def get_no_nano_in_mini_mc_datasets(mc_tag_meta, full_mc_datasets):
no_nano_in_mini_mc_datasets = {}
mini_to_nano_from_nano = {}
for mc_dataset_name in mc_datasets:
for year in mc_datasets[mc_dataset_name]:
if 'nanoaod' not in mc_datasets[mc_dataset_name][year]: continue
for path in mc_datasets[mc_dataset_name][year]['nanoaod']:
parent = mc_datasets[mc_dataset_name][year]['nanoaod'][path][
'parent_chain'][0]
mini_to_nano_from_nano[parent] = path
# Check if nano is in mini
for mc_dataset_name in mc_datasets:
for year in mc_datasets[mc_dataset_name]:
if 'miniaod' not in mc_datasets[mc_dataset_name][year]: continue
for path in mc_datasets[mc_dataset_name][year]['miniaod']:
children = mc_datasets[mc_dataset_name][year]['miniaod'][path][
'children']
if path not in mini_to_nano_from_nano:
found_nano = False
for nano in children:
if mc_tag_meta[year][2] in nano:
found_nano = True
break
if not found_nano:
nested_dict.fill_nested_dict(
no_nano_in_mini_mc_datasets,
[mc_dataset_name, year, 'miniaod', path],
mc_datasets[mc_dataset_name][year]['miniaod'][path]
['children'])
return no_nano_in_mini_mc_datasets
def get_rejected_mc_datasets(mc_datasets, reject_mc_function, reject_input):
rejected_mc_datasets = {}
for mc_dataset_name in mc_datasets:
for year in mc_datasets[mc_dataset_name]:
for data_tier in mc_datasets[mc_dataset_name][year]:
for path in mc_datasets[mc_dataset_name][year][data_tier]:
if reject_mc_function(reject_input, mc_datasets, mc_dataset_name, year, data_tier, path):
path_info = mc_datasets[mc_dataset_name][year][data_tier][path]
nested_dict.fill_nested_dict(rejected_mc_datasets, [mc_dataset_name, year, data_tier, path], path_info)
return rejected_mc_datasets
def get_rejected_data_datasets(data_datasets, reject_data_function, reject_input):
rejected_data_datasets = {}
for stream in data_datasets:
for year in data_datasets[stream]:
for run_group in data_datasets[stream][year]:
for data_tier in data_datasets[stream][year][run_group]:
for path in data_datasets[stream][year][run_group][data_tier]:
if reject_data_function(reject_input, data_datasets, stream, year, run_group, data_tier, path):
path_info = data_datasets[stream][year][run_group][data_tier][path]
nested_dict.fill_nested_dict(rejected_data_datasets, [stream, year, run_group, data_tier, path], path_info)
return rejected_data_datasets
def get_unrejected_if_possible_mc_datasets(mc_datasets, reject_mc_function, reject_input=None):
unrejected_mc_datasets = {}
for mc_dataset_name in mc_datasets:
for year in mc_datasets[mc_dataset_name]:
for data_tier in mc_datasets[mc_dataset_name][year]:
found_mc_dataset = False
list_rejected_mc_dataset = []
for path in mc_datasets[mc_dataset_name][year][data_tier]:
path_info = mc_datasets[mc_dataset_name][year][data_tier][path]
if reject_mc_function(reject_input, mc_datasets, mc_dataset_name, year, data_tier, path):
list_rejected_mc_dataset.append([path, path_info])
continue
found_mc_dataset = True
if not found_mc_dataset:
for rejected_mc_dataset in list_rejected_mc_dataset:
nested_dict.fill_nested_dict(unrejected_mc_datasets, [mc_dataset_name, year, data_tier, rejected_mc_dataset[0]], rejected_mc_dataset[1])
return unrejected_mc_datasets
def get_rejected_if_possible_mc_datasets(mc_datasets, reject_mc_function, reject_input, verbose=False):
rejected_mc_datasets = {}
for mc_dataset_name in mc_datasets:
for year in mc_datasets[mc_dataset_name]:
for data_tier in mc_datasets[mc_dataset_name][year]:
found_mc_dataset = False
list_rejected_mc_dataset = []
for path in mc_datasets[mc_dataset_name][year][data_tier]:
path_info = mc_datasets[mc_dataset_name][year][data_tier][path]
if reject_mc_function(reject_input, mc_datasets, mc_dataset_name, year, data_tier, path):
if verbose: print('Possibly rejected '+path)
list_rejected_mc_dataset.append([path, path_info])
continue
if verbose: print('Found '+path)
found_mc_dataset = True
if found_mc_dataset:
if verbose: print('Rejected '+path)
for rejected_mc_dataset in list_rejected_mc_dataset:
nested_dict.fill_nested_dict(rejected_mc_datasets, [mc_dataset_name, year, data_tier, rejected_mc_dataset[0]], rejected_mc_dataset[1])
return rejected_mc_datasets
def select_paths_from_multiple(mc_tag_meta, mc_datasets, multiple_selection):
mc_datasets_selected = {}
mc_datasets_non_selected = {}
for mc_dataset_name in mc_datasets:
for year in mc_datasets[mc_dataset_name]:
for data_tier in mc_datasets[mc_dataset_name][year]:
search_string = datasets.get_mc_dataset_search_string(mc_tag_meta, mc_dataset_name, year, data_tier)
multiple_selected_paths = None
if search_string in multiple_selection:
multiple_selected_paths = multiple_selection[search_string]['selected_paths']
if len(mc_datasets[mc_dataset_name][year][data_tier]) == 1:
path = next(iter(mc_datasets[mc_dataset_name][year][data_tier]))
nested_dict.fill_nested_dict(mc_datasets_selected, [mc_dataset_name, year, data_tier, path], mc_datasets[mc_dataset_name][year][data_tier][path])
else:
for path in mc_datasets[mc_dataset_name][year][data_tier]:
if multiple_selected_paths != None:
if path in multiple_selected_paths:
nested_dict.fill_nested_dict(mc_datasets_selected, [mc_dataset_name, year, data_tier, path], mc_datasets[mc_dataset_name][year][data_tier][path])
else:
print('[Warning] '+path+' is not in multiple_selection. Will not select any dataset.')
nested_dict.fill_nested_dict(mc_datasets_non_selected, [mc_dataset_name, year, data_tier, path], mc_datasets[mc_dataset_name][year][data_tier][path])
return mc_datasets_selected, mc_datasets_non_selected
