def generate_test_data_score(method):
# get number of paramenters
hf = h5py.File(h5_file, 'r')
parameters = len(hf['parameters']['names'])
sa = SampleAugmenter(h5_file, include_nuisance_parameters=False)
theta_input = inputs[str(method)]['theta']
theta_sampling = theta_input['sampling_method']
if (theta_sampling == 'random_morphing_points'):
prior = []
for p in range(parameters):
this_tuple = theta_input['prior']['parameter_' + str(p)]
prior.append((str(this_tuple['prior_shape']),
float(this_tuple['prior_param_0']),
float(this_tuple['prior_param_1'])))
x, theta0, theta1, y, r_xz, t_xz = sample_train_local(
theta=eval(theta_sampling)(theta_input['n_thetas'], prior),
n_samples=inputs['n_samples']['test'],
folder='/home/test/' + method + '/',
filename='test',
switch_train_test_events=False,
)
if (theta_sampling == 'benchmark'):
_ = sa.sample_train_local(
theta=eval(theta_sampling)(theta_input['argument']),
n_samples=inputs['n_samples']['test'],
folder='/home/test/' + method + '/',
filename='test',
switch_train_test_events=False,
)
def generate_test_data_score(method: str):
"""
Generates test data files given a particular method (score)
:param method: name of the MadMiner method to generate theta
"""
sampler = SampleAugmenter(data_file, include_nuisance_parameters=False)
thetas = inputs[method]
theta_spec = thetas["theta_0"]
theta_vals = get_theta_values(theta_spec)
sampler.sample_train_local(
theta=theta_vals,
n_samples=n_samples_test,
folder=f"{tests_dir}/{method}",
filename="test",
)
#
# First, it unweights the samples, i.e. for a given parameter vector `theta` (or a distribution `p(theta)`) it picks events `x` such that their distribution follows `p(x|theta)`. The selected samples will all come from the event file we have so far, but their frequency is changed -- some events will appear multiple times, some will disappear.
#
# Second, `SampleAugmenter` calculates all the augmented data ("gold") that is the key to our new inference methods. Depending on the specific technique, these are the joint likelihood ratio and / or the joint score. It saves all these pieces of information for the selected events in a set of numpy files that can easily be used in any machine learning framework.
# In[3]:
sampler = SampleAugmenter('data/delphes_data_shuffled.h5')
# The relevant `SampleAugmenter` function for local score estimators is `extract_samples_train_local()`. As in part 3a of the tutorial, for the argument `theta` you can use the helper functions `sampling.benchmark()`, `sampling.benchmarks()`, `sampling.morphing_point()`, `sampling.morphing_points()`, and `sampling.random_morphing_points()`.
# In[4]:
x, theta, t_xz, _ = sampler.sample_train_local(
theta=sampling.benchmark('sm'),
#n_samples=4 * 10**5, #100000,
n_samples=2 * 10**6, # fewer than others
folder='./data/samples',
filename='train_score')
# We can use the same data as in part 3a, so you only have to execute this if you haven't gone through tutorial 3a:
# In[5]:
# _ = sampler.sample_test(
# theta=sampling.benchmark('sm'),
# n_samples=1*10**6,
# folder='./data/samples',
# filename='test'
# )
# ## 2. Train score estimator
theta0=theta_0_vals,
theta1=theta_1_vals,
n_samples=n_samples_train,
folder=f'{data_dir}/Samples_{method}_{i}',
filename=f'{method}_train',
test_split=test_split,
)
elif method in train_local_methods:
theta_spec = training_params['theta_0']
theta_vals = get_theta_values(theta_spec)
sampler.sample_train_local(
theta=theta_vals,
n_samples=n_samples_train,
folder=f'{data_dir}/Samples_{method}_{i}',
filename=f'{method}_train',
test_split=test_split,
)
elif method in train_global_methods:
theta_spec = training_params['theta_0']
theta_vals = get_theta_values(theta_spec)
sampler.sample_train_density(
theta=theta_vals,
n_samples=n_samples_train,
folder=f'{data_dir}/Samples_{method}_{i}',
filename=f'{method}_train',
test_split=test_split,
)
for p in range(parameters):
this_tuple = theta_input['prior']['parameter_' + str(p)]
prior.append((str(this_tuple['prior_shape']),
float(this_tuple['prior_param_0']),
float(this_tuple['prior_param_1'])))
x, theta0, theta1, y, r_xz, t_xz = sample_train_local(
theta=eval(theta_sampling)(theta_input['n_thetas'], prior),
n_samples=int(inputs['n_samples']['train']),
folder='/home/data/Samples_' + str(method) + '_' + str(i),
filename=method + '_train')
if (theta_sampling == 'benchmark'):
_ = sampler.sample_train_local(
theta=eval(theta_sampling)(theta_input['argument']),
n_samples=int(inputs['n_samples']['train']),
folder='/home/data/Samples_' + str(method) + '_' + str(i),
filename=method + '_train')
# #TRAIN GLOBAL
if method in ['scandal']:
theta_sampling = inputs['theta']['sampling_method']
theta = inputs[str(method)][
'theta'] #parameters for theta sampling
if (theta_sampling == 'random_morphing_points'):
tuple_0 = theta_sampling['prior'][
'parameter_0'] #tuple for parameter 0
tuple_1 = theta_sampling['prior'][
'parameter_1'] #tuple for parameter 1
prior = [ (str(tuple_0['prior_shape']), float(tuple_0['prior_param_0']), float(tuple_0['prior_param_1'])), \
