dict(model_solver=asgl_model, weight_calculator=asgl_wc_pca_d_7), dict(model_solver=asgl_model, weight_calculator=asgl_wc_pca_d_8), dict(model_solver=asgl_model, weight_calculator=asgl_wc_pca_d_9), dict(model_solver=asgl_model, weight_calculator=asgl_wc_pca_d_10) ] results = gf.automatic_simulator(data_param=data_param, model_selection_param=model_selection_param, model_param=model_param, data_generator=data_generator, n_repetitions=n_repetitions, folder=folder) ######################################################################################################################## results = af.simulation_results_to_tables(results=results, from_file=False, table_format='row_models') sorting = [ 'lasso', 'sgl', 'asgl_pca_d_0.1', 'asgl_pca_d_0.2', 'asgl_pca_d_0.3', 'asgl_pca_d_0.4', 'asgl_pca_d_0.5', 'asgl_pca_d_0.6', 'asgl_pca_d_0.7', 'asgl_pca_d_0.8', 'asgl_pca_d_0.9', 'asgl_pca_d_1' ] gc.boxplot_creator_by_metric_var_pct(results=results, interesting_metrics=['final_error'], figsize=(33, 10), sorting=sorting) ########################################################################################################################
model_param=model_param, n_repetitions=n_repetitions, folder=folder) ######################################################################################################################## """ Processing the results obtained """ route = 'D:/Documentos_2/GoogleDrive/Doctorado/Tesis/Codigo/Python/Quantile_regression/simulation_results/' fnamer2 = '2019-05-07--10-31-51--real_dataset--n=120--p=3734--standardized--cols--tau5.json' fnamer3 = '2019-05-11--00-03-53--real_dataset--n=120--p=3734--standardized--cols--tau3.json' fnamer4 = '2019-05-15--17-30-16--real_dataset--n=120--p=3734--standardized--cols--tau7.json' results5 = af.simulation_results_to_tables(results=route + fnamer2, from_file=True, table_format='row_models') results3 = af.simulation_results_to_tables(results=route + fnamer3, from_file=True, table_format='row_models') results7 = af.simulation_results_to_tables(results=route + fnamer4, from_file=True, table_format='row_models') gc.boxplot_creator_by_metric( results=results, interesting_metrics=['final_error', 'non_zero_pred_beta'], figsize=(25, 10), sorting=['lasso', 'sgl', 'asgl_pca_d', 'asgl_pls_d']) significance = gc.variables_probability_heatmap(