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 ###