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)
train_generator = TrainGenerator(param_generator, train_generator)
# SET MODEL
logger.info('Set up regressor')
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'))
evaluate_regressor(model, prefix='valid')
# MEASUREMENT
result_row['nfcn'] = NCALL
result_table = [
run_iter(model, result_row, i, test_config, valid_generator,
test_generator)
for i, test_config in enumerate(config.iter_test_config())
]
result_table = pd.DataFrame(result_table)
result_table.to_csv(os.path.join(model.results_path, 'results.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 main():
# BASIC SETUP
logger = set_logger()
args = GB_parse_args(main_description="Training launcher for Gradient boosting on S3D2 benchmark")
logger.info(args)
flush(logger)
# Config
config = Config()
config.TRUE = Parameter(r=0.1, lam=2.7, mu=0.1)
train_generator = Generator(SEED)
valid_generator = Generator(SEED+1)
test_generator = Generator(SEED+2)
X_test, y_test, w_test = test_generator.generate(*config.TRUE, n_samples=config.N_TESTING_SAMPLES)
# for nuisance in p(nuisance | data)
nuisance_param_sample = [param_generator().nuisance_parameters for _ in range(25)]
average_list = []
variance_list = []
all_results = []
for nuisance_params in nuisance_param_sample:
logger.info(f"nuisance_params = {nuisance_params}")
estimator_values = []
results = {name : value for name, value in zip(config.TRUE.nuisance_parameters_names, nuisance_params)}
for i_cv in range(N_ITER):
clf = build_model(args, i_cv)
parameters = Parameter(*nuisance_params, config.CALIBRATED.interest_parameters)
print(parameters)
n_samples = config.N_TRAINING_SAMPLES
X_train, y_train, w_train = train_generator.generate(*parameters, n_samples=n_samples)
logger.info(f"Training {clf.full_name}")
# TODO : is it OK to provide w_train to the classifier or useless ?
clf.fit(X_train, y_train, w_train)
compute_summaries = ClassifierSummaryComputer(clf, n_bins=10)
nll_computer = NLLComputer(compute_summaries, valid_generator, X_test, w_test, config=config)
compute_nll = lambda mu : nll_computer(*nuisance_params, mu)
minimizer = get_minimizer(compute_nll)
results.update(evaluate_minuit(minimizer, [config.TRUE.interest_parameters]))
all_results.append(results.copy())
# TODO : Add results to some csv
estimator_values.append(results['mu'])
average_list.append(np.mean(estimator_values))
variance_list.append(np.var(estimator_values))
logger.info(f"average_list {average_list}")
logger.info(f"variance_list {variance_list}")
v_stat = np.mean(variance_list)
v_syst = np.var(average_list)
v_total = v_stat + v_syst
logger.info(f"V_stat = {v_stat}")
logger.info(f"V_syst = {v_syst}")
logger.info(f"V_total = {v_total}")
def main():
# BASIC SETUP
logger = set_logger()
args = REG_parse_args(
main_description="Training launcher for Regressor on S3D2 benchmark")
logger.info(args)
flush(logger)
# Setup model
logger.info("Setup model")
model = build_model(args, 0)
os.makedirs(model.results_directory, exist_ok=True)
# Setup data
logger.info("Setup data")
config = Config()
config_table = evaluate_config(config)
config_table.to_csv(
os.path.join(model.results_directory, 'config_table.csv'))
seed = SEED + 99999
train_generator = TrainGenerator(param_generator, Generator(seed))
valid_generator = Generator(seed + 1)
test_generator = Generator(seed + 2)
i_cv = 0
result_row = {'i_cv': i_cv}
# TRAINING / LOADING
train_or_load_neural_net(model, train_generator, retrain=args.retrain)
# CHECK TRAINING
result_row.update(evaluate_neural_net(model, prefix='valid'))
evaluate_regressor(model, prefix='valid')
print_line()
result_table = [
run_iter(model, result_row, i, test_config, valid_generator,
test_generator)
for i, test_config in enumerate(config.iter_test_config())
]
result_table = pd.DataFrame(result_table)
result_table.to_csv(os.path.join(model.results_directory, 'results.csv'))
logger.info('Plot params')
param_names = [CALIB_PARAM_NAME]
for name in param_names:
plot_params(name,
result_table,
title=model.full_name,
directory=model.results_directory)
logger.info('DONE')
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 = 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
calib_r = load_calib_r(DATA_NAME, BENCHMARK_NAME)
calib_lam = load_calib_lam(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, calib_r, calib_lam, n_bins=N_BINS)
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 main():
# BASIC SETUP
logger = set_logger()
args = REG_parse_args(
main_description="Training launcher for Regressor on S3D2 benchmark")
logger.info(args)
flush(logger)
# INFO
args.net = AR5R5E(n_in=3, n_out=2, n_extra=2)
args.optimizer = get_optimizer(args)
model = get_model(args, Regressor)
model.set_info(DATA_NAME, BENCHMARK_NAME, -1)
pb_config = S3D2Config()
# RUN
results = [run(args, i_cv) for i_cv in range(N_ITER)]
results = pd.concat(results, ignore_index=True)
results.to_csv(os.path.join(model.results_directory, 'results.csv'))
# EVALUATION
eval_table = evaluate_estimator(pb_config.INTEREST_PARAM_NAME, results)
print_line()
print_line()
print(eval_table)
print_line()
print_line()
eval_table.to_csv(os.path.join(model.results_directory, 'evaluation.csv'))
gather_images(model.results_directory)
def run(args, i_cv):
logger = logging.getLogger()
print_line()
logger.info('Running iter n°{}'.format(i_cv))
print_line()
directory = os.path.join(DIRECTORY, f'cv_{i_cv}')
os.makedirs(directory, exist_ok=True)
config = S3D2Config()
seed = SEED + i_cv * 5
test_seed = seed + 2
result_table = [
run_iter(i_cv, i, test_config, test_seed, directory)
for i, test_config in enumerate(config.iter_test_config())
]
result_table = pd.DataFrame(result_table)
result_table.to_csv(os.path.join(directory, 'estimations.csv'))
logger.info('Plot params')
param_names = config.PARAM_NAMES
for name in param_names:
plot_params(name,
result_table,
title='Likelihood fit',
directory=directory)
return result_table
def run(args, i_cv):
logger = logging.getLogger()
print_line()
logger.info('Running iter n°{}'.format(i_cv))
print_line()
directory = os.path.join(DIRECTORY, f'cv_{i_cv}')
os.makedirs(directory, exist_ok=True)
config = Config()
seed = SEED + i_cv * 5
train_generator = Generator(seed)
valid_generator = Generator(seed+1)
test_generator = Generator(seed+2)
N_BINS = 10
X_train, y_train, w_train = train_generator.generate(*config.CALIBRATED, n_samples=config.N_TRAINING_SAMPLES)
compute_summaries = HistogramSummaryComputer(n_bins=N_BINS).fit(X_train)
result_table = [run_iter(compute_summaries, i_cv, i, test_config, valid_generator, test_generator, directory) for i, test_config in enumerate(config.iter_test_config())]
result_table = pd.DataFrame(result_table)
result_table.to_csv(os.path.join(directory, 'results.csv'))
logger.info('Plot params')
param_names = config.PARAM_NAMES
for name in param_names:
plot_params(name, result_table, title='Likelihood fit', directory=directory)
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 = Generator(seed)
# valid_generator = Generator(seed+1)
test_generator = Generator(seed+2)
# SET MODEL
# logger.info('Set up classifier')
model = build_model(args, i_cv)
# flush(logger)
# TRAINING / LOADING
# train_or_load_classifier(model, train_generator, config.CALIBRATED, config.N_TRAINING_SAMPLES, 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_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='')
result_table = [run_iter(model, result_row, i, i_cv, args, test_config, test_generator, n_bins=N_BINS)
for i, test_config in enumerate(config.iter_test_config())]
result_table = pd.DataFrame(result_table)
result_table.to_csv(os.path.join(model.results_path, 'results.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.path)
logger.info('DONE')
return result_table
def main():
logger = set_logger()
logger.info("Hello world !")
os.makedirs(DIRECTORY, exist_ok=True)
set_plot_config()
args = None
config = S3D2Config()
results = [run(args, i_cv) for i_cv in range(N_ITER)]
results = pd.concat(results, ignore_index=True)
results.to_csv(os.path.join(DIRECTORY, 'results.csv'))
# EVALUATION
eval_table = evaluate_estimator(config.TRUE.interest_parameters_names,
results)
print_line()
print_line()
print(eval_table)
print_line()
print_line()
eval_table.to_csv(os.path.join(DIRECTORY, 'evaluation.csv'))
gather_images(DIRECTORY)
def param_generator():
pb_config = S3D2Config()
# r = np.random.normal(pb_config.CALIBRATED_R, pb_config.CALIBRATED_R_ERROR)
# lam = -1
# while lam <= 0:
# lam = np.random.normal(pb_config.CALIBRATED_LAMBDA, pb_config.CALIBRATED_LAMBDA_ERROR)
r = pb_config.CALIBRATED_R
lam = pb_config.CALIBRATED_LAMBDA
mu_min = min(pb_config.TRUE_MU_RANGE)
mu_max = max(pb_config.TRUE_MU_RANGE)
mu_range = mu_max - mu_min
mu_min = max(0.0, mu_min - mu_range / 10)
mu_max = min(1.0, mu_max + mu_range / 10)
mu = np.random.uniform(0, 1)
return Parameter(
r,
lam,
mu,
)
def likelihood_fit():
print("Hello world !")
set_plot_config()
config = S3D2Config()
DATA_N_SAMPLES = 80_000
result_table = []
for mu in config.TRUE_MU_RANGE[1:]:
result_row = {}
config.TRUE_MU = mu
generator = S3D2(SEED)
data, label = generator.sample_event(config.TRUE.r, config.TRUE.lam, config.TRUE_MU, size=DATA_N_SAMPLES)
n_sig = np.sum(label==1)
n_bkg = np.sum(label==0)
print(f"nb of signal = {n_sig}")
print(f"nb of backgrounds = {n_bkg}")
compute_nll = lambda r, lam, mu : generator.nll(data, r, lam, mu)
print('Prepare minuit minimizer')
minimizer = get_minimizer(compute_nll, config)
fmin, params = estimate(minimizer)
params_truth = [config.TRUE_R, config.TRUE_LAMBDA, config.TRUE_MU]
my_print_params(params, params_truth)
register_params(params, params_truth, result_row)
result_row['is_mingrad_valid'] = minimizer.migrad_ok()
result_row.update(fmin)
result_table.append(result_row.copy())
result_table = pd.DataFrame(result_table)
result_table.to_csv(os.path.join(DIRECTORY, 'results.csv'))
print('Plot params')
param_names = config.PARAM_NAMES
for name in param_names:
my_plot_params(name, 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}
result_table = []
# LOAD/GENERATE DATA
logger.info('Set up data generator')
pb_config = S3D2Config()
seed = config.SEED + i_cv * 5
train_generator = S3D2(seed)
valid_generator = S3D2(seed + 1)
test_generator = S3D2(seed + 2)
# SET MODEL
logger.info('Set up rergessor')
args.net = AR5R5E(n_in=3, n_out=2, n_extra=2)
args.optimizer = get_optimizer(args)
model = get_model(args, Regressor)
model.set_info(BENCHMARK_NAME, i_cv)
model.param_generator = param_generator
flush(logger)
# TRAINING / LOADING
if not args.retrain:
try:
logger.info('loading from {}'.format(model.model_path))
model.load(model.model_path)
except Exception as e:
logger.warning(e)
args.retrain = True
if args.retrain:
logger.info('Training {}'.format(model.get_name()))
model.fit(train_generator)
logger.info('Training DONE')
# SAVE MODEL
save_model(model)
# CHECK TRAINING
logger.info('Plot losses')
plot_REG_losses(model)
plot_REG_log_mse(model)
result_row['loss'] = model.losses[-1]
result_row['mse_loss'] = model.mse_losses[-1]
# MEASUREMENT
for mu in pb_config.TRUE_MU_RANGE:
pb_config.TRUE_MU = mu
logger.info('Generate testing data')
test_generator.reset()
X_test, y_test, w_test = test_generator.generate(
# pb_config.TRUE_R,
# pb_config.TRUE_LAMBDA,
pb_config.CALIBRATED_R,
pb_config.CALIBRATED_LAMBDA,
pb_config.TRUE_MU,
n_samples=pb_config.N_TESTING_SAMPLES)
p_test = np.array(
(pb_config.CALIBRATED_R, pb_config.CALIBRATED_LAMBDA))
pred, sigma = model.predict(X_test, w_test, p_test)
name = pb_config.INTEREST_PARAM_NAME
result_row[name] = pred
result_row[name + _ERROR] = sigma
result_row[name + _TRUTH] = pb_config.TRUE_MU
logger.info('{} =vs= {} +/- {}'.format(pb_config.TRUE_MU, pred, sigma))
result_table.append(result_row.copy())
result_table = pd.DataFrame(result_table)
logger.info('Plot params')
name = pb_config.INTEREST_PARAM_NAME
plot_params(name,
result_table,
title=model.full_name,
directory=model.results_path)
logger.info('DONE')
return result_table
def explore():
print("Hello master !")
set_plot_config()
config = S3D2Config()
N_SAMPLES = 10_000
R_MIN = -0.3
R_MAX = 0.3
LAM_MIN = 2
LAM_MAX = 4
MU_MIN = 0.0
MU_MAX = 1.0
generator = S3D2(SEED)
X, label = generator.sample_event(config.TRUE.r, config.TRUE.lam, config.TRUE.mu, size=N_SAMPLES)
n_sig = np.sum(label==1)
n_bkg = np.sum(label==0)
print(f"nb of signal = {n_sig}")
print(f"nb of backgrounds = {n_bkg}")
df = pd.DataFrame(X, columns=["x1","x2","x3"])
df['label'] = label
g = sns.PairGrid(df, vars=["x1","x2","x3"], hue='label')
g = g.map_upper(sns.scatterplot)
g = g.map_diag(sns.kdeplot)
g = g.map_lower(sns.kdeplot, n_levels=6)
g = g.add_legend()
# g = g.map_offdiag(sns.kdeplot, n_levels=6)
g.savefig(os.path.join(DIRECTORY, 'pairgrid.png'))
plt.clf()
nll = generator.nll(X, config.TRUE.r, config.TRUE.lam, config.TRUE.mu)
print(f"NLL = {nll}")
R_RANGE = np.linspace(R_MIN, R_MAX, 30)
nll = [generator.nll(X, r, config.TRUE.lam, config.TRUE.mu) for r in R_RANGE]
min_nll = R_RANGE[np.argmin(nll)]
plt.plot(R_RANGE, nll, label="nll(r)")
plt.axvline(config.TRUE.r, c="orange", label="true r")
plt.axvline(min_nll, c="red", label="min nll")
plt.xlabel("r")
plt.ylabel("NLL")
plt.title("NLL according to r param")
plt.legend()
plt.savefig(os.path.join(DIRECTORY, 'NLL_r.png'))
plt.clf()
LAM_RANGE = np.linspace(LAM_MIN, LAM_MAX, 30)
nll = [generator.nll(X, config.TRUE.r, lam, config.TRUE.mu) for lam in LAM_RANGE]
min_nll = LAM_RANGE[np.argmin(nll)]
plt.plot(LAM_RANGE, nll, label="nll(lam)")
plt.axvline(config.TRUE.lam, c="orange", label="true lam")
plt.axvline(min_nll, c="red", label="min nll")
plt.xlabel("$\lambda$")
plt.ylabel("NLL")
plt.title("NLL according to $\lambda$ param")
plt.legend()
plt.savefig(os.path.join(DIRECTORY, 'NLL_lambda.png'))
plt.clf()
MU_RANGE = np.linspace(MU_MIN, MU_MAX, 30)
nll = [generator.nll(X, config.TRUE.r, config.TRUE.lam, mu) for mu in MU_RANGE]
min_nll = MU_RANGE[np.argmin(nll)]
plt.plot(MU_RANGE, nll, label="nll(mu)")
plt.axvline(config.TRUE.mu, c="orange", label="true mu")
plt.axvline(min_nll, c="red", label="min nll")
plt.xlabel("$\mu$")
plt.ylabel("NLL")
plt.title("NLL according to $\mu$ param")
plt.legend()
plt.savefig(os.path.join(DIRECTORY, 'NLL_mu.png'))
plt.clf()
def main():
print("Hello world !")
set_plot_config()
config = S3D2Config()
DATA_N_SAMPLES = 8_000
R_MIN = -0.3
R_MAX = 0.3
LAM_MIN = 2
LAM_MAX = 4
MU_MIN = 0.1
MU_MAX = 0.3
R_N_SAMPLES = 101
LAM_N_SAMPLES = 102
MU_N_SAMPLES = 103
prior_r = stats.uniform(loc=R_MIN, scale=R_MAX-R_MIN)
prior_lam = stats.uniform(loc=LAM_MIN, scale=LAM_MAX-LAM_MIN)
prior_mu = stats.uniform(loc=MU_MIN, scale=MU_MAX-MU_MIN)
r_grid = np.linspace(R_MIN, R_MAX, R_N_SAMPLES)
lam_grid = np.linspace(LAM_MIN, LAM_MAX, LAM_N_SAMPLES)
mu_grid = np.linspace(MU_MIN, MU_MAX, MU_N_SAMPLES)
data_generator = S3D2(SEED)
data, label = data_generator.sample_event(config.TRUE.r, config.TRUE.lam, config.TRUE.mu, size=DATA_N_SAMPLES)
n_sig = np.sum(label==1)
n_bkg = np.sum(label==0)
print(f"nb of signal = {n_sig}")
print(f"nb of backgrounds = {n_bkg}")
shape = (R_N_SAMPLES, LAM_N_SAMPLES, MU_N_SAMPLES)
n_elements = np.prod(shape)
print(f"3D grid has {n_elements} elements")
log_likelihood = np.zeros(shape)
log_prior_proba = np.zeros(shape)
for i, j, k in tqdm(itertools.product(range(R_N_SAMPLES), range(LAM_N_SAMPLES), range(MU_N_SAMPLES)), total=n_elements):
log_likelihood[i, j, k] = data_generator.log_proba_density(data, r_grid[i], lam_grid[j], mu_grid[k]).sum()
log_prior_proba[i, j, k] = prior_r.logpdf(r_grid[i]) \
+ prior_lam.logpdf(lam_grid[j]) \
+ prior_mu.logpdf(mu_grid[k])
element_min = (log_likelihood + log_prior_proba).min()
print("min element = ", element_min)
posterior_r_lam_mu = softmax(log_likelihood + log_prior_proba)
n_zeros = (posterior_r_lam_mu == 0).sum()
n_elements = np.prod(posterior_r_lam_mu.shape)
print()
print(f"number of zeros in posterior = {n_zeros}/{n_elements} ({n_zeros/n_elements*100:2.3f} %)")
marginal_r = posterior_r_lam_mu.sum(axis=2).sum(axis=1)
marginal_lam = posterior_r_lam_mu.sum(axis=2).sum(axis=0)
marginal_mu = posterior_r_lam_mu.sum(axis=1).sum(axis=0)
marginal_r_lam = posterior_r_lam_mu.sum(axis=2)
assert marginal_r.shape == r_grid.shape, "sum along the wrong axis for marginal r"
assert marginal_lam.shape == lam_grid.shape, "sum along the wrong axis for marginal lam"
assert marginal_mu.shape == mu_grid.shape, "sum along the wrong axis for marginal mu"
assert marginal_r_lam.shape == (R_N_SAMPLES, LAM_N_SAMPLES), "sum along the wrong axis for marginal (r, lam)"
n_zeros = (marginal_r == 0).sum()
n_elements = np.prod(marginal_r.shape)
print(f"number of zeros in marginal r = {n_zeros}/{n_elements} ({n_zeros/n_elements*100:2.3f} %)")
n_zeros = (marginal_lam == 0).sum()
n_elements = np.prod(marginal_lam.shape)
print(f"number of zeros in marginal lam = {n_zeros}/{n_elements} ({n_zeros/n_elements*100:2.3f} %)")
n_zeros = (marginal_mu == 0).sum()
n_elements = np.prod(marginal_mu.shape)
print(f"number of zeros in marginal mu = {n_zeros}/{n_elements} ({n_zeros/n_elements*100:2.3f} %)")
n_zeros = (marginal_r_lam == 0).sum()
n_elements = np.prod(marginal_r_lam.shape)
print(f"number of zeros in marginal r_lam = {n_zeros}/{n_elements} ({n_zeros/n_elements*100:2.3f} %)")
posterior_mu = np.divide(posterior_r_lam_mu, marginal_r_lam.reshape(R_N_SAMPLES, LAM_N_SAMPLES, 1),
out=np.zeros_like(posterior_r_lam_mu), where=(posterior_r_lam_mu!=0))
print("probability densities should sum to one")
# TODO : posterior_mu sum to SOME_N_SAMPLES. is it ok ?
# TODO : with new division policy posterior_mu/ALPHA_N sums to 1-zero_ration in marginal_y
# ... It does not look good
print(np.sum(posterior_mu)/n_elements, np.sum(posterior_r_lam_mu), np.sum(marginal_r), np.sum(marginal_lam))
print(np.sum(marginal_r_lam))
print()
print("True mu value =", config.TRUE.mu)
sig_ratio = n_sig/DATA_N_SAMPLES
print("Sig ratio =", sig_ratio)
expect_mu = expectancy(mu_grid, marginal_mu)
print("E[mu|x] =", expect_mu)
full_var = variance(mu_grid, marginal_mu)
print("Var[mu|x] =", full_var)
std_mu = np.sqrt(full_var)
print("sqrt(Var[mu|x]) =", std_mu)
print("argmax_mu p(mu|x) =", mu_grid[np.argmax(marginal_mu)])
i_max, j_max, k_max = np.unravel_index(np.argmax(log_likelihood), log_likelihood.shape)
assert np.max(log_likelihood) == log_likelihood[i_max, j_max, k_max], "max and argmax should point to the same value"
print("argmax_r_lam_mu logp(x|r, lam, mu) =", r_grid[i_max], lam_grid[j_max], mu_grid[k_max])
stat_err = stat_uncertainty(mu_grid, posterior_mu, marginal_r_lam)
print("stat_uncertainty=", stat_err)
stat_err = stat_uncertainty2(mu_grid, posterior_mu, marginal_r_lam)
print("stat_uncertainty=", stat_err)
stat_err = stat_uncertainty3(mu_grid, posterior_mu, marginal_r_lam)
print("stat_uncertainty=", stat_err)
print("syst_uncertainty=", full_var - stat_err)
syst_err = syst_uncertainty(mu_grid, posterior_mu, marginal_r_lam, marginal_mu)
print("syst_uncertainty=", syst_err)
syst_err = syst_uncertainty2(mu_grid, posterior_mu, marginal_r_lam)
print("syst_uncertainty=", syst_err)
syst_err = syst_uncertainty3(mu_grid, posterior_mu, marginal_r_lam)
print("syst_uncertainty=", syst_err)
print()
print("check marginals")
print("mu ", marginal_mu.min(), marginal_mu.max())
print("lam ", marginal_lam.min(), marginal_lam.max())
print("r ", marginal_r.min(), marginal_r.max())
print("check posterior")
print("p(y|x) ", posterior_mu.min(), posterior_mu.max())
print("p(y|x,a)", posterior_r_lam_mu.min(), posterior_r_lam_mu.max())
# return None
plt.axvline(config.TRUE.mu, c="orange", label="true mu")
plt.axvline(config.TRUE.mu-std_mu, c="orange", label="true mu - std(mu)")
plt.axvline(config.TRUE.mu+std_mu, c="orange", label="true mu + std(mu)")
plt.axvline(sig_ratio, c="red", label="signal ratio")
plt.axvline(expect_mu, c="green", label="E[mu|x]")
plt.plot(mu_grid, marginal_mu, label="posterior")
plt.xlabel("mu")
plt.ylabel("proba density")
plt.title("posterior marginal proba of mu vs mu values")
plt.legend()
plt.savefig(os.path.join(DIRECTORY, 'marginal_mu.png'))
plt.clf()
plt.plot(lam_grid, marginal_lam, label="posterior")
plt.axvline(config.TRUE.lam, c="orange", label="true lambda")
plt.xlabel("lambda")
plt.ylabel("proba density")
plt.title("posterior marginal proba of lam vs lam values")
plt.legend()
plt.savefig(os.path.join(DIRECTORY, 'marginal_lam.png'))
plt.clf()
plt.plot(r_grid, marginal_r, label="posterior")
plt.axvline(config.TRUE.r, c="orange", label="true r")
plt.xlabel("r")
plt.ylabel("proba density")
plt.title("posterior marginal proba of r vs r values")
plt.legend()
plt.savefig(os.path.join(DIRECTORY, 'marginal_r.png'))
plt.clf()
