def simulate(plot=True): plotting = Plotting() preprocess = PreprocessData() preprocess.enable_normalisation_scaler = True preprocess.feature_range = [0, 1] window_size = 20 # 1. get data and apply normalisation sets_training, sets_test, sets_training_scaled, sets_test_scaled, training_dataset_names, test_dataset_names, maturities = preprocess.get_data( chunks_of=window_size) print("sets_training_scaled.shape", sets_training_scaled[0].shape) # plotting.plot_2d(sets_training_scaled[0][:, 0], "sets_training_scaled[0][:, 0]", save=False) # plotting.plot_2d(sets_test_scaled[0][:, 0], "test_feature_normalised_short_end", save=True) ae_params = { 'input_dim': ( window_size, sets_training_scaled[0].shape[1], ), # 10 x 56 'latent_dim': ( 2, 56, ), 'hidden_layers': ( 12 * 56, 4 * 56, ), 'leaky_relu': 0.1, 'loss': 'mse', 'last_activation': 'linear', 'batch_size': 20, 'epochs': 100, 'steps_per_epoch': 500, } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = AutoencoderWindows(ae_params) print("sets_training_scaled", sets_training_scaled[0].shape) autoencoder.train(sets_training_scaled, sets_test_scaled) autoencoder.save_model("ae_" + ae_params_hash) # autoencoder.load_model("ae_" + ae_params_hash) # 2: encode data using autoencoder sets_encoded_training = [] for set_training_scaled in sets_training_scaled: sets_encoded_training.append(autoencoder.encode(set_training_scaled)) sets_encoded_test = [] for set_test_scaled in sets_test_scaled: sets_encoded_test.append(autoencoder.encode(set_test_scaled)) print("sets_encoded_training", len(sets_encoded_training), sets_encoded_training[0].shape) print("sets_encoded_test", sets_encoded_test[0].shape) # 6: decode using autoencoder decoded_test = autoencoder.decode(sets_encoded_test[0]) print("decoded_test", decoded_test.shape) # 7: undo minimax, for now only the first simulation # decoded_generated_segments_first_sim = decoded_generated_segments[0] preprocess.enable_curve_smoothing = True simulated_smooth = preprocess.rescale_data( decoded_test, dataset_name=test_dataset_names[0]) # reconstruction error # reconstruction_error(sets_test_scaled[0], decoded_test) # error = reconstruction_error(np.array(sets_test[0]), simulated_smooth) # print("error:", error) smape_result_smooth = smape(simulated_smooth, np.array(sets_test[0]), over_curves=True) print(np.mean(smape_result_smooth), np.var(smape_result_smooth)) if plot: # plotting.plot_2d(sets_encoded_test[0], "test_feature_normalised_encoded_autoencoder_on_", save=True) # plotting.plot_some_curves("normalised_compare_ae_before_rescale", sets_test_scaled[0], decoded_test, # [25, 50, 75, 815], maturities) plotting.plot_some_curves("normalised_compare_ae", sets_test[0], simulated_smooth, [25, 50, 75, 815], maturities)
def simulate(latent_dim=2, plot=False, preprocess_type=None, model_type=None, force_training=True): plotting = Plotting() preprocess = PreprocessData(preprocess_type) window_size = None if model_type is AEModel.AE_WINDOWS: window_size = 10 # 1. get data and apply normalisation sets_training, sets_test, sets_training_scaled, sets_test_scaled, training_dataset_names, test_dataset_names, maturities = preprocess.get_data( chunks_of=window_size) all_training_scaled = np.vstack(sets_training_scaled) if model_type is AEModel.AAE: ae_params = { 'preprocess_type': preprocess_type. value, # only to make preprocess_type part of the hash 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': latent_dim, 'hidden_layers': ( 56, 40, 28, 12, 4, ), 'hidden_layers_discriminator': ( 2, 2, ), 'leaky_relu': 0.1, 'last_activation': 'linear', 'last_activation_discriminator': 'sigmoid', 'loss_generator': 'mean_squared_error', 'loss_discriminator': 'binary_crossentropy', 'batch_size': 20, 'epochs': 20000 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() # 2. train/load variational autoencoder autoencoder = AdversarialAutoencoder(ae_params, plot=False) elif model_type is AEModel.VAE: ae_params = { 'preprocess_type': preprocess_type. value, # only to make preprocess_type part of the hash 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': latent_dim, 'hidden_layers': ( 56, 40, 28, 12, 4, ), 'leaky_relu': 0.1, 'last_activation': 'linear', # sigmoid or linear 'loss': 'mean_squared_error', # binary_crossentropy or mean_square_error 'epsilon_std': 1.0, 'batch_size': 20, 'epochs': 100, 'steps_per_epoch': 500 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() # 2. train/load variational autoencoder autoencoder = VariationalAutoencoder(ae_params, plot=False) elif model_type is AEModel.AE: ae_params = { 'preprocess_type': preprocess_type. value, # only to make preprocess_type part of the hash 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': latent_dim, 'hidden_layers': ( 56, 40, 28, 12, 4, ), 'leaky_relu': 0.1, 'loss': 'mse', 'last_activation': 'linear', 'batch_size': 20, 'epochs': 100, 'steps_per_epoch': 500 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = Autoencoder(ae_params, plot=False) elif model_type is AEModel.PCA: ae_params = { 'preprocess_type': preprocess_type. value, # only to make preprocess_type part of the hash 'latent_dim': latent_dim } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = PCAModel(ae_params, plot=False) else: # model_type is AEModel.AE_WINDOWS: ae_params = { 'input_dim': ( window_size, sets_training_scaled[0].shape[1], ), # 10 x 56 'latent_dim': ( 2, 56, ), 'hidden_layers': ( 12 * 56, 4 * 56, ), 'leaky_relu': 0.1, 'loss': 'mse', 'last_activation': 'linear', 'batch_size': 20, 'epochs': 10, 'steps_per_epoch': 500, } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = AutoencoderWindows(ae_params, plot=False) if force_training: autoencoder.train(all_training_scaled, sets_test_scaled, "ae_" + ae_params_hash) else: autoencoder.load_else_train(all_training_scaled, sets_test_scaled, "ae_" + ae_params_hash) # 2: encode data using autoencoder sets_encoded_training = autoencoder.encode(sets_training_scaled) sets_encoded_test = autoencoder.encode(sets_test_scaled) # 6: decode using autoencoder decoded_test = autoencoder.decode(sets_encoded_test[0]) # 7: undo scaling # decoded_generated_segments_first_sim = decoded_generated_segments[0] simulated = preprocess.rescale_data(decoded_test, dataset_name=test_dataset_names[0]) preprocess.enable_curve_smoothing = True simulated_smooth = preprocess.rescale_data( decoded_test, dataset_name=test_dataset_names[0]) # reconstruction error # error = reconstruction_error(np.array(sets_test[0]), simulated) # error_smooth = reconstruction_error(np.array(sets_test[0]), simulated_smooth) smape_result = smape(simulated, np.array(sets_test[0]), over_curves=True) smape_result_smooth = smape(simulated_smooth, np.array(sets_test[0]), over_curves=True) print(np.mean(smape_result_smooth)) if plot and model_type is not AEModel.AE_WINDOWS: plotting.plot_2d(sets_encoded_test[0], preprocess_type.name + "_" + model_type.name + "_latent_space", sets_test_scaled[0].index.values, save=True) plotting.plot_some_curves( preprocess_type.name + "_" + model_type.name + "_in_vs_out", sets_test[0], simulated, [25, 50, 75, 815], maturities) # plotting.plot_some_curves("normalised_compare_ae", sets_test[0], sets_test_scaled[0], # [25, 50, 75, 815, 100, 600, 720, 740], maturities, plot_separate=True) preprocess.enable_curve_smoothing = False if model_type is AEModel.VAE: plotting.plot_grid_2dim(maturities, autoencoder.generator_model, preprocess_type.name + "_" + model_type.name + "_latent_grid", preprocess, test_dataset_names[0], n=6) elif model_type is AEModel.AAE: plotting.plot_grid_2dim(maturities, autoencoder.decoder, preprocess_type.name + "_" + model_type.name + "_latent_grid", preprocess, test_dataset_names[0], n=6) return smape_result_smooth
def simulate(): plotting = Plotting() preprocess_normalisation = PreprocessData() preprocess_normalisation.enable_normalisation_scaler = True preprocess_normalisation.feature_range = [0, 1] # preprocess_normalisation.enable_scaler = True # 1. get data and apply normalisation sets_training, sets_test, sets_training_scaled, sets_test_scaled, training_dataset_names, test_dataset_names, maturities = preprocess_normalisation.get_data( ) # plotting.plot_2d(sets_training_scaled[0][:, 0], "sets_training_scaled[0][:, 0]", save=False) # plotting.plot_2d(sets_test_scaled[0][:, 0], "test_feature_normalised_short_end", save=True) all_stacked = np.vstack((np.vstack(sets_training), np.vstack(sets_test))) all_stacked_scaled = np.vstack( (np.vstack(sets_training_scaled), np.vstack(sets_test_scaled))) all_training_scaled = np.vstack(sets_training_scaled) # print("all_stacked_scaled.shape", all_stacked_scaled.shape) # plotting.plot_2d(all_stacked[:, 0], "training and test data", save=False) # plotting.plot_2d(all_stacked_scaled[:, 0], "training and test data scaled", save=False) ae_params = { 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': 2, 'hidden_layers': (56, 40, 28, 12, 4, 2), 'leaky_relu': 0.1, 'loss': 'mse', 'last_activation': 'linear', 'batch_size': 20, 'epochs': 100, 'steps_per_epoch': 500 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = Autoencoder(ae_params) # autoencoder.train(all_stacked_scaled, sets_test_scaled) # autoencoder.train(sets_test_scaled[0], sets_test_scaled) # autoencoder.train(all_training_scaled, sets_test_scaled) # autoencoder.save_model("ae_" + ae_params_hash) autoencoder.load_model("ae_" + ae_params_hash) # 2: encode data using autoencoder sets_encoded_training = [] for set_training_scaled in sets_training_scaled: sets_encoded_training.append(autoencoder.encode(set_training_scaled)) sets_encoded_test = [] for set_test_scaled in sets_test_scaled: sets_encoded_test.append(autoencoder.encode(set_test_scaled)) plotting.plot_2d(sets_encoded_test[0], "test_feature_normalised_encoded_autoencoder_on_", save=True) # 6: decode using autoencoder decoded_test = autoencoder.decode(sets_encoded_test[0]) # 7: undo minimax, for now only the first simulation simulated = preprocess_normalisation.rescale_data( decoded_test, dataset_name=test_dataset_names[0]) plotting.plot_some_curves( "test_feature_normalised_compare_autoencoder_before_rescale", sets_test_scaled[0], decoded_test, [25, 50, 75, 815], maturities) # old: [25, 50, 75, 100, 600, 720, 740, 815] plotting.plot_some_curves( "test_feature_normalised_compare_autoencoder", sets_test[0], simulated, [25, 50, 75, 815], maturities) # old: [25, 50, 75, 100, 600, 720, 740, 815] # curve_smooth = [] # for curve in simulated: # print("curve.shape", curve.shape) # curve_smooth.append(savgol_filter(curve, 23, 5)) # window size 51, polynomial order 3 # curve_smooth = np.array(curve_smooth) print("reconstruction error BEFORE smoothing:") reconstruction_error(np.array(sets_test[0]), simulated) preprocess_normalisation.enable_curve_smoothing = True simulated = preprocess_normalisation.rescale_data( decoded_test, dataset_name=test_dataset_names[0]) plotting.plot_some_curves( "test_feature_normalised_compare_autoencoder", sets_test[0], simulated, [25, 50, 75, 815], maturities) # old: [25, 50, 75, 100, 600, 720, 740, 815] # plotting.plot_some_curves("test_feature_normalised_compare_normalisation", sets_test[0], sets_test_scaled[0], # [25, 50, 75, 815, 100, 600, 720, 740], maturities, plot_separate=True) # reconstruction error # reconstruction_error(sets_test_scaled[0], decoded_test) print("reconstruction error AFTER smoothing:") reconstruction_error(np.array(sets_test[0]), simulated)
def simulate(latent_dim=2, preprocess_type1=None, preprocess_type2=None, ae_model=None, gan_model=None, force_training=True, plot=False): preprocess1 = PreprocessData(preprocess_type1) preprocess2 = PreprocessData(preprocess_type2) # 1. get data and apply scaling sets_training, sets_test, sets_training_scaled, sets_test_scaled, training_dataset_names, test_dataset_names, maturities = preprocess1.get_data( ) if ae_model is AEModel.AAE: ae_params = { 'preprocess_type': preprocess_type1. value, # only to make preprocess_type part of the hash 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': latent_dim, 'hidden_layers': ( 56, 40, 28, 12, 4, ), 'hidden_layers_discriminator': ( 2, 2, ), 'leaky_relu': 0.1, 'last_activation': 'linear', 'last_activation_discriminator': 'sigmoid', 'loss_generator': 'mean_squared_error', 'loss_discriminator': 'binary_crossentropy', 'batch_size': 20, 'epochs': 20000 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = AdversarialAutoencoder(ae_params, plot=False) elif ae_model is AEModel.VAE: ae_params = { 'preprocess_type': preprocess_type1. value, # only to make preprocess_type part of the hash 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': latent_dim, 'hidden_layers': ( 56, 40, 28, 12, 4, ), 'leaky_relu': 0.1, 'last_activation': 'linear', # sigmoid or linear 'loss': 'mean_square_error', # binary_crossentropy or mean_square_error 'epsilon_std': 1.0, 'batch_size': 20, 'epochs': 100, 'steps_per_epoch': 500 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = VariationalAutoencoder(ae_params, plot=False) elif ae_model is AEModel.AE: ae_params = { 'preprocess_type': preprocess_type1. value, # only to make preprocess_type part of the hash 'input_dim': sets_training_scaled[0].shape[1], # 56 'latent_dim': latent_dim, 'hidden_layers': ( 56, 40, 28, 12, 4, ), 'leaky_relu': 0.1, 'loss': 'mse', 'last_activation': 'linear', 'batch_size': 20, 'epochs': 100, 'steps_per_epoch': 500 } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = Autoencoder(ae_params, plot=False) else: # elif ae_model is AEModel.PCA: ae_params = { 'preprocess_type': preprocess_type1. value, # only to make preprocess_type part of the hash 'latent_dim': latent_dim } ae_params_hash = hashlib.md5( json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = PCAModel(ae_params, plot=False) # 2. train/load autoencoder autoencoder.load_else_train(np.vstack(sets_training_scaled), sets_test_scaled, "ae_" + ae_params_hash) # 2: encode data using autoencoder sets_encoded_training = autoencoder.encode(sets_training_scaled) sets_encoded_test = autoencoder.encode(sets_test_scaled) # 3: log returns of encoded data sets_encoded_log_training = preprocess2.scale_data(sets_encoded_training, training_dataset_names, should_fit=True) sets_encoded_log_test = preprocess2.scale_data(sets_encoded_test, test_dataset_names, should_fit=True) num_z = 6 * 7 num_c = 6 * 7 num_o = 6 * 7 if gan_model is GANModel.WGAN: gan_params = { 'ae_params_hash': ae_params_hash, 'num_tenors': sets_encoded_log_training[0].shape[1], 'num_c': num_c, 'num_z': num_z, 'num_o': num_o, 'gen_model_type': 'standard', # conv 'dis_model_type': 'standard', # conv 'gen_layers': (4 * (6 * 7 * 2), ), # 4 * num_o * num_tenors 'dis_layers': (4 * (6 * 7), ), # 4 * num_o 'gen_last_activation': 'tanh', 'dis_last_activation': 'sigmoid', 'loss': 'binary_crossentropy', 'batch_size': 32, 'epochs': 10000, 'sample_interval': 1000 } gan_params_hash = hashlib.md5( json.dumps(gan_params, sort_keys=True).encode('utf-8')).hexdigest() gan = CWGANGP(gan_params, plot=False) else: if gan_model is GANModel.GAN_CONV: model_type = 'conv' else: # if gan_model is GANModel.GAN: model_type = 'standard' gan_params = { 'ae_params_hash': ae_params_hash, 'num_tenors': sets_encoded_log_training[0].shape[1], 'num_c': num_c, 'num_z': num_z, 'num_o': num_o, 'gen_model_type': model_type, # conv 'dis_model_type': model_type, # conv 'gen_layers': (4 * (6 * 7 * 2), ), # 4 * num_o * num_tenors 'dis_layers': (4 * (6 * 7), ), # 4 * num_o 'gen_last_activation': 'tanh', 'dis_last_activation': 'sigmoid', 'loss': 'binary_crossentropy', 'batch_size': 128, 'epochs': 20000 } gan_params_hash = hashlib.md5( json.dumps(gan_params, sort_keys=True).encode('utf-8')).hexdigest() gan = GAN(gan_params, plot=False) # try training on larger input and output if force_training: gan.train(sets_encoded_log_training, "gan_" + gan_params_hash) else: gan.load_else_train(sets_encoded_log_training, "gan_" + gan_params_hash) # 4: simulate on encoded log returns, conditioned on test dataset num_simulations = 100 num_repeats = 1 generated, _ = gan.generate(condition=sets_encoded_log_test[-1], condition_on_end=False, num_simulations=num_simulations, repeat=num_repeats) # insert the last real futures curve in order to do rescaling if preprocess_type2 is PreprocessType.LOG_RETURNS_OVER_TENORS: generated = np.insert(generated, 0, sets_encoded_log_test[-1].iloc[num_c], axis=1) # 5: undo scaling encoded_generated = preprocess2.rescale_data( generated, start_value=sets_encoded_test[-1][num_c], dataset_name=test_dataset_names[-1]) if preprocess_type2 is PreprocessType.LOG_RETURNS_OVER_TENORS: encoded_generated = encoded_generated[:, 1:] # remove first curve again # 6: decode using autoencoder decoded_generated_segments = autoencoder.decode(encoded_generated) # 7: undo scaling, this can be log-returns simulated = preprocess1.rescale_data(decoded_generated_segments, start_value=sets_test[-1].iloc[num_c], dataset_name=test_dataset_names[-1]) preprocess1.enable_curve_smoothing = True simulated_smooth = preprocess1.rescale_data( decoded_generated_segments, start_value=sets_test[-1].iloc[num_c], dataset_name=test_dataset_names[-1]) if preprocess_type2 is PreprocessType.LOG_RETURNS_OVER_TENORS: real = sets_test[-1].iloc[ num_c:num_c + num_o * num_repeats + 1] # `+1` because the log-returns also does +1 else: real = sets_test[-1].iloc[num_c:num_c + num_o * num_repeats + 1] print("simulated, real", simulated.shape, real.shape) smape_result = smape(simulated, real) smape_result_smooth = smape(simulated_smooth, real) print("smape_result_smooth mean and std:", np.mean(smape_result_smooth), np.std(smape_result_smooth)) if plot: plotting = Plotting() plotting.plot_3d("real", real, show_title=False) cov_log_returns = cov_log_returns_over_tenors(real) plotting.plot_3d_cov("gan_real_cov", cov_log_returns, show_title=False) for i in np.arange(1, 11): # name = '_' + preprocess_type1.name + '_' + preprocess_type2.name + '_' + str(latent_dim) + '_' + ae_model.name + '_'+ gan_model.name plotting.plot_3d("gan_simulated_" + str(i), simulated_smooth[i], maturities=maturities, time=real.index.values, show_title=False) smape_result = smape(simulated_smooth[i], real) print("simulated_smooth[i], real", simulated_smooth[i].shape, real.shape) print("simulate rates", i) print("smape:", smape_result) print("=============\n") cov_log_returns = cov_log_returns_over_tenors(simulated_smooth[i]) plotting.plot_3d_cov("gan_simulated_" + str(i) + "_cov", cov_log_returns, maturities=maturities, show_title=False) return smape_result_smooth
def simulate(): plotting = Plotting() preprocess_normalisation = PreprocessData() preprocess_logreturns = PreprocessData() preprocess_normalisation.enable_normalisation_scaler = True preprocess_logreturns.enable_log_returns = True # 1. get data and apply pre-processing sets_training, sets_test, sets_training_scaled, sets_test_scaled, training_dataset_names, test_dataset_names, maturities = preprocess_normalisation.get_data() ae_params = { 'preprocess_type': PreprocessType.NORMALISATION_OVER_TENORS.value, 'input_dim': (10, sets_training_scaled[0].shape[1],), # 56 'latent_dim': 2*56, 'hidden_layers': (12*56, 4*56, ), 'leaky_relu': 0.1, 'loss': 'mse', 'last_activation': 'linear', 'batch_size': 5, 'epochs': 5, 'steps_per_epoch': 500} ae_params_hash = hashlib.md5(json.dumps(ae_params, sort_keys=True).encode('utf-8')).hexdigest() autoencoder = Autoencoder(ae_params) # autoencoder.train(np.vstack(sets_training_scaled), sets_test_scaled) # autoencoder.save_model("ae_" + ae_params_hash) autoencoder.load_else_train(sets_training_scaled, sets_test_scaled, "ae_" + ae_params_hash) # 2: encode data using autoencoder sets_encoded_training = autoencoder.encode(sets_training_scaled) sets_encoded_test = autoencoder.encode(sets_test_scaled) print("sets_encoded_test", sets_encoded_test[0].shape) plotting.plot_2d(sets_encoded_test[0], "encoded test data with deep autoencoder", save=False) # 3: log returns of encoded data sets_encoded_log_training = preprocess_logreturns.scale_data(sets_encoded_training) sets_encoded_log_test = preprocess_logreturns.scale_data(sets_encoded_test) plotting.plot_2d(sets_encoded_log_test[0], "encoded test data with deep autoencoder, then log returns", save=False) num_c = 6*7 num_o = 6*7 gan_params = {'ae_params_hash': ae_params_hash, 'num_tenors': sets_encoded_log_training[0].shape[1], 'num_c': num_c, 'num_z': 6*7, 'num_o': num_o, 'gen_model_type': 'standard', # conv 'dis_model_type': 'standard', # conv 'gen_layers': (4*(6*7*2),), # 4 * num_o * num_tenors 'dis_layers': (4*(6*7),), # 4 * num_o 'gen_last_activation': 'tanh', 'dis_last_activation': 'sigmoid', 'loss': 'binary_crossentropy', 'batch_size': 128, 'epochs': 20000} gan_params_hash = hashlib.md5(json.dumps(gan_params, sort_keys=True).encode('utf-8')).hexdigest() gan = GAN(gan_params) # try training on larger input and output # gan.train(sets_encoded_log_training, sample_interval=200) # gan.save_model("gan_" + gan_params_hash) gan.load_model("gan_" + gan_params_hash) # COV TEST, TEMPORARY # for name, set in zip(training_dataset_names, sets_training): # print("name:", name) # set_cov_log_returns_over_features = cov_log_returns_over_features(set) # plotting.plot_3d_cov("covariance_time_series_" + name, set_cov_log_returns_over_features, show_title=False) # plotting.plot_3d("time_series_" + name, set, maturities) # END COV TEST. # 4: simulate on encoded log returns, conditioned on test dataset num_simulations = 10 num_repeats = 0 generated, _ = gan.generate(condition=sets_encoded_log_test[-1], condition_on_end=False, num_simulations=num_simulations, repeat=num_repeats) # insert the last real futures curve in order to do rescaling print("sets_encoded_log_test[-1][num_c] shape", sets_encoded_log_test[-1].iloc[num_c].shape) print("generated_segments.shape", generated.shape) generated = np.insert(generated, 0, sets_encoded_log_test[-1].iloc[num_c], axis=0) # 5: undo log-returns # todo: this start_value is actually one off! Error still persists... autoencoder causing the difference? encoded_generated = preprocess_logreturns.rescale_data(generated, start_value=sets_encoded_test[-1][num_c]) encoded_generated = encoded_generated[:, 1:] # remove first curve again # 6: decode using autoencoder decoded_generated_segments = autoencoder.decode(encoded_generated) # 7: undo minimax, for now only the first simulation simulated = preprocess_normalisation.rescale_data(decoded_generated_segments, dataset_name=test_dataset_names[-1]) preprocess_normalisation.enable_curve_smoothing = True simulated_smooth = preprocess_normalisation.rescale_data(decoded_generated_segments, dataset_name=test_dataset_names[-1]) real = np.array(sets_test[-1])[num_c:num_c + num_o] print("simulated, real", simulated.shape, real.shape) smape_result = smape(simulated, real) smape_result_smooth = smape(simulated_smooth, real) print("smape_result and smooth", smape_result, smape_result_smooth) print("smape_resul_smooth", smape_result_smooth)