def find_masses():
""" Finds the masses to be used in the fit
Parameters:
-----------
info_dir : str
Path to the info_directory of the required channel
global_settings : dict
Global settings (channel, bdtType etc.)
masses_type : str
Which masses type to use. 'low', 'high' or 'all'
Returns:
--------
masses : list
List of masses to be used.
"""
channel_dir, info_dir, global_settings = ut.find_settings()
scenario = global_settings['scenario']
reader = hpr.HHParameterReader(channel_dir, scenario)
preferences = reader.parameters
if masses_type == 'all':
masses = preferences['masses']
else:
masses = preferences['masses_' + masses_type]
return masses
def prepare_data(analysis):
channel_dir, info_dir, global_settings = ut.find_settings()
scenario = global_settings['scenario']
reader = hpr.HHParameterReader(channel_dir, scenario)
preferences = reader.parameters
preferences['trainvars'] = preferences['all_trainvar_info'].keys()
startTime = datetime.now()
print('data loading is started: ' + str(startTime))
if analysis == 'HHmultilepton':
normalizer = hht.HHDataNormalizer
loader = hht.HHDataLoader(normalizer, preferences, global_settings)
elif analysis == 'HHbbWW':
normalizer = bbwwt.bbWWDataNormalizer
loader = bbwwt.bbWWLoader(normalizer, preferences, global_settings)
data = loader.data
print('data loading is finished')
print(datetime.now() - startTime)
scenario = global_settings['scenario']
scenario = scenario if 'nonres' in scenario else 'res/' + scenario
hyperparameters_file = os.path.join(
os.path.expandvars('$CMSSW_BASE'),
'src/machineLearning/machineLearning/info/',
global_settings['process'], global_settings['channel'], scenario,
'hyperparameters.json')
with open(hyperparameters_file, 'rt') as in_file:
preferences['hyperparameters'] = json.load(in_file)
return data, preferences, global_settings
def main(output_dir, save_model, channel, mode, era, BM):
settings_dir = os.path.join(
os.path.expandvars('$CMSSW_BASE'),
'src/machineLearning/machineLearning/settings')
global_settings = ut.read_settings(settings_dir, 'global')
global_settings['ml_method'] = 'lbn'
global_settings['channel'] = 'bb1l'
if output_dir == 'None':
output_dir = global_settings['channel']+'/'+global_settings['ml_method']+'/'+\
res_nonres + '/' + mode +'/' + era
global_settings['output_dir'] = output_dir
else:
global_settings['output_dir'] = output_dir
global_settings['output_dir'] = os.path.expandvars(
global_settings['output_dir'])
if not os.path.exists(global_settings['output_dir']):
os.makedirs(global_settings['output_dir'])
channel_dir, info_dir, _ = ut.find_settings()
scenario = global_settings['scenario']
reader = hpr.HHParameterReader(channel_dir, scenario)
preferences = reader.parameters
if not BM == 'None':
preferences["nonResScenarios"] = [BM]
print('BM point to be considered: ' + str(preferences["nonResScenarios"]))
if not era == '0':
preferences['included_eras'] = [era.replace('20', '')]
print('era: ' + str(preferences['included_eras']))
preferences = define_trainvars(global_settings, preferences, info_dir)
particles = PARTICLE_INFO[global_settings['channel']]
data_dict = create_data_dict(preferences, global_settings)
classes = set(data_dict["even_data"]["process"])
for class_ in classes:
multitarget = list(
set(data_dict["even_data"].loc[data_dict["even_data"]["process"] ==
class_, "multitarget"]))[0]
print(str(class_) + '\t' + str(multitarget))
even_model = create_model(preferences, global_settings, data_dict,
"even_data", save_model)
if global_settings['feature_importance'] == 1:
trainvars = preferences['trainvars']
data = data_dict['odd_data']
LBNFeatureImportance = nt.LBNFeatureImportances(even_model, data,\
trainvars, global_settings['channel'])
score_dict = LBNFeatureImportance.custom_permutation_importance()
hhvt.plot_feature_importances_from_dict(score_dict,
global_settings['output_dir'])
odd_model = create_model(preferences, global_settings, data_dict,
"odd_data", save_model)
print(odd_model.summary())
nodewise_performance(data_dict['odd_data'], data_dict['even_data'],\
odd_model, even_model, data_dict['trainvars'], particles, \
global_settings, preferences)
even_train_info, even_test_info = evaluate_model(
even_model, data_dict['even_data'], data_dict['odd_data'],\
data_dict['trainvars'], global_settings, "even_data", particles)
odd_train_info, odd_test_info = evaluate_model(
odd_model, data_dict['odd_data'], data_dict['even_data'], \
data_dict['trainvars'], global_settings, "odd_data", particles)
hhvt.plotROC([odd_train_info, odd_test_info],
[even_train_info, even_test_info], global_settings)
def main():
""" Main function for operating the fitting, plotting and creation of
histo_dict
Parameters:
-----------
fit : bool
Whether to do a fit
create_info : bool
Whether to create histo_dict from scratch
weight_dir : str
Path to the directory where the TProfile files will be saved
masses_type : str
Type of the masses to be used. 'low', 'high' or 'all'
create_profile : bool
Whether to create the TProfiles.
Returns:
--------
Nothing
"""
channel_dir, info_dir, global_settings = ut.find_settings()
if 'nonres' in global_settings['scenario']:
raise TypeError("gen_mHH profiling is done only for resonant cases")
else:
scenario = global_settings['scenario']
reader = hpr.HHParameterReader(channel_dir, scenario)
normalizer = hht.HHDataNormalizer
preferences = reader.parameters
preferences['trainvars'] = preferences['all_trainvar_info'].keys()
if create_info:
create_histo_dict(info_dir, preferences)
if create_profile or fit:
loader = hht.HHDataLoader(normalizer,
preferences,
global_settings,
normalize=False)
data = loader.data
if not os.path.exists(weight_dir):
os.makedirs(weight_dir)
if fit:
do_fit(info_dir, data, preferences)
resulting_hadd_file = os.path.join(weight_dir, 'all_fitFunc.root')
print('Creating a single fit file with "hadd" to: ' +
str(resulting_hadd_file))
create_all_fitFunc_file(global_settings)
if create_profile:
create_TProfiles(info_dir, data, preferences, label='raw')
try:
data = loader.prepare_data(data)
create_TProfiles(info_dir,
data,
preferences,
label='reweighed')
except ReferenceError:
print('No fit for variables found')
print('Please fit the variables for plots after reweighing')
def main():
channel_dir, info_dir, global_settings = ut.find_settings()
preferences = hhat.get_hh_parameters(channel_dir,
global_settings['tauID_training'],
info_dir)
total_df = pandas.DataFrame()
for era in preferences['included_eras']:
input_path_key = 'inputPath' + str(era)
preferences['era_inputPath'] = preferences[input_path_key]
preferences['era_keys'] = preferences['keys' + str(era)]
era_df, labels = load_one_era(preferences, global_settings)
total_df.append(era_df, ignore_index=True)
create_latex_table(total_df, labels, global_settings['output_dir'])
def main(output_dir, settings_dir, hyperparameter_file, debug):
if settings_dir == 'None':
settings_dir = os.path.join(
os.path.expandvars('$CMSSW_BASE'),
'src/machineLearning/machineLearning/settings')
global_settings = ut.read_settings(settings_dir, 'global')
if output_dir == 'None':
output_dir = global_settings['output_dir']
else:
global_settings['output_dir'] = output_dir
global_settings['output_dir'] = os.path.expandvars(
global_settings['output_dir'])
if not os.path.exists(global_settings['output_dir']):
os.makedirs(global_settings['output_dir'])
channel_dir, info_dir, _ = ut.find_settings()
scenario = global_settings['scenario']
reader = hpr.HHParameterReader(channel_dir, scenario)
preferences = reader.parameters
if hyperparameter_file == 'None':
hyperparameter_file = os.path.join(info_dir, 'hyperparameters.json')
hyperparameters = ut.read_json_cfg(hyperparameter_file)
evaluation_main(global_settings, preferences, hyperparameters, debug)
def main(output_dir, settings_dir, hyperparameter_file, debug):
if settings_dir == 'None':
settings_dir = os.path.join(
os.path.expandvars('$CMSSW_BASE'),
'src/machineLearning/machineLearning/settings')
global_settings = settings_dir + '/' + 'global_%s_%s_%s_settings.json' % (
channel, mode, res_nonres)
command = 'rsync %s ~/machineLearning/CMSSW_11_2_0_pre1/src/machineLearning/machineLearning/settings/global_settings.json' % global_settings
p = subprocess.Popen(command,
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
global_settings = ut.read_settings(settings_dir, 'global')
if output_dir == 'None':
output_dir = global_settings['channel']+'/'+global_settings['ml_method']+'/'+\
res_nonres + '/' + mode +'/' + era
global_settings['output_dir'] = output_dir
else:
global_settings['output_dir'] = output_dir
global_settings['output_dir'] = os.path.expandvars(
global_settings['output_dir'])
if not os.path.exists(global_settings['output_dir']):
os.makedirs(global_settings['output_dir'])
channel_dir, info_dir, _ = ut.find_settings()
scenario = global_settings['scenario']
reader = hpr.HHParameterReader(channel_dir, scenario)
preferences = reader.parameters
if not BM == 'None':
preferences["nonResScenarios"] = [BM]
print('BM point to be considered: ' + str(preferences["nonResScenarios"]))
if not era == '0':
preferences['included_eras'] = [era.replace('20', '')]
print('era: ' + str(preferences['included_eras']))
preferences = define_trainvars(global_settings, preferences, info_dir)
if hyperparameter_file == 'None':
hyperparameter_file = os.path.join(info_dir, 'hyperparameters.json')
hyperparameters = ut.read_json_cfg(hyperparameter_file)
print('hyperparametrs ' + str(hyperparameters))
evaluation_main(global_settings, preferences, hyperparameters, debug)