel()).mean(axis=0)**.5)
print "TIMER predict", time.clock() - ttt
alpha.append(gp.alpha)
covmat.append(gp.K)
print r"\alpha STD: %f" % (sp.std(gp.alpha) / sp.mean(sp.absolute(gp.alpha)))
print "\n", "-"*60, "\n"
# P = dataset['P'][range(0,split)+range(split+1,5)].flatten()
# X = dataset['X'][P]
# T = dataset['T'][P]
alphas = teach_database_plusone(gp, eigX_db, y_db, eigX_t, y_t)
alpha_target.append(alphas)
# --------------------------------------------
# --------------------------------------------
# Second time don't include the test set and predict
# --------------------------------------------
ttt = time.clock()
gp.flush_data()
# Fit to data
gp.fit(eigX_db, y_db)
print "TIMER teach", time.clock() - ttt
beta = sp.dot(gp.inverse, gp.alpha)
y_pred, k = gp.predict(eigX_t, return_k=True)
# --------------------------------------------
# predict the alphas the K-1 * K-1 * k way
# --------------------------------------------
alpha_predicted.append(sp.dot(k, beta.flatten()))
energy_target.append(y_t)
energy_error.append(y_pred - y_t)
# check whether the ML itself is doing sensible things
print "ERROR = ", energy_error[-1]
print "ALPHA TRUE vs. PREDICTED:", alphas, alpha_predicted[-1]
with open('alpha_predictions.txt', 'a') as f:
f.write("n_test_molecules=%d n_databases=%d db_size=%d\n" % (Ntest, Ndatabases, Nteach))
output_data = sp.vstack((sp.array(alpha_target).flatten(), sp.array(alpha_predicted).flatten(), sp.array(energy_target).flatten(), sp.array(energy_error).flatten()))
sp.savetxt(f, output_data.T)
alpha_target.append(alphas)
gp.flush_data()
# --------------------------------------------
# --------------------------------------------
# Second time don't include the test set and predict
# --------------------------------------------
ttt = time.clock()
# Fit to data
gp.fit(eigX_db, y_db)
gp_level2.fit(eigX_db, gp.alpha.flatten())
print "TIMER teach", time.clock() - ttt
y_pred = gp.predict(eigX_t)
# --------------------------------------------
# predict the alphas
# --------------------------------------------
alpha_pred = gp_level2.predict(eigX_t)
alpha_predicted.append(alpha_pred.flatten())
energy_target.append(y_t)
energy_error.append(y_pred - y_t)
# check whether the level 1 ML itself is predicting the property correctly
print "ERROR = ", energy_error[-1]
print "ALPHA TRUE vs. PREDICTED:", alphas, alpha_predicted[-1]
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
y_pred, MSE = gp.predict(eigt, eval_MSE=True)
sigma = sp.sqrt(MSE)
print('\n test set:')
print('MAE: %5.2f kcal/mol' %
sp.absolute(y_pred - Ttest.ravel()).mean(axis=0))
print('RMSE: %5.2f kcal/mol' %
sp.square(y_pred - Ttest.ravel()).mean(axis=0)**.5)
print "TIMER predict", time.clock() - ttt
alpha.append(gp.alpha)
covmat.append(gp.K)
print r"\alpha STD: %f" % (sp.std(gp.alpha) /
sp.mean(sp.absolute(gp.alpha)))
print "\n", "-" * 60, "\n"
alpha_target.append(alphas)
gp.flush_data()
# --------------------------------------------
# --------------------------------------------
# Second time don't include the test set and predict
# --------------------------------------------
ttt = time.clock()
# Fit to data
gp.fit(eigX_db, y_db)
gp_level2.fit(eigX_db, gp.alpha.flatten())
print "TIMER teach", time.clock() - ttt
y_pred = gp.predict(eigX_t)
# --------------------------------------------
# predict the alphas
# --------------------------------------------
alpha_pred = gp_level2.predict(eigX_t)
alpha_predicted.append(alpha_pred.flatten())
energy_target.append(y_t)
energy_error.append(y_pred - y_t)
# check whether the level 1 ML itself is predicting the property correctly
print "ERROR = ", energy_error[-1]
print "ALPHA TRUE vs. PREDICTED:", alphas, alpha_predicted[-1]
