#print("The number of layers were: ",myfmodel.n_layers_) #print("The output activation function was ",myfmodel.out_activation_) #Percentage errors in each test data sample perror = 100.0 * (np.abs(ytest - yhat) / ytest) #find maximum percentage error maxperror = np.max(100.0 * (np.abs(ytest - yhat) / ytest)) print("Maximum percet error = ", maxperror) #Plot the percentage errors #import matplotlib.pyplot as plt #from IPython import get_ipython #plt.plot(perror) #plt.show() #Plot the true and predicted Transmittance #get_ipython().run_line_magic('matplotlib', 'qt') plot_true_vs_pred(ytest, yhat, ytrain, ytrain_out, norm_lims, exp_str, j, "", "") export_csv = performance_out.to_csv( exp_str + "/" + r'Ynew_performances_1_2.csv', index=None, header=True) #Don't forget to add '.csv' at the end of the path pklfile = open(file=exp_str + "/train_learned_nh_" + str(num_hidden_neuron) + ".pkl", mode="rb") obj = pickle.load(pklfile) pklfile.close() #See the Regression metrics section of the user guide for further details. # #metrics.explained_variance_score(y_true, y_pred) Explained variance regression score function #metrics.mean_absolute_error(y_true, y_pred) Mean absolute error regression loss #metrics.mean_squared_error(y_true, y_pred[, …]) Mean squared error regression loss
#print("The number of layers were: ",myfmodel.n_layers_) #print("The output activation function was ",myfmodel.out_activation_) #Percentage errors in each test data sample perror = 100.0 * (np.abs(ytest - yhat) / ytest) #find maximum percentage error maxperror = np.max(100.0 * (np.abs(ytest - yhat) / ytest)) print("Maximum percet error = ", maxperror) #Plot the percentage errors #import matplotlib.pyplot as plt #from IPython import get_ipython #plt.plot(perror) #plt.show() #Plot the true and predicted Transmittance #get_ipython().run_line_magic('matplotlib', 'qt') plot_true_vs_pred(ytest, yhat, ytrain, ytrain_out, norm_lims, exp_str, j, which_conc_feature, "") export_csv = performance_out.to_csv( exp_str + "/" + r'Ynew_performances_1_1.csv', index=None, header=True) #Don't forget to add '.csv' at the end of the path pklfile = open(file=exp_str + "/train_learned_nh_" + str(num_hidden_neuron) + which_conc_feature + ".pkl", mode="rb") obj = pickle.load(pklfile) pklfile.close() #metrics section of the user guide for further details. # #metrics.explained_variance_score(y_true, y_pred) Explained variance regression score function #metrics.mean_absolute_error(y_true, y_pred) Mean absolute error regression loss #metrics.mean_squared_error(y_true, y_pred[, …]) Mean squared error regression loss