def predict(m, X, did_mf):
if not did_mf:
return m.predict(X)
else:
X_list = convert_x_list_to_array([X, X])
X_list_l = X_list[:X.shape[0]]
X_list_h = X_list[X.shape[0]:]
return m.predict(X_list_h)
def predict(self, x):
# Convert x_plot to its ndarray representation
X = convert_x_list_to_array([x, x])
X_l = X[:len(x)]
X_h = X[len(x):]
# Compute mean predictions and associated variance
lf_mean, lf_var = self.model.predict(X_l)
lf_std = np.sqrt(lf_var)
hf_mean, hf_var = self.model.predict(X_h)
hf_std = np.sqrt(hf_var)
return lf_mean, lf_std, hf_mean, hf_std
kernels = [GPy.kern.RBF(5), GPy.kern.RBF(5)]
lin_mf_kernel = emukit.multi_fidelity.kernels.LinearMultiFidelityKernel(
kernels)
gpy_lin_mf_model = GPyLinearMultiFidelityModel(X_train,
Y_train,
lin_mf_kernel,
n_fidelities=2)
gpy_lin_mf_model.mixed_noise.Gaussian_noise.fix(0)
gpy_lin_mf_model.mixed_noise.Gaussian_noise.fix(0)
gpy_lin_mf_model.optimize_restarts(num_restarts=5)
return gpy_lin_mf_model
log_lin_mf_model = log_linear_mfdgp(X_train, Y_train_log)
x_met = convert_x_list_to_array([x_val, x_val])
n = x_val.shape[0]
def test_log_likelihood(model, X_test, y_test):
""" Marginal log likelihood for GPy model on test data"""
_, test_log_likelihood, _ = model.inference_method.inference(
model.kern.rbf_1, X_test, model.likelihood.Gaussian_noise_1, y_test,
model.mean_function, model.Y_metadata)
return test_log_likelihood
lat_heldout_ll = []
for x in hf_val_lat:
x_met = convert_x_list_to_array([x, x])
held_log_lik = test_log_likelihood(log_lin_mf_model, x_met[:len(x)],
gpy_lin_mf_model.mixed_noise.Gaussian_noise_1.fix(0)
lin_mf_model = model = GPyMultiOutputWrapper(gpy_lin_mf_model,
2,
n_optimization_restarts=5,
verbose_optimization=False)
## Fit the model
lin_mf_model.optimize()
####
## Convert test points to appropriate representation
# print(x_plot)
X_plot = convert_x_list_to_array([x_plot, x_plot])
# print(X_plot)
X_plot_low = X_plot[:200]
X_plot_high = X_plot[200:]
## Compute mean and variance predictions
hf_mean_lin_mf_model, hf_var_lin_mf_model = lin_mf_model.predict(X_plot_high)
hf_std_lin_mf_model = np.sqrt(hf_var_lin_mf_model)
lf_mean_lin_mf_model, lf_var_lin_mf_model = lin_mf_model.predict(X_plot_low)
lf_std_lin_mf_model = np.sqrt(lf_var_lin_mf_model)
## Compare linear and nonlinear model fits
plt.figure(figsize=(12, 8))
# to DataFrame
hr_data_df = hr_data_ds.to_dataframe().dropna().reset_index()
lr_data_df = lr_data_ds.to_dataframe().dropna().reset_index()
x_train_lf = lr_data_df[['time', 'lat',
'lon']].values.reshape(-1,
3) # , 'elevation', 'slope'
y_train_lf = lr_data_df['tp'].values.reshape(-1, 1)
x_train_hf = hf_train_df[['time', 'lon',
'lat']].values.reshape(-1, 3) # 'z', 'slope'
y_train_hf = hf_train_df['tp'].values.reshape(-1, 1)
# Input data
X_train = convert_x_list_to_array([x_train_lf, x_train_hf])
Y_train = convert_x_list_to_array([y_train_lf, y_train_hf])
# Plot data
# , 'elevation', 'slope']
x_plot = hr_data_df[['time', 'lat', 'lon']].values.reshape(-1, 3)
X_plot = convert_x_list_to_array([x_plot, x_plot])
n = x_plot.shape[0]
def linear_mfdgp(X_train, Y_train):
kernels = [GPy.kern.RBF(3), GPy.kern.RBF(3)]
lin_mf_kernel = emukit.multi_fidelity.kernels.LinearMultiFidelityKernel(
kernels)
gpy_lin_mf_model = GPyLinearMultiFidelityModel(X_train,
Y_train,
def denvsrecmain(n_fid, x_dim, n):
#################
### Functions ###
#################
f_exact = test_funs.ackley
def f_name():
return f_exact(0)[1]
def f_m(x):
return f_exact(x)[0]
a = 4 * (np.random.rand(n_fid - 1) - .5)
b = 4 * (np.random.rand(n_fid - 1) - .5)
c = 4 * (np.random.rand(n_fid - 1) - .5)
d = np.random.randint(-4, 5, size=(n_fid - 1, x_dim + 1))
def f(x, fid):
if fid == n_fid - 1:
return f_m(x)
else:
x1_ptb = np.array([x_i[0] - d[fid][0] for x_i in x])[:, None]
return a[fid] * f(x, fid + 1) + b[fid] * x1_ptb + c[fid]
###############
### x_dim-D ###
###############
### Plotting data ###
x_min = [-5] * x_dim
x_max = [5] * x_dim
x_plot_grid = [
np.linspace(x_min[j], x_max[j], 50)[:, None] for j in range(x_dim)
]
x_plot_mesh = np.meshgrid(*x_plot_grid)
x_plot_list = np.hstack([layer.reshape(-1, 1) for layer in x_plot_mesh])
X_plot_mf = convert_x_list_to_array([x_plot_list] * n_fid)
X_plot_mf_list = X_plot_mf.reshape((n_fid, len(x_plot_list), x_dim + 1))
### Training data ###
x_train = [x_plot_list[::len(x_plot_list) // n_i] for n_i in n
] # Include possibility to insert training data of choice.
y_train = [f(x_train[j], j) for j in range(n_fid)]
X_train_mf, Y_train_mf = convert_xy_lists_to_arrays(x_train, y_train)
############################
### DENSE GP CALCULATION ###
############################
n_opt_restarts = 3
kernels_mf = []
for k in range(n_fid):
kernels_mf.append(GPy.kern.RBF(input_dim=x_dim))
lin_mf_kernel = emukit.multi_fidelity.kernels.LinearMultiFidelityKernel(
kernels_mf)
# print(lin_mf_kernel)
# print(lin_mf_kernel.kernels[0])
start_den = time.time()
# print(X_train_mf)
gpy_m_den_mf = GPyLinearMultiFidelityModel(X_train_mf,
Y_train_mf,
lin_mf_kernel,
n_fidelities=n_fid)
# print(gpy_m_den_mf)
### Fixing kernel parameters ###
for k in range(n_fid):
gpy_m_den_mf.mixed_noise.likelihoods_list[k].fix(0)
# print(gpy_m_den_mf)
m_den_mf = GPyMultiOutputWrapper(gpy_m_den_mf,
n_fid,
n_optimization_restarts=n_opt_restarts,
verbose_optimization=False)
end_den_1 = time.time()
# print('Dense MFGPR construction', end_den_1 - start_den)
### Dense HPO ###
m_den_mf_pre_HPO = m_den_mf
m_den_mf.optimize()
print(gpy_m_den_mf)
# print(gpy_m_den_mf.kern)
# print(lin_mf_kernel)
# print(lin_mf_kernel.kernels[0])
# print(X_train_mf)
# test = lin_mf_kernel.K(X=X_train_mf)
# print(test)
# print(lin_mf_kernel)
end_den_2 = time.time()
# print('Dense MFGPR construction + HPO', end_den_2 - start_den)
# print(gpy_m_den_mf)
### Prediction ###
# for j in range(n_fid):
# a = time.time()
# test = m_den_mf.predict(X_plot_mf_list[j])
# b = time.time()
# print(b - a)
mu_den_mf = [m_den_mf.predict(X_plot_mf_list[j])[0] for j in range(n_fid)]
# print(X_plot_mf_list)
# print(mu_den_mf)
# sigma_den_mf = [m_den_mf.predict(X_plot_mf_list[j])[1] for j in range(n_fid)]
#
# end_den_3 = time.time()
# print('Dense MFGPR construction + HPO + prediction', end_den_3 - start_den)
################################
### RECURSIVE GP CALCULATION ###
################################
start_rec = time.time()
# m_rec_mf = GPy.models.multiGPRegression(x_train, y_train, kernel=[GPy.kern.RBF(x_dim) for i in
# range(n_fid)]) # Improve kernel selection...?
end_rec_1 = time.time()
# print('Recursive MFGPR construction', end_rec_1 - start_rec)
# for k in range(n_fid): m_rec_mf.models[k]['Gaussian_noise.variance'].fix(0)
### Recursive HPO ###
# m_rec_mf_pre_HPO = m_rec_mf
# m_rec_mf.optimize_restarts(restarts=n_opt_restarts, verbose=False)
# for j in range(n_fid): print(m_rec_mf.models[j])
end_rec_2 = time.time()
# print('Recursive MFGPR construction + HPO', end_rec_2 - start_rec)
# for k in range(m): print(m_rec_mf.models[k])
### Prediction ###
# mu_rec_mf, sigma_rec_mf = m_rec_mf.predict(x_plot_list)
# print(mu_rec_mf)
#
# end_rec_3 = time.time()
# print('Recursive MFGPR construction + HPO + prediction', end_rec_3 - start_rec)
# times = [np.array([end_den_1, end_den_2, end_den_3]) - start_den, np.array([end_rec_1, end_rec_2, end_rec_3]) - start_rec]
times = [end_den_2 - start_den, end_rec_2 - start_rec]
return times, n_fid, x_dim
def test_convert_x_list_to_array():
x_list = [np.array([[1, 0], [2, 1]]), np.array([[3, 2], [4, 5]])]
x_array = convert_x_list_to_array(x_list)
expected_output = np.array([[1, 0, 0], [2, 1, 0], [3, 2, 1], [4, 5, 1]])
assert np.array_equal(x_array, expected_output)
def test_convert_x_list_to_array_fails_with_1d_input():
x_list = [np.array([0.0, 1.0]), np.array([2.0, 5.0])]
with pytest.raises(ValueError):
convert_x_list_to_array(x_list)
# gpy_m_den.mixed_noise.Gaussian_noise_2.fix(0)
m_den_mf = GPyMultiOutputWrapper(gpy_m_den_mf, m, n_optimization_restarts=4, verbose_optimization=True)
# m_den = GPyMultiOutputWrapper(gpy_m_den, 3, n_optimization_restarts=4, verbose_optimization=False)
m_den_mf_pre_HPO = m_den_mf
m_den_mf.optimize()
print(gpy_m_den_mf)
# m_den.optimize()
end2 = time.time()
print('dense + HPO', end2 - start)
# print(gpy_m_den)
# Prediction
X_plot_mf = convert_x_list_to_array([x_plot] * m)
# X_plot = convert_x_list_to_array([x_plot, x_plot, x_plot])
# X_plot_0 = X_plot[:len(x_plot)]
# X_plot_1 = X_plot[len(x_plot):2 * len(x_plot)]
# X_plot_2 = X_plot[2 * len(x_plot):]
X_plot_mf_list = X_plot_mf.reshape((m, len(x_plot), 2))
# print(X_plot_mf_list)
mu_den_mf = [m_den_mf.predict(X_plot_mf_list[j])[0] for j in range(m)]
sigma_den_mf = [m_den_mf.predict(X_plot_mf_list[j])[1] for j in range(m)]
# mu_den_0, sigma_den_0 = m_den.predict(X_plot_0)
# mu_den_1, sigma_den_1 = m_den.predict(X_plot_1)
# mu_den_2, sigma_den_2 = m_den.predict(X_plot_2)
## RECURSIVE GP CALCULATION WITH MF-GPY
##########
### dD ###
##########
### Plotting data ###
x_min = [-5] * x_dim
x_max = [5] * x_dim
x_plot_grid = [
np.linspace(x_min[j], x_max[j], 50)[:, None] for j in range(x_dim)
]
x_plot_mesh = np.meshgrid(*x_plot_grid)
x_plot_list = np.hstack([layer.reshape(-1, 1) for layer in x_plot_mesh])
X_plot_mf = convert_x_list_to_array([x_plot_list] * n_fid)
X_plot_mf_list = X_plot_mf.reshape((n_fid, len(x_plot_list), x_dim + 1))
### Training data ###
n = [5 * (n_fid - i) for i in range(n_fid)
] # Include possibility to insert training data of choice.
x_train = [x_plot_list[::len(x_plot_list) // n_i] for n_i in n
] # Include possibility to insert training data of choice.
y_train = [f(x_train[j], j) for j in range(n_fid)]
X_train_mf, Y_train_mf = convert_xy_lists_to_arrays(x_train, y_train)
############################
### DENSE GP CALCULATION ###
