def run_estimation_iter(model, result_row, i_iter, config, valid_generator, test_generator, calibs, n_bins=N_BINS, tolerance=10): logger = logging.getLogger() logger.info('-' * 45) logger.info(f'iter : {i_iter}') flush(logger) iter_directory = os.path.join(model.results_path, f'iter_{i_iter}') os.makedirs(iter_directory, exist_ok=True) result_row['i'] = i_iter result_row['n_test_samples'] = test_generator.n_samples suffix = config.get_suffix() logger.info('Generate testing data') test_generator.reset() X_test, y_test, w_test = test_generator.generate( *config.TRUE, n_samples=config.N_TESTING_SAMPLES, no_grad=True) # PLOT SUMMARIES evaluate_summary_computer(model, X_test, y_test, w_test, n_bins=n_bins, prefix='', suffix=suffix, directory=iter_directory) # CALIBRATION config = calibrates(calibs, config, X_test, w_test) for name, value in config.CALIBRATED.items(): result_row[name + "_calib"] = value for name, value in config.CALIBRATED_ERROR.items(): result_row[name + "_calib_error"] = value logger.info('Set up NLL computer') compute_summaries = model.summary_computer(n_bins=n_bins) compute_nll = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config) # NLL PLOTS plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix) # MINIMIZE NLL logger.info('Prepare minuit minimizer') minimizer = get_minimizer(compute_nll, config.CALIBRATED, config.CALIBRATED_ERROR, tolerance=tolerance) result_row.update( evaluate_minuit(minimizer, config.TRUE, iter_directory, suffix=suffix)) return result_row.copy()
def run_estimation_iter(model, result_row, i_iter, config, valid_generator, test_generator, n_bins=N_BINS): logger = logging.getLogger() logger.info('-'*45) logger.info(f'iter : {i_iter}') flush(logger) iter_directory = os.path.join(model.results_path, f'iter_{i_iter}') os.makedirs(iter_directory, exist_ok=True) result_row['i'] = i_iter result_row['n_test_samples'] = config.N_TESTING_SAMPLES suffix = f'-mu={config.TRUE.mu:1.2f}_r={config.TRUE.r}_lambda={config.TRUE.lam}' logger.info('Generate testing data') test_generator.reset() X_test, y_test, w_test = test_generator.generate(*config.TRUE, n_samples=config.N_TESTING_SAMPLES, no_grad=True) # PLOT SUMMARIES evaluate_summary_computer(model, X_test, y_test, w_test, n_bins=n_bins, prefix='', suffix=suffix, directory=iter_directory) logger.info('Set up NLL computer') compute_summaries = model.summary_computer(n_bins=n_bins) compute_nll = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config) # NLL PLOTS plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix) # MINIMIZE NLL logger.info('Prepare minuit minimizer') minimizer = get_minimizer(compute_nll, config.CALIBRATED, config.CALIBRATED_ERROR) result_row.update(evaluate_minuit(minimizer, config.TRUE, iter_directory, suffix=suffix)) return result_row.copy()
def run_conditional_estimation(args, i_cv): logger = logging.getLogger() print_line() logger.info('Running iter n°{}'.format(i_cv)) print_line() result_row = {'i_cv': i_cv} # LOAD/GENERATE DATA logger.info('Set up data generator') config = Config() seed = SEED + i_cv * 5 train_generator = GeneratorTorch(seed, cuda=args.cuda) train_generator = TrainGenerator(train_generator, cuda=args.cuda) valid_generator = Generator(seed + 1) test_generator = Generator(seed + 2) # SET MODEL logger.info('Set up classifier') model = build_model(args, i_cv) os.makedirs(model.results_path, exist_ok=True) flush(logger) # TRAINING / LOADING train_or_load_neural_net(model, train_generator, retrain=args.retrain) # CHECK TRAINING logger.info('Generate validation data') X_valid, y_valid, w_valid = valid_generator.generate( *config.CALIBRATED, n_samples=config.N_VALIDATION_SAMPLES) result_row.update(evaluate_neural_net(model, prefix='valid')) result_row.update( evaluate_classifier(model, X_valid, y_valid, w_valid, prefix='valid')) # MEASUREMENT evaluate_summary_computer(model, X_valid, y_valid, w_valid, n_bins=N_BINS, prefix='valid_', suffix='') iter_results = [ run_conditional_estimation_iter(model, result_row, i, test_config, valid_generator, test_generator, n_bins=N_BINS) for i, test_config in enumerate(config.iter_test_config()) ] conditional_estimate = pd.concat(iter_results) conditional_estimate['i_cv'] = i_cv fname = os.path.join(model.results_path, "conditional_estimations.csv") conditional_estimate.to_csv(fname) logger.info('DONE') return conditional_estimate
def run(args, i_cv): logger = logging.getLogger() print_line() logger.info('Running iter n°{}'.format(i_cv)) print_line() result_row = {'i_cv': i_cv} # LOAD/GENERATE DATA logger.info('Set up data generator') config = Config() seed = SEED + i_cv * 5 train_generator = Generator(seed) valid_generator = Generator(seed + 1) # test_generator = Generator(seed+2) results = [] for n_train_samples in N_TRAIN_RANGE: result_row['n_train_samples'] = n_train_samples # SET MODEL logger.info('Set up classifier') model = build_model(args, i_cv) os.makedirs(model.results_path, exist_ok=True) flush(logger) # TRAINING / LOADING X_train, y_train, w_train = train_generator.generate( *config.CALIBRATED, n_samples=n_train_samples) model.fit(X_train, y_train, w_train) # CHECK TRAINING logger.info('Generate validation data') X_valid, y_valid, w_valid = valid_generator.generate( *config.CALIBRATED, n_samples=config.N_VALIDATION_SAMPLES) some_eval = evaluate_classifier(model, X_valid, y_valid, w_valid, prefix='valid', suffix=f'-{n_train_samples}') result_row['valid_auc'] = some_eval[f'valid_auc-{n_train_samples}'] result_row['valid_accuracy'] = some_eval[ f'valid_accuracy-{n_train_samples}'] N_BINS = 10 evaluate_summary_computer(model, X_valid, y_valid, w_valid, n_bins=N_BINS, prefix='valid_', suffix=f'{n_train_samples}') results.append(result_row.copy()) result_table = pd.DataFrame(results) return result_table
def run_iter(model, result_row, i_iter, config, valid_generator, test_generator, n_bins=10): logger = logging.getLogger() logger.info('-' * 45) logger.info(f'iter : {i_iter}') flush(logger) iter_directory = os.path.join(model.results_path, f'iter_{i_iter}') os.makedirs(iter_directory, exist_ok=True) result_row['i'] = i_iter result_row['n_test_samples'] = config.N_TESTING_SAMPLES suffix = f'-mu={config.TRUE.mu:1.2f}_rescale={config.TRUE.rescale}' logger.info('Generate testing data') test_generator.reset() X_test, y_test, w_test = test_generator.generate( *config.TRUE, n_samples=config.N_TESTING_SAMPLES) # PLOT SUMMARIES evaluate_summary_computer(model, X_test, y_test, w_test, n_bins=n_bins, prefix='', suffix=suffix, directory=iter_directory) logger.info('Set up NLL computer') compute_summaries = lambda X, w: model.compute_summaries( X, w, n_bins=n_bins) compute_nll = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config) # NLL PLOTS plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix) # MEASURE STAT/SYST VARIANCE logger.info('MEASURE STAT/SYST VARIANCE') conditional_results = make_conditional_estimation(compute_nll, config) fname = os.path.join(iter_directory, "no_nuisance.csv") conditional_estimate = pd.DataFrame(conditional_results) conditional_estimate['i'] = i_iter conditional_estimate.to_csv(fname) # MINIMIZE NLL logger.info('Prepare minuit minimizer') minimizer = get_minimizer(compute_nll, config.CALIBRATED, config.CALIBRATED_ERROR) result_row.update(evaluate_minuit(minimizer, config.TRUE)) return result_row.copy(), conditional_estimate
def run(args, i_cv): logger = logging.getLogger() print_line() logger.info('Running iter n°{}'.format(i_cv)) print_line() result_row = {'i_cv': i_cv} # LOAD/GENERATE DATA logger.info('Set up data generator') config = Config() seed = SEED + i_cv * 5 train_generator = Generator(seed) train_generator = TrainGenerator(param_generator, train_generator) valid_generator = Generator(seed+1) test_generator = Generator(seed+2) # SET MODEL logger.info('Set up classifier') model = build_model(args, i_cv) os.makedirs(model.results_path, exist_ok=True) flush(logger) # TRAINING / LOADING train_or_load_pivot(model, train_generator, config.N_TRAINING_SAMPLES*N_AUGMENT, retrain=args.retrain) # CHECK TRAINING logger.info('Generate validation data') X_valid, y_valid, w_valid = valid_generator.generate(*config.CALIBRATED, n_samples=config.N_VALIDATION_SAMPLES) result_row.update(evaluate_neural_net(model, prefix='valid')) result_row.update(evaluate_classifier(model, X_valid, y_valid, w_valid, prefix='valid')) # MEASUREMENT N_BINS = 10 evaluate_summary_computer(model, X_valid, y_valid, w_valid, n_bins=N_BINS, prefix='valid_', suffix='') iter_results = [run_iter(model, result_row, i, test_config, valid_generator, test_generator, n_bins=N_BINS) for i, test_config in enumerate(config.iter_test_config())] result_table = [e0 for e0, e1 in iter_results] result_table = pd.DataFrame(result_table) result_table.to_csv(os.path.join(model.results_path, 'estimations.csv')) logger.info('Plot params') param_names = config.PARAM_NAMES for name in param_names: plot_params(name, result_table, title=model.full_name, directory=model.results_path) conditional_estimate = pd.concat([e1 for e0, e1 in iter_results]) conditional_estimate['i_cv'] = i_cv fname = os.path.join(model.results_path, "conditional_estimations.csv") conditional_estimate.to_csv(fname) logger.info('DONE') return result_table, conditional_estimate
def run_estimation(args, i_cv): logger = logging.getLogger() print_line() logger.info('Running iter n°{}'.format(i_cv)) print_line() result_row = {'i_cv': i_cv} # LOAD/GENERATE DATA logger.info('Set up data generator') config = Config() seed = SEED + i_cv * 5 train_generator, valid_generator, test_generator = get_generators_torch(seed, cuda=args.cuda, GeneratorClass=GeneratorClass) train_generator = TrainGenerator(train_generator, cuda=args.cuda) valid_generator = GeneratorCPU(valid_generator) test_generator = GeneratorCPU(test_generator) # SET MODEL logger.info('Set up classifier') model = build_model(args, i_cv) os.makedirs(model.results_path, exist_ok=True) flush(logger) # TRAINING / LOADING train_or_load_neural_net(model, train_generator, retrain=args.retrain) # CHECK TRAINING logger.info('Generate validation data') X_valid, y_valid, w_valid = valid_generator.generate(*config.CALIBRATED, n_samples=config.N_VALIDATION_SAMPLES, no_grad=True) result_row.update(evaluate_neural_net(model, prefix='valid')) result_row.update(evaluate_classifier(model, X_valid, y_valid, w_valid, prefix='valid')) # MEASUREMENT calibs = {} calibs['tes'] = load_calib_tes(DATA_NAME, BENCHMARK_NAME) calibs['jes'] = load_calib_jes(DATA_NAME, BENCHMARK_NAME) calibs['les'] = load_calib_les(DATA_NAME, BENCHMARK_NAME) evaluate_summary_computer(model, X_valid, y_valid, w_valid, n_bins=N_BINS, prefix='valid_', suffix='') iter_results = [run_estimation_iter(model, result_row, i, test_config, valid_generator, test_generator, calibs, n_bins=N_BINS, tolerance=args.tolerance) for i, test_config in enumerate(config.iter_test_config())] result_table = pd.DataFrame(iter_results) result_table.to_csv(os.path.join(model.results_path, 'estimations.csv')) logger.info('Plot params') param_names = config.PARAM_NAMES for name in param_names: plot_params(name, result_table, title=model.full_name, directory=model.results_path) logger.info('DONE') return result_table
def run_iter(model, result_row, i_iter, config, valid_generator, test_generator, calib_rescale, n_bins=10): logger = logging.getLogger() logger.info('-'*45) logger.info(f'iter : {i_iter}') flush(logger) iter_directory = os.path.join(model.results_path, f'iter_{i_iter}') os.makedirs(iter_directory, exist_ok=True) result_row['i'] = i_iter result_row['n_test_samples'] = config.N_TESTING_SAMPLES suffix = f'-mu={config.TRUE.mu:1.2f}_rescale={config.TRUE.rescale}' logger.info('Generate testing data') test_generator.reset() X_test, y_test, w_test = test_generator.generate(*config.TRUE, n_samples=config.N_TESTING_SAMPLES) # PLOT SUMMARIES evaluate_summary_computer(model, X_test, y_test, w_test, n_bins=n_bins, prefix='', suffix=suffix, directory=iter_directory) # CALIBRATION rescale_mean, rescale_sigma = calib_rescale.predict(X_test, w_test) logger.info('rescale = {} =vs= {} +/- {}'.format(config.TRUE.rescale, rescale_mean, rescale_sigma) ) config.CALIBRATED = Parameter(rescale_mean, config.CALIBRATED.interest_parameters) config.CALIBRATED_ERROR = Parameter(rescale_sigma, config.CALIBRATED_ERROR.interest_parameters) for name, value in config.CALIBRATED.items(): result_row[name+"_calib"] = value for name, value in config.CALIBRATED_ERROR.items(): result_row[name+"_calib_error"] = value logger.info('Set up NLL computer') compute_summaries = ClassifierSummaryComputer(model, n_bins=n_bins) compute_nll = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config) # NLL PLOTS plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix) # MEASURE STAT/SYST VARIANCE logger.info('MEASURE STAT/SYST VARIANCE') conditional_results = make_conditional_estimation(compute_nll, config) fname = os.path.join(iter_directory, "no_nuisance.csv") conditional_estimate = pd.DataFrame(conditional_results) conditional_estimate['i'] = i_iter conditional_estimate.to_csv(fname) # MINIMIZE NLL logger.info('Prepare minuit minimizer') minimizer = get_minimizer(compute_nll, config.CALIBRATED, config.CALIBRATED_ERROR) result_row.update(evaluate_minuit(minimizer, config.TRUE)) return result_row.copy(), conditional_estimate
def run_estimation_iter(model, result_row, i_iter, config, valid_generator, test_generator, calib_r, calib_lam, n_bins=10): logger = logging.getLogger() logger.info('-'*45) logger.info(f'iter : {i_iter}') flush(logger) iter_directory = os.path.join(model.results_path, f'iter_{i_iter}') os.makedirs(iter_directory, exist_ok=True) result_row['i'] = i_iter result_row['n_test_samples'] = config.N_TESTING_SAMPLES suffix = f'-mu={config.TRUE.mu:1.2f}_r={config.TRUE.r}_lambda={config.TRUE.lam}' logger.info('Generate testing data') test_generator.reset() X_test, y_test, w_test = test_generator.generate(*config.TRUE, n_samples=config.N_TESTING_SAMPLES) # PLOT SUMMARIES evaluate_summary_computer(model, X_test, y_test, w_test, n_bins=n_bins, prefix='', suffix=suffix, directory=iter_directory) # CALIBRATION config = calibrates(calib_r, calib_lam, config, X_test, w_test) for name, value in config.FITTED.items(): result_row[name+"_fitted"] = value for name, value in config.FITTED_ERROR.items(): result_row[name+"_fitted_error"] = value logger.info('Set up NLL computer') compute_summaries = ClassifierSummaryComputer(model, n_bins=n_bins) compute_nll = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config) # NLL PLOTS plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix) # MINIMIZE NLL logger.info('Prepare minuit minimizer') minimizer = get_minimizer(compute_nll, config.FITTED, config.FITTED_ERROR) result_row.update(evaluate_minuit(minimizer, config.TRUE, iter_directory, suffix=suffix)) return result_row.copy()
def run(args, i_cv): logger = logging.getLogger() print_line() logger.info('Running iter n°{}'.format(i_cv)) print_line() result_row = {'i_cv': i_cv} result_table = [] # LOAD/GENERATE DATA logger.info('Set up data generator') pb_config = Config() seed = config.SEED + i_cv * 5 train_generator = Synthetic3DGeneratorTorch(seed) valid_generator = S3D2(seed + 1) test_generator = S3D2(seed + 2) # SET MODEL logger.info('Set up inferno') model = build_model(args, i_cv) flush(logger) # TRAINING / LOADING train_or_load_inferno(model, train_generator, retrain=args.retrain) # CHECK TRAINING result_row.update(evaluate_neural_net(model)) logger.info('Generate validation data') X_valid, y_valid, w_valid = valid_generator.generate( pb_config.CALIBRATED_R, pb_config.CALIBRATED_LAMBDA, pb_config.CALIBRATED_MU, n_samples=pb_config.N_VALIDATION_SAMPLES) # MEASUREMENT N_BINS = args.n_bins compute_summaries = model.compute_summaries for mu in pb_config.TRUE_MU_RANGE: true_params = Parameter(pb_config.TRUE.r, pb_config.TRUE.lam, mu) suffix = f'-mu={true_params.mu:1.2f}_r={true_params.r}_lambda={true_params.lam}' logger.info('Generate testing data') X_test, y_test, w_test = test_generator.generate( *true_params, n_samples=pb_config.N_TESTING_SAMPLES) # PLOT SUMMARIES evaluate_summary_computer(model, X_valid, y_valid, w_valid, X_test, w_test, n_bins=N_BINS, prefix='', suffix=suffix) logger.info('Set up NLL computer') compute_nll = S3D2NLL(compute_summaries, valid_generator, X_test, w_test) # NLL PLOTS plot_nll_around_min(compute_nll, true_params, model.path, suffix) # MINIMIZE NLL logger.info('Prepare minuit minimizer') minimizer = get_minimizer(compute_nll, pb_config.CALIBRATED, pb_config.CALIBRATED_ERROR) fmin, params = estimate(minimizer) result_row.update(evaluate_minuit(minimizer, fmin, params, true_params)) result_table.append(result_row.copy()) result_table = pd.DataFrame(result_table) logger.info('Plot params') param_names = pb_config.PARAM_NAMES for name in param_names: plot_params(name, result_table, title=model.full_name, directory=model.path) logger.info('DONE') return result_table