def run_iter(model,
result_row,
i_iter,
i_cv,
args,
config,
test_generator,
n_bins=10):
logger = logging.getLogger()
iter_directory = os.path.join(model.results_path, f'iter_{i_iter}')
os.makedirs(iter_directory, exist_ok=True)
result_row['i'] = i_iter
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 = ClassifierSummaryComputer(model, n_bins=n_bins)
# compute_nll = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config)
compute_nll = NLL(X_test, w_test, i_cv, args, config=config, n_bins=n_bins)
# 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))
return result_row.copy()
def run_iter(compute_summaries, i_cv, i_iter, config, valid_generator,
test_generator, directory):
logger = logging.getLogger()
result_row = dict(i_cv=i_cv, i=i_iter)
iter_directory = os.path.join(directory, f'iter_{i_iter}')
os.makedirs(iter_directory, exist_ok=True)
logger.info(f"True Parameters = {config.TRUE}")
suffix = f'-mu={config.TRUE.mu:1.2f}_rescale={config.TRUE.rescale}'
X_test, y_test, w_test = test_generator.generate(
*config.TRUE, n_samples=config.N_TESTING_SAMPLES)
debug_label(y_test)
compute_nll = NLLComputer(compute_summaries,
valid_generator,
X_test,
w_test,
config=config)
plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix)
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
def run_estimation_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
config = calibrates(calib_rescale, 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 = 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)
# 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_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_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_iter(i_cv, i_iter, config, seed, directory):
logger = logging.getLogger()
result_row = dict(i_cv=i_cv, i=i_iter)
iter_directory = os.path.join(directory, f'iter_{i_iter}')
os.makedirs(iter_directory, exist_ok=True)
logger.info(f"True Parameters = {config.TRUE}")
suffix = f'-mu={config.TRUE.mu:1.2f}_rescale={config.TRUE.rescale}'
generator = Generator(seed) # test_generator
data, label = generator.sample_event(*config.TRUE,
size=config.N_TESTING_SAMPLES)
debug_label(label)
compute_nll = lambda rescale, mu: generator.nll(data, rescale, mu)
plot_nll_around_min(compute_nll, config.TRUE, iter_directory, suffix)
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
