def main(): df_train = pd.read_csv('data/train.csv') df_test = pd.read_csv('data/test.csv') oof_svc, preds_svc = train_nusvc(df_train, df_test) ut.plot_results(oof_svc, preds_svc, df_train, 'nusvc.png')
def task2(nmax, random_numbers, steps_count=20): results = [] # steps_count = 20 step = nmax / steps_count val_list = range(2, nmax, int(step)) for k in val_list: tmp = ut.std_dev(k, random_numbers) results.append(tmp) # prec_result = [ut.multi_dim_analytical(1)] * len(results) ut.plot_results(val_list, results, "std_dev Simulation", "log", "Number of samples", "Integral value")
def task3(nmax, random_numbers, dim): results = [] # steps_count = 20 val_list = range(1, dim) prec_results = [] for k in val_list: print("simul:" + str(ut.multi_dim_approach(nmax, random_numbers, k))) print("precise:" + str(ut.multi_dim_analytical(k))) tmp = ut.multi_dim_approach(nmax, random_numbers, k) results.append(tmp) prec_results.append(ut.multi_dim_analytical(k)) results = ut.np.asarray(results) prec_results = ut.np.asarray(prec_results) diff = results - prec_results ut.plot_results(val_list, diff, "multidim Simulation", "linear", "Dimensions", "Difference value")
print('Predicting on the test set using the trained RNN') t0 = time.time() test_predicted_time = regressor.predict(X_test) #predicted_time = sc.inverse_transform(predicted_time) print('Predicting on the test set complete. time_to_predict={:.2f} seconds'. format(time.time() - t0)) # In[29]: # Save predictions on test set test_prediction = pd.DataFrame(test_predicted_time) test_pred_filename = results_dir + '/' + 'test_prediction.csv' test_prediction.to_csv(test_pred_filename) print('Predictions on test set saved to {}'.format(test_pred_filename)) # In[31]: # Visualize predictions on test set test_res_plot_filename = results_dir + '/' + 'test_true_vs_pred' + '.png' utility.plot_results(true_test_time, test_prediction, 'True vs predicted time_to_earthquake on test set', test_res_plot_filename) # In[32]: # Compute error metrics on test set test_mse = mean_squared_error(true_test_time, test_predicted_time) test_rmse = test_mse**0.5 test_mae = mean_absolute_error(true_test_time, test_predicted_time) print( 'Error metrics on test set. test_mse: {:.4f}, test_rmse: {:.4f}, test_mae: {:.4f}' .format(test_mse, test_rmse, test_mae))
train_prediction.to_csv(train_pred_filename) train_prediction_orig = pd.DataFrame(train_predicted_time_orig) train_pred_orig_filename = params.results_dir + '/' + 'train_prediction_orig.csv' train_prediction_orig.to_csv(train_pred_orig_filename) print('Predictions on train set saved to {}, and {}'.format( train_pred_filename, train_pred_orig_filename)) # In[49]: # Visualize predictions on training set train_res_orig_plot_filename = params.results_dir + '/' + 'train_true_vs_pred_orig' + '.png' utility.plot_results( y_train, train_prediction_orig, 'True (orig) vs predicted time_to_earthquake on train set', train_res_orig_plot_filename) train_res_plot_filename = params.results_dir + '/' + 'train_true_vs_pred' + '.png' utility.plot_results(y_train, train_prediction, 'True vs predicted time_to_earthquake on train set', train_res_plot_filename) # In[50]: # Compute error metrics on training set N = params.ma_window train_mse, train_rmse, train_mae, train_r2 = utility.metrics( y_train, train_predicted_time_orig[N - 1:])
def main(): df_train = pd.read_csv('data/train.csv') df_test = pd.read_csv('data/test.csv') oof_logit, preds_logit = train_logit(df_train, df_test, pca=True) ut.plot_results(oof_logit, preds_logit, df_train, 'logit_'+str(c))