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)
valid_generator = Generator(seed + 1)
test_generator = Generator(seed + 2)
# SET MODEL
logger.info('Set up inferno model')
model = build_model(args, i_cv)
os.makedirs(model.results_path, exist_ok=True)
flush(logger)
# TRAINING / LOADING
train_or_load_inferno(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'))
evaluate_inferno(model, 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_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_inferno(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
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,
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(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)
valid_generator = Generator(seed + 1)
test_generator = Generator(seed + 2)
# SET MODEL
logger.info('Set up inferno model')
model = build_model(args, i_cv)
os.makedirs(model.results_path, exist_ok=True)
flush(logger)
# TRAINING / LOADING
train_or_load_inferno(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'))
evaluate_inferno(model, prefix='valid')
# MEASUREMENT
calib_rescale = load_calib_rescale()
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,
calib_rescale,
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(args, i_cv):
logger = logging.getLogger()
print_line()
logger.info('Running iter n°{}'.format(i_cv))
print_line()
# LOAD/GENERATE DATA
logger.info('Set up data generator')
config = Config()
seed = SEED + i_cv * 5
train_generator = GeneratorTorch(seed, 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_inferno(model, train_generator, retrain=args.retrain)
some_fisher = compute_fisher(
*compute_bins(model, valid_generator, config, n_bins=3),
config.TRUE.mu)
some_fisher_bis = compute_fisher(
*compute_bins(model, valid_generator, config, n_bins=3),
config.TRUE.mu)
assert some_fisher == some_fisher_bis, f"Fisher info should be deterministic but found : {some_fisher} =/= {some_fisher_bis}"
# MEASUREMENT
result_row = {'i_cv': i_cv}
results = []
for test_config in config.iter_test_config():
logger.info(
f"Running test set : {test_config.TRUE}, {test_config.N_TESTING_SAMPLES} samples"
)
for n_bins in range(1, 30):
result_row = {'i_cv': i_cv}
gamma_array, beta_array = compute_bins(model,
valid_generator,
test_config,
n_bins=n_bins)
fisher = compute_fisher(gamma_array, beta_array,
test_config.TRUE.mu)
result_row.update({
f'gamma_{i}': gamma
for i, gamma in enumerate(gamma_array, 1)
})
result_row.update(
{f'beta_{i}': beta
for i, beta in enumerate(beta_array, 1)})
result_row.update(test_config.TRUE.to_dict(prefix='true_'))
result_row['n_test_samples'] = test_config.N_TESTING_SAMPLES
result_row['fisher'] = fisher
result_row['n_bins'] = n_bins
results.append(result_row.copy())
results = pd.DataFrame(results)
print(results)
return results
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