def make_input_plot(input_file):
confhandler = ConfigFileHandler()
confhandler.load_configuration(input_file)
models = confhandler.get_sections()
df = pd.DataFrame()
for model in models:
cur_sect = confhandler.get_section(model)
used_nonperiodic_vars = filter(
None,
ConfigFileUtils.parse_list(cur_sect["nonperiodic_columns"],
lambda x: x))
used_periodic_vars = filter(
None,
ConfigFileUtils.parse_list(cur_sect["periodic_columns"],
lambda x: x))
used_vars = used_nonperiodic_vars + used_periodic_vars
var_dict = {col: [1.0] for col in used_vars}
var_dict["model"] = model
row_df = pd.DataFrame.from_dict(var_dict)
df = pd.concat([df, row_df], axis=0)
df = df.fillna(0.0)
datacols = [col for col in df.columns if col is not "model"]
plot_data = df[datacols].as_matrix()
y_label = [convert_variable_name(name) for name in np.array(datacols)]
x_label = [convert_model_label(label) for label in df["model"].as_matrix()]
fig = plt.figure(figsize=(12, 10))
ax = fig.add_subplot(111)
cax = ax.matshow(plot_data.transpose(), cmap='Blues', vmin=0, vmax=1)
ax.set_xticklabels(np.concatenate([[''], x_label]),
rotation='vertical',
fontsize=11)
ax.set_yticklabels(np.concatenate([[''], y_label]), fontsize=10)
ax.xaxis.set_label_position("top")
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
plt.tight_layout()
return fig
def load_file(path, keys):
confhandler = ConfigFileHandler()
confhandler.load_configuration(path)
retval = {}
for section_name in confhandler.get_sections():
cur_section = confhandler.get_section(section_name)
for key in keys:
if not key in retval:
retval[key] = []
retval[key].append(float(cur_section[key]))
return retval
def run_bayesian_optimization(name, eval_file, target, var_ranges, init_points, max_iterations, patience, alpha):
global evalcnt
evalcnt = 0
print "now optimizing the following variables: " + str(var_ranges)
print "alpha = " + str(alpha)
# change the kernel to have a length scale more appropriate to this function
# alpha ... corresponds to the value added to the diagonal elements of the covariance matrix <-> the approximate noise level in the observations
gp_params = {'kernel': ConstantKernel(1.0, (1e-8, 1e2)) * Matern(length_scale = 0.01, length_scale_bounds = (1e-5, 1e5), nu = 1.5),
'alpha': alpha}
bo = BayesianOptimization(target, var_ranges)
# check if a file with previous evaluations of this utility function already exists, if so, use it for initialization
evaluations_path = os.path.join(out_dir, eval_file)
if os.path.exists(evaluations_path):
confhandler = ConfigFileHandler()
confhandler.load_configuration(evaluations_path)
init_dict = {}
for section_name in confhandler.get_sections():
cur_section = confhandler.get_section(section_name)
for key, value in cur_section.iteritems():
# only take those variables that are actually relevant
if key in var_ranges or key == "target":
if key not in init_dict:
init_dict[key] = []
init_dict[key].append(float(value))
evalcnt = int(re.sub('evaluation_', '', confhandler.get_sections()[-1])) + 1
print "resuming " + name + " at evaluation " + str(evalcnt)
init_points_loaded = len(init_dict["target"])
print "found " + str(init_points_loaded) + " initialization points: " + str(init_dict)
bo.initialize(init_dict)
bo.maximize(init_points = max(0, init_points - init_points_loaded), n_iter = 0, acq = 'poi', kappa = 3, xi = xi_scheduler(0.0, max_iterations), **gp_params)
print "initialization done"
else:
bo.maximize(init_points = init_points, n_iter = 0, acq = 'poi', kappa = 3, xi = xi_scheduler(0.0, max_iterations), **gp_params)
cur_iteration = 1
patience_cnt = 0
best_cost = -7.0
for it in range(max_iterations):
cur_xi = xi_scheduler(cur_iteration, max_iterations)
print "cur_iteration = " + str(cur_iteration) + ", using xi = " + str(cur_xi)
cur_iteration += 1
bo.maximize(init_points = 0, n_iter = 1, acq = 'poi', kappa = 3, xi = cur_xi, **gp_params)
# evaluate the current maximum
curval = bo.res['max']
cost = curval['max_val']
curparams = curval['max_params']
confhandler = ConfigFileHandler()
confhandler.config.optionxform = str
confhandler.new_section(name)
confhandler.set_field(name, 'target', str(cost))
for key, val in curparams.iteritems():
confhandler.set_field(name, key, str(val))
confhandler.save_configuration(os.path.join(out_dir, name + '.txt'))
# check if it is time to stop this optimization
if(cost > best_cost):
best_cost = cost
patience_cnt = 0
patience_cnt += 1
if(patience_cnt > patience):
break
return curparams
def main():
if len(sys.argv) != 3:
print "Error: exactly 2 arguments are required"
# global settings
categories = [
"UnTagged", "VBF1jTagged", "VBF2jTagged", "VHLeptTagged",
"VHHadrTagged", "ttHLeptTagged", "ttHHadrTagged", "VHMETTagged"
]
processes = {
'ggH': 'ggH_hzz',
'qqH': 'qqH_hzz',
'WH_lep': 'WH_lep_hzz',
'WH_had': 'WH_had_hzz',
'ZH_lep': 'ZH_lep_hzz',
'ZH_had': 'ZH_had_hzz',
'ttH_lep': 'ttH_lep_hzz',
'ttH_had': 'ttH_had_hzz',
'tqH': 'tqH_hzz',
'bbH': 'bbH_hzz',
'qqZZ': 'qqZZ_hzz',
'ggZZ': 'ggZZ_hzz'
}
input_file = sys.argv[1]
output_path = sys.argv[2]
# output_path = os.path.dirname(input_file)
output_file_expt = os.path.join(output_path, "systematics_expt_13TeV.yaml")
output_file_th = os.path.join(output_path, "systematics_theory_13TeV.yaml")
confhandler = ConfigFileHandler()
confhandler.load_configuration(input_file)
# prepare the YAML file for the experimental uncertainties
syst_expt = Systematics2YAML()
# --------------------------------
# PileUp
# --------------------------------
# the global, inclusive one
source_syst_name = 'PileUp'
YAML_syst_name = 'CMS_PileUp'
syst_type = 'lnN'
syst_expt.add_systematics(YAML_syst_name)
for category in categories:
syst_expt.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " +
"inclusive")
syst_expt.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in processes.keys():
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_expt.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# for each category
source_syst_name = 'PileUp'
YAML_syst_name = 'CMS_PileUp_cat'
syst_type = 'lnN'
syst_expt.add_systematics(YAML_syst_name)
for category in categories:
syst_expt.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_expt.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in processes.keys():
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_expt.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# --------------------------------
# Jet Energy Scale
# --------------------------------
source_syst_name = 'JEC'
YAML_syst_name = 'CMS_scale_j_13TeV'
syst_type = 'lnN'
syst_expt.add_systematics(YAML_syst_name)
for category in categories:
syst_expt.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_expt.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in processes.keys():
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_expt.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# --------------------------------
# Lepton Energy Scale
# --------------------------------
source_syst_name = 'LEC'
YAML_syst_name = 'CMS_scale_l_13TeV'
syst_type = 'lnN'
syst_expt.add_systematics(YAML_syst_name)
for category in categories:
syst_expt.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_expt.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in processes.keys():
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_expt.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# --------------------------------
# BTagging
# --------------------------------
source_syst_name = 'BTag'
YAML_syst_name = 'CMS_eff_b'
syst_type = 'lnN'
syst_expt.add_systematics(YAML_syst_name)
for category in categories:
syst_expt.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_expt.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in processes.keys():
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_expt.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
syst_expt.save(output_file_expt)
# ---------------------------------------------------------------------------------
# ---------------------------------------------------------------------------------
# prepare the YAML file for the theoretical uncertainties
syst_th = Systematics2YAML()
# --------------------------------
# PDF scale
# --------------------------------
source_syst_name = 'PDF_scale'
YAML_syst_name = 'pdf_Higgs_gg_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["ggH", "ggZZ"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
source_syst_name = 'PDF_scale'
YAML_syst_name = 'pdf_Higgs_qqbar_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["qqH", "WH_lep", "WH_had", "ZH_lep", "ZH_had"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
source_syst_name = 'PDF_scale'
YAML_syst_name = 'pdf_Higgs_ttH_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["ttH_lep", "ttH_had"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
source_syst_name = 'PDF_scale'
YAML_syst_name = 'pdf_qqbar_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["qqZZ"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# --------------------------------
# QCD scale
# --------------------------------
source_syst_name = 'QCD_scale'
YAML_syst_name = 'QCDscale_qqH_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["qqH"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
source_syst_name = 'QCD_scale'
YAML_syst_name = 'QCDscale_VH_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["WH_lep", "WH_had"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# here, since did not have the values for ZH_had and ZH_lep available, copy them from the corresponding WH processes
if process == "WH_lep":
syst_th.add_category_entry(
YAML_syst_name, category,
{processes["ZH_lep"]: val_string})
if process == "WH_had":
syst_th.add_category_entry(
YAML_syst_name, category,
{processes["ZH_had"]: val_string})
source_syst_name = 'QCD_scale'
YAML_syst_name = 'QCDscale_ttH_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["ttH_lep", "ttH_had", "tqH", "bbH"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
source_syst_name = 'QCD_scale'
YAML_syst_name = 'QCDscale_VV_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["qqZZ"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# --------------------------------
# EW corrections
# --------------------------------
source_syst_name = 'EWCorr'
YAML_syst_name = 'EWcorr_VV_cat'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
for process in ["qqZZ"]:
val_list = ConfigFileUtils.parse_list(cur_sect[process],
lambda x: float(x))
val_string = str(val_list[0]) + "/" + str(val_list[1])
if not (val_list[0] == 1.0 and val_list[1] == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val_string})
# --------------------------------
# ggH uncertainties
# --------------------------------
source_syst_name = 'THU_ggH_Mu'
YAML_syst_name = 'THU_ggH_Mu'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
# can use the same value as well for the ggZZ background! (here and in the following)
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_Res'
YAML_syst_name = 'THU_ggH_Res'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_Mig01'
YAML_syst_name = 'THU_ggH_Mig01'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_Mig12'
YAML_syst_name = 'THU_ggH_Mig12'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_VBF2j'
YAML_syst_name = 'THU_ggH_VBF2j'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_VBF3j'
YAML_syst_name = 'THU_ggH_VBF3j'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_PT60'
YAML_syst_name = 'THU_ggH_PT60'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_PT120'
YAML_syst_name = 'THU_ggH_PT120'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
source_syst_name = 'THU_ggH_qmtop'
YAML_syst_name = 'THU_ggH_qmtop'
syst_type = 'lnN'
syst_th.add_systematics(YAML_syst_name)
for category in categories:
syst_th.add_category(YAML_syst_name, category)
cur_sect = confhandler.get_section(source_syst_name + ": " + category)
syst_th.add_category_entry(YAML_syst_name, category,
{'type': syst_type})
process = "ggH"
val = float(cur_sect[process])
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes[process]: val})
if not (val == 1.0):
syst_th.add_category_entry(YAML_syst_name, category,
{processes["ggZZ"]: val})
syst_th.save(output_file_th)
def main():
if len(sys.argv) != 3:
print "Error: exactly 2 arguments are required!"
source_path = sys.argv[1]
#source_path = "/data_CMS/cms/wind/CJLST_NTuples_prepared_systematics/"
dest_path = sys.argv[2]
# global settings:
zzroot = os.environ["CMSSW_BASE"]
bin_dir = os.path.join(zzroot, "bin/slc6_amd64_gcc630/")
scrambler = os.path.join(bin_dir, "run_scrambler")
chunk_extractor = os.path.join(bin_dir, "run_chunk_extractor")
settings_path = os.path.join(dest_path, "settings.conf")
confhandler = ConfigFileHandler()
confhandler.load_configuration(settings_path)
# load global settings from the configuration file
root_file_name = confhandler.get_field("Global", "root_file_name")
source_dir = confhandler.get_field("Global", "source_dir")
chunk_size = int(confhandler.get_field("Global", "chunk_size"))
def submit_job(cmd_dir, command):
job_submitter = os.environ["JOB_SUBMITTER"]
filename = str(uuid.uuid4()) + ".sh"
file_path = os.path.join(cmd_dir, filename)
with open(file_path, "w") as cmd_file:
cmd_file.write("#!/bin/bash\n")
cmd_file.write(command)
while True:
try:
output = sp.check_output([job_submitter, "-short", file_path])
break
except sp.CalledProcessError:
print "-------------------------------------------------"
print " error submitting job, retrying ... "
print "-------------------------------------------------"
print output
def chunk_file(in_dir, out_root, base_name, number_chunks, cmd_dir):
splits = np.linspace(0, 1, number_chunks)
in_file = os.path.join(in_dir, root_file_name)
if number_chunks == 1:
out_folder = os.path.join(out_root, base_name + "_chunk_0/")
if not os.path.exists(out_folder):
os.makedirs(out_folder)
out_file = os.path.join(out_folder, root_file_name)
command = " ".join([chunk_extractor, in_file, out_file, str(0.0), str(1.0), str(0)])
submit_job(cmd_dir, command)
print command
else:
for i in range(len(splits) - 1):
start_split = splits[i]
end_split = splits[i + 1]
out_folder = os.path.join(out_root, base_name + "_chunk_" + str(i) + "/")
if not os.path.exists(out_folder):
os.makedirs(out_folder)
out_file = os.path.join(out_folder, root_file_name)
command = " ".join([chunk_extractor, in_file, out_file, str(start_split), str(end_split), str(0)])
submit_job(cmd_dir, command)
print command
# create the needed folders:
train_dir = os.path.join(dest_path, "training/")
validation_dir = os.path.join(dest_path, "validation/")
test_dir = os.path.join(dest_path, "test/")
trainval_dir = os.path.join(dest_path, "trainval/")
temp_dir = os.path.join(dest_path, "temp/")
# create these directories
if not os.path.exists(train_dir):
os.makedirs(train_dir)
if not os.path.exists(validation_dir):
os.makedirs(validation_dir)
if not os.path.exists(test_dir):
os.makedirs(test_dir)
if not os.path.exists(trainval_dir):
os.makedirs(trainval_dir)
if not os.path.exists(temp_dir):
os.makedirs(temp_dir)
training_files = [cur_file for cur_file in confhandler.get_sections() if "Global" not in cur_file]
available_files = next(os.walk(source_path))[1]
used_files = []
for training_file in training_files:
sect = confhandler.get_section(training_file)
print "--------------------------------------------------"
print "currently splitting: " + training_file
source_files = ConfigFileUtils.parse_list(sect["source"], lambda x: x)
train_val_splits = ConfigFileUtils.parse_list(sect["train_val_split"], lambda x: float(x))
val_test_splits = ConfigFileUtils.parse_list(sect["val_test_split"], lambda x: float(x))
# first split the needed files into 3 pieces, as dictated by the splits read from the config file
for source_file, train_val_split, val_test_split in zip(source_files, train_val_splits, val_test_splits):
print "extracting 0.0 - " + str(train_val_split) + " from " + source_file
dest_dir = os.path.join(train_dir, source_file)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
output = sp.check_output([chunk_extractor, os.path.join(source_path, source_file, root_file_name),
os.path.join(dest_dir, root_file_name), str(0.0), str(train_val_split)])
print output
print "-- -- -- -- -- -- -- -- -- -- -- --"
print "extracting " + str(train_val_split) + " - " + str(val_test_split) + " from " + source_file
dest_dir = os.path.join(validation_dir, source_file)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
output = sp.check_output([chunk_extractor, os.path.join(source_path, source_file, root_file_name),
os.path.join(dest_dir, root_file_name), str(train_val_split), str(val_test_split)])
print output
print "-- -- -- -- -- -- -- -- -- -- -- --"
print "extracting " + str(val_test_split) + " - 1.0 from " + source_file
dest_dir = os.path.join(test_dir, source_file)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
output = sp.check_output([chunk_extractor, os.path.join(source_path, source_file, root_file_name),
os.path.join(dest_dir, root_file_name), str(val_test_split), str(1.0)])
print output
used_files.append(source_file)
print "--------------------------------------------------"
unused_files = [cur_file for cur_file in available_files if cur_file not in used_files]
# for all files that are not used for training, split them 50:50 into validation and test ...
for unused_file in unused_files:
source_dir = os.path.join(source_path, unused_file)
# ... unless they are only needed to assess systematics, i.e. are not going to be used at all during the validation step
if "ext" in unused_file or "tuneup" in unused_file or "tunedown" in unused_file:
print "extracting 0.0 - 1.0 from " + unused_file
dest_dir = os.path.join(test_dir, unused_file)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
output = sp.check_output([chunk_extractor, os.path.join(source_dir, root_file_name),
os.path.join(dest_dir, root_file_name), str(0.0), str(1.0)])
print output
else:
print "extracting 0.0 - 0.5 from " + unused_file
dest_dir = os.path.join(validation_dir, unused_file)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
output = sp.check_output([chunk_extractor, os.path.join(source_dir, root_file_name),
os.path.join(dest_dir, root_file_name), str(0.0), str(0.5)])
print output
print "-- -- -- -- -- -- -- -- -- -- -- --"
print "extracting 0.5 - 1.0 from " + unused_file
dest_dir = os.path.join(test_dir, unused_file)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
output = sp.check_output([chunk_extractor, os.path.join(source_dir, root_file_name),
os.path.join(dest_dir, root_file_name), str(0.5), str(1.0)])
print output
# now have all the needed files split apart, can now proceed to combine them into the training
# datasets that will end up in trainval
for training_file in training_files:
print "now building training dataset: " + training_file
sect = confhandler.get_section(training_file)
source_folders = ConfigFileUtils.parse_list(sect["source"], lambda x: x)
for mode in ["training", "validation"]:
temp_dest_folder = os.path.join(dest_path, temp_dir, training_file, mode)
temp_dest_file = os.path.join(temp_dest_folder, root_file_name)
if not os.path.exists(temp_dest_folder):
os.makedirs(temp_dest_folder)
source_files = [os.path.join(dest_path, mode, cur_file, root_file_name) for cur_file in source_folders]
print "hadd " + temp_dest_file + " " + " ".join(source_files)
output = sp.check_output(["hadd", temp_dest_file] + source_files)
print output
temp_scrambled_folder = os.path.join(dest_path, temp_dir, "scrambled", training_file, mode)
if not os.path.exists(temp_scrambled_folder):
os.makedirs(temp_scrambled_folder)
temp_scrambled_file = os.path.join(temp_scrambled_folder, root_file_name)
print scrambler + " " + temp_dest_file + " " + temp_scrambled_file
output = sp.check_output([scrambler, temp_dest_file, temp_scrambled_file])
print output
trainval_dest_folder = os.path.join(trainval_dir, training_file)
if not os.path.exists(trainval_dest_folder):
os.makedirs(trainval_dest_folder)
print "hadd " + os.path.join(trainval_dest_folder, root_file_name) + " " + os.path.join(dest_path, temp_dir, "scrambled", training_file, "training", root_file_name) + " " + os.path.join(dest_path, temp_dir, "scrambled", training_file, "validation", root_file_name)
output = sp.check_output(["hadd", os.path.join(trainval_dest_folder, root_file_name),
os.path.join(dest_path, temp_dir, "scrambled", training_file, "training", root_file_name),
os.path.join(dest_path, temp_dir, "scrambled", training_file, "validation", root_file_name)])
print output
# at the end, chunk the ROOT files into many smaller ones, to keep the augmentation time short
train_chunks_dir = os.path.join(dest_path, "training_chunks/")
validation_chunks_dir = os.path.join(dest_path, "validation_chunks/")
test_chunks_dir = os.path.join(dest_path, "test_chunks/")
# create these directories
if not os.path.exists(train_chunks_dir):
os.makedirs(train_chunks_dir)
if not os.path.exists(validation_chunks_dir):
os.makedirs(validation_chunks_dir)
if not os.path.exists(test_chunks_dir):
os.makedirs(test_chunks_dir)
for mode in ["training", "validation", "test"]:
# look at each file individually and put it into chunks
cur_dir = os.path.join(dest_path, mode)
available_folders = next(os.walk(cur_dir))[1]
for available_folder in available_folders:
available_file = os.path.join(cur_dir, available_folder, root_file_name)
number_chunks = max(1, os.path.getsize(available_file) / chunk_size)
print "now splitting file " + available_file + " into " + str(number_chunks) + " chunks"
out_root = os.path.join(dest_path, mode + "_chunks")
chunk_file(os.path.join(dest_path, mode, available_folder), out_root, available_folder, number_chunks, temp_dir)
print "done."
def main():
global evalcnt
if len(sys.argv) != 4:
print "Error: exactly 3 arguments are required"
run_dir = sys.argv[1]
out_dir = sys.argv[2]
engine = sys.argv[3]
print run_dir
print out_dir
print engine
# punzi_target_2d = lambda WHlept_prior, ZHlept_prior: punzi_target(ggH_prior_default, WHhadr_prior_default, ZHhadr_prior_default,
# WHlept_prior, ZHlept_prior, ZHMET_prior_default,
# ttHhadr_prior_default, ttHlept_prior_default)
def punzi_target(ggH_prior, WHhadr_prior, ZHhadr_prior, WHlept_prior,
ZHlept_prior, ZHMET_prior, ttHhadr_prior, ttHlept_prior):
global evalcnt
bin_dir = "/home/llr/cms/wind/cmssw/CMSSW_9_4_2/bin/slc6_amd64_gcc630/"
cost_function_evaluator = "run_prior_evaluator"
output = check_output([
bin_dir + cost_function_evaluator, run_dir, out_dir, engine,
str(ggH_prior),
str(WHhadr_prior),
str(ZHhadr_prior),
str(WHlept_prior),
str(ZHlept_prior),
str(ZHMET_prior),
str(ttHhadr_prior),
str(ttHlept_prior)
])
costval = 0.0
for line in output.split('\n'):
if "cost = " in line:
costval = float(line.replace("cost = ", ""))
break
if math.isnan(costval):
costval = -8.75
# add a regularization term that prefers default priors (i.e. close to 1.0)
reg_term = 1.0 / 8.0 * (
(ggH_prior - 1.0)**2.0 + (WHhadr_prior - 1.0)**2.0 +
(ZHhadr_prior - 1.0)**2.0 + (WHlept_prior - 1.0)**2.0 +
(ZHlept_prior - 1.0)**2.0 + (ZHMET_prior - 1.0)**2.0 +
(ttHhadr_prior - 1.0)**2.0 + (ttHlept_prior - 1.0)**2.0)
costval -= reg_term * lambda_reg
# save the sampled point such that later they can be used as exploration points (if the need occurs)
confhandler = ConfigFileHandler()
evaluations_path = out_dir + 'evaluations.txt'
if os.path.exists(evaluations_path):
confhandler.load_configuration(evaluations_path)
print "saving evaluation for iteration " + str(evalcnt)
section_name = 'evaluation_' + str(evalcnt)
confhandler.new_section(section_name)
confhandler.set_field(section_name, 'cost', str(costval))
confhandler.set_field(section_name, 'ggH_prior', str(ggH_prior))
confhandler.set_field(section_name, 'WHhadr_prior', str(WHhadr_prior))
confhandler.set_field(section_name, 'ZHhadr_prior', str(ZHhadr_prior))
confhandler.set_field(section_name, 'WHlept_prior', str(WHlept_prior))
confhandler.set_field(section_name, 'ZHlept_prior', str(ZHlept_prior))
confhandler.set_field(section_name, 'ZHMET_prior', str(ZHMET_prior))
confhandler.set_field(section_name, 'ttHhadr_prior',
str(ttHhadr_prior))
confhandler.set_field(section_name, 'ttHlept_prior',
str(ttHlept_prior))
confhandler.save_configuration(evaluations_path)
evalcnt += 1
return costval
eps = 1e-1
delta = 0.2
bo = BayesianOptimization(
punzi_target, {
'ggH_prior': (1.0 - delta, 1.0 + delta),
'WHhadr_prior': (eps, 1.0),
'ZHhadr_prior': (eps, 1.0),
'WHlept_prior': (eps, 1.0),
'ZHlept_prior': (eps, 1.0),
'ZHMET_prior': (eps, 1.0),
'ttHhadr_prior': (eps, 1.0),
'ttHlept_prior': (eps, 1.0)
})
# bo = BayesianOptimization(punzi_target_2d, {'WHlept_prior': (eps, WHlept_prior_default + delta),
# 'ZHlept_prior': (eps, ZHlept_prior_default + delta)})
# check if a file with previously evaluated points exists, if so, use them for initialization
confhandler = ConfigFileHandler()
evaluations_path = out_dir + 'evaluations.txt'
if os.path.exists(evaluations_path):
confhandler.load_configuration(evaluations_path)
ggH_priors_init = []
WHhadr_priors_init = []
ZHhadr_priors_init = []
WHlept_priors_init = []
ZHlept_priors_init = []
ZHMET_priors_init = []
ttHhadr_priors_init = []
ttHlept_priors_init = []
targets_init = []
for section_name in confhandler.get_sections():
cur_section = confhandler.get_section(section_name)
targets_init.append(float(cur_section['cost']))
ggH_priors_init.append(float(cur_section['ggH_prior']))
WHhadr_priors_init.append(float(cur_section['WHhadr_prior']))
ZHhadr_priors_init.append(float(cur_section['ZHhadr_prior']))
WHlept_priors_init.append(float(cur_section['WHlept_prior']))
ZHlept_priors_init.append(float(cur_section['ZHlept_prior']))
ZHMET_priors_init.append(float(cur_section['ZHMET_prior']))
ttHhadr_priors_init.append(float(cur_section['ttHhadr_prior']))
ttHlept_priors_init.append(float(cur_section['ttHlept_prior']))
init_dict = {
'target': targets_init,
'ggH_prior': ggH_priors_init,
'WHhadr_prior': WHhadr_priors_init,
'ZHhadr_prior': ZHhadr_priors_init,
'WHlept_prior': WHlept_priors_init,
'ZHlept_prior': ZHlept_priors_init,
'ZHMET_prior': ZHMET_priors_init,
'ttHhadr_prior': ttHhadr_priors_init,
'ttHlept_prior': ttHlept_priors_init
}
evalcnt = int(re.sub('evaluation_', '',
confhandler.get_sections()[-1])) + 1
print "resuming at evaluation " + str(evalcnt)
bo.initialize(init_dict)
initialized = True
else:
initialized = False
# change the kernel to have a length scale more appropriate to this function
# alpha ... corresponds to the value added to the diagonal elements of the covariance matrix <-> the approximate noise level in the observations
gp_params = {
'kernel':
1.0 *
Matern(length_scale=0.05, length_scale_bounds=(1e-5, 1e5), nu=1.5),
'alpha':
1e-1
}
# perform the standard initialization and setup
if initialized:
bo.maximize(init_points=0,
n_iter=0,
acq='poi',
kappa=3,
xi=xi_scheduler(0.0),
**gp_params)
else:
bo.maximize(init_points=6,
n_iter=0,
acq='poi',
kappa=3,
xi=xi_scheduler(0.0),
**gp_params)
cur_iteration = 1
for it in range(1000):
cur_iteration += 1
cur_xi = xi_scheduler(cur_iteration)
print "using xi = " + str(cur_xi)
bo.maximize(init_points=6,
n_iter=1,
acq='poi',
kappa=3,
xi=cur_xi,
**gp_params)
# evaluate the current maximum
curval = bo.res['max']
cost = curval['max_val']
priors = curval['max_params']
confhandler = ConfigFileHandler()
confhandler.config.optionxform = str
confhandler.new_section('Priors')
confhandler.set_field('Priors', 'cost', str(cost))
confhandler.set_field('Priors', 'VBF_prior', str(1.0))
for key, val in priors.iteritems():
confhandler.set_field('Priors', key, str(val))
confhandler.save_configuration(out_dir + 'priors.txt')
def main():
global evalcnt
if len(sys.argv) != 4:
print "Error: exactly 3 arguments are required"
ref_dir = sys.argv[1]
out_dir = sys.argv[2]
lumi = float(sys.argv[3])
print ref_dir
print out_dir
print lumi
def punzi_target(WP_VBF2j, WP_VBF1j, WP_WHh, WP_ZHh):
global evalcnt
bin_dir = "/home/llr/cms/wind/cmssw/CMSSW_9_4_2/bin/slc6_amd64_gcc630/"
cost_function_evaluator = "run_WP_evaluator"
output = check_output([
bin_dir + cost_function_evaluator, ref_dir, out_dir,
str(lumi),
str(WP_VBF2j),
str(WP_VBF1j),
str(WP_WHh),
str(WP_ZHh)
])
costval = 0.0
for line in output.split('\n'):
if "cost = " in line:
costval = float(line.replace("cost = ", ""))
break
if math.isnan(costval):
costval = -8.75
# save the sampled point such that later they can be used as exploration points (if the need occurs)
confhandler = ConfigFileHandler()
evaluations_path = out_dir + 'evaluations.txt'
if os.path.exists(evaluations_path):
confhandler.load_configuration(evaluations_path)
print "saving evaluation for iteration " + str(evalcnt)
section_name = 'evaluation_' + str(evalcnt)
confhandler.new_section(section_name)
confhandler.set_field(section_name, 'cost', str(costval))
confhandler.set_field(section_name, 'WP_VBF2j', str(WP_VBF2j))
confhandler.set_field(section_name, 'WP_VBF1j', str(WP_VBF1j))
confhandler.set_field(section_name, 'WP_WHh', str(WP_WHh))
confhandler.set_field(section_name, 'WP_ZHh', str(WP_ZHh))
confhandler.save_configuration(evaluations_path)
evalcnt += 1
return costval
eps = 1e-3
delta = 0.2
bo = BayesianOptimization(
punzi_target, {
'WP_VBF2j': (eps, 1.0 - eps),
'WP_VBF1j': (eps, 1.0 - eps),
'WP_WHh': (eps, 1.0 - eps),
'WP_ZHh': (eps, 1.0 - eps)
})
# check if a file with previously evaluated points exists, if so, use them for initialization
confhandler = ConfigFileHandler()
evaluations_path = out_dir + 'evaluations.txt'
if os.path.exists(evaluations_path):
confhandler.load_configuration(evaluations_path)
targets_init = []
WP_VBF2j_init = []
WP_VBF1j_init = []
WP_WHh_init = []
WP_ZHh_init = []
for section_name in confhandler.get_sections():
cur_section = confhandler.get_section(section_name)
targets_init.append(float(cur_section['cost']))
WP_VBF2j_init.append(float(cur_section['WP_VBF2j']))
WP_VBF1j_init.append(float(cur_section['WP_VBF1j']))
WP_WHh_init.append(float(cur_section['WP_WHh']))
WP_ZHh_init.append(float(cur_section['WP_ZHh']))
init_dict = {
'target': targets_init,
'WP_VBF2j': WP_VBF2j_init,
'WP_VBF1j': WP_VBF1j_init,
'WP_WHh': WP_WHh_init,
'WP_ZHh': WP_ZHh_init
}
evalcnt = int(re.sub('evaluation_', '',
confhandler.get_sections()[-1])) + 1
print "resuming at evaluation " + str(evalcnt)
bo.initialize(init_dict)
initialized = True
else:
initialized = False
# change the kernel to have a length scale more appropriate to this function
gp_params = {
'kernel':
1.0 *
Matern(length_scale=0.05, length_scale_bounds=(1e-5, 1e5), nu=1.5),
'alpha':
1e-5
}
# perform the standard initialization and setup
if initialized:
bo.maximize(init_points=0,
n_iter=0,
acq='poi',
kappa=3,
xi=xi_scheduler(0.0),
**gp_params)
else:
bo.maximize(init_points=6,
n_iter=0,
acq='poi',
kappa=3,
xi=xi_scheduler(0.0),
**gp_params)
cur_iteration = 1
for it in range(1000):
cur_xi = xi_scheduler(cur_iteration)
cur_iteration += 1
print "using xi = " + str(cur_xi)
bo.maximize(init_points=6,
n_iter=1,
acq='poi',
kappa=3,
xi=cur_xi,
**gp_params)
# evaluate the current maximum
curval = bo.res['max']
cost = curval['max_val']
WPs = curval['max_params']
confhandler = ConfigFileHandler()
confhandler.config.optionxform = str
confhandler.new_section('WPs')
confhandler.set_field('WPs', 'cost', str(cost))
for key, val in WPs.iteritems():
confhandler.set_field('WPs', key, str(val))
confhandler.save_configuration(out_dir + 'WPs.txt')