def finalize( self ):
from Gaugi import save, mkdir_p
outputname = self.getProperty("OutputFile")
for etBinIdx in range(len(self._etbins)-1):
for etaBinIdx in range(len(self._etabins)-1):
key = 'et%d_eta%d' % (etBinIdx,etaBinIdx)
mkdir_p( outputname )
if self._event[key] is None:
continue
d = {
"features" : self._event_label,
"etBins" : self._etbins,
"etaBins" : self._etabins,
"etBinIdx" : etBinIdx,
"etaBinIdx" : etaBinIdx
}
d[ 'pattern_'+key ] = np.array( self._event[key] )
MSG_INFO( self, 'Saving %s with : (%d, %d)', key, d['pattern_'+key].shape[0], d['pattern_'+key].shape[1] )
save( d, outputname+'/'+outputname+"_"+key , protocol = 'savez_compressed')
return StatusCode.SUCCESS
def __call__(self, **kw):
# Cross validation configuration
outputFolder = retrieve_kw(kw, 'outputFolder', 'jobConfig')
sortBounds = retrieve_kw(kw, 'sortBounds', 5)
nInits = retrieve_kw(kw, 'nInits', 10)
nSortsPerJob = retrieve_kw(kw, 'nSortsPerJob', 1)
nInitsPerJob = retrieve_kw(kw, 'nInitsPerJob', 10)
nModelsPerJob = retrieve_kw(kw, 'nModelsPerJob', 1)
models = retrieve_kw(kw, 'models', [default_model])
model_tags = retrieve_kw(kw, 'model_tags', ['mlp_100_5_1'])
crossval = retrieve_kw(kw, 'crossval',
KFold(10, shuffle=True, random_state=512))
time_stamp = self.time_stamp()
# creating the job mechanism file first
mkdir_p(outputFolder)
if type(models) is not list:
models = [models]
modelJobsWindowList = create_iter(
lambda i, sorts: list(range(i, i + sorts)), nModelsPerJob,
len(models))
sortJobsWindowList = create_iter(
lambda i, sorts: list(range(i, i + sorts)), nSortsPerJob,
sortBounds)
initJobsWindowList = create_iter(
lambda i, sorts: list(range(i, i + sorts)), nInitsPerJob, nInits)
nJobs = 0
for (model_idx_list, sort_list,
init_list) in product(modelJobsWindowList, sortJobsWindowList,
initJobsWindowList):
MSG_INFO(
self,
'Creating job config with sort (%d to %d) and %d inits and model Index %d to %d',
sort_list[0], sort_list[-1], len(init_list), model_idx_list[0],
model_idx_list[-1])
from saphyra.core.readers.versions import Job_v1
job = Job_v1()
# to be user by the database table
job.setId(nJobs)
job.setSorts(sort_list)
job.setInits(init_list)
job.setModels([models[idx] for idx in model_idx_list],
model_idx_list)
# save config file
model_str = 'ml%i.mu%i' % (model_idx_list[0], model_idx_list[-1])
sort_str = 'sl%i.su%i' % (sort_list[0], sort_list[-1])
init_str = 'il%i.iu%i' % (init_list[0], init_list[-1])
job.save(outputFolder + '/' + ('job_config.ID_%s.%s_%s_%s.%s') %
(str(nJobs).zfill(4), model_str, sort_str, init_str,
time_stamp))
nJobs += 1
MSG_INFO(self, "A total of %d jobs...", nJobs)
numberOfJobs = 1
from Gaugi import save, mkdir_p
mkdir_p('job_config_dummy')
for job_id in range(numberOfJobs):
name = 'job_config_dummy/job_config.id%1.4d.dummy' % (job_id)
f = open(name, 'w')
f.write(str(job_id))
f.close()
f = open('data.dummy', 'w')
f.close()
def plot(self, dirnames, pdfoutputs, pdftitles, runLabel='', doPDF=True):
SetAtlasStyle()
beamer_plots = {}
global tobject_collector
basepath = self.getProperty("Basepath")
etBins = self.getProperty("EtBinningValues")
etaBins = self.getProperty("EtaBinningValues")
for idx, feat in enumerate(self.__selectionFeatures):
dirname = os.getcwd() + '/' + dirnames[idx]
mkdir_p(dirname)
# hold selection name
selection_name = feat.name_a() + '_Vs_' + feat.name_b()
# For beamer...
if not selection_name in beamer_plots.keys():
beamer_plots[selection_name] = {}
beamer_plots[selection_name]['integrated'] = {}
### Plot binning plots
if (len(etBins) * len(etaBins)) > 1:
for etBinIdx, etaBinIdx in progressbar(
product(range(len(etBins) - 1),
range(len(etaBins) - 1)),
(len(etBins) - 1) * (len(etaBins) - 1),
prefix="Plotting... ",
logger=self._logger):
# hold binning name
binning_name = ('et%d_eta%d') % (etBinIdx, etaBinIdx)
# for beamer...
if not binning_name in beamer_plots[selection_name].keys():
beamer_plots[selection_name][binning_name] = {}
### loop over standard quantities
for key in standardQuantitiesNBins.keys():
outname = dirname + '/' + selection_name.replace(
'_Vs_', '_') + '_' + key + '_' + binning_name
out = PlotQuantities(basepath + '/' + selection_name +
'/' + binning_name,
key,
outname,
etidx=etBinIdx,
etaidx=etaBinIdx,
xlabel=electronQuantities[key],
divide='b',
runLabel=runLabel)
beamer_plots[selection_name][binning_name][key] = out
#del tobject_collector[:]
### loop over info quantities
for key in basicInfoQuantities.keys():
outname = dirname + '/' + selection_name.replace(
'_Vs_', '_') + '_' + key + '_' + binning_name
out = PlotQuantities(basepath + '/' + selection_name +
'/' + binning_name,
key,
outname,
etidx=etBinIdx,
etaidx=etaBinIdx,
xlabel=basicInfoQuantities[key],
divide='b',
runLabel=runLabel)
beamer_plots[selection_name][binning_name][key] = out
#del tobject_collector[:]
beamer_plots[selection_name][binning_name]['statistics'] = GetStatistics(basepath+'/'+selection_name+'/'+binning_name, \
'avgmu',etidx=etBinIdx,etaidx=etaBinIdx)
#### Plot integrated histograms
### loop over standard quantities
for key in standardQuantitiesNBins.keys():
outname = dirname + '/' + selection_name.replace(
'_Vs_', '_') + '_' + key
out = PlotQuantities(basepath + '/' + selection_name,
key,
outname,
xlabel=electronQuantities[key],
divide='b',
runLabel=runLabel,
addbinlines=True)
beamer_plots[selection_name]['integrated'][key] = out
tobject_collector = []
gc.collect()
### loop over info quantities
for key in basicInfoQuantities.keys():
outname = dirname + '/' + selection_name.replace(
'_Vs_', '_') + '_' + key + '_' + binning_name
out = PlotQuantities(basepath + '/' + selection_name,
key,
outname,
xlabel=basicInfoQuantities[key],
divide='b',
runLabel=runLabel,
addbinlines=True)
beamer_plots[selection_name]['integrated'][key] = out
tobject_collector = []
gc.collect()
beamer_plots[selection_name]['integrated'][
'statistics'] = GetStatistics(basepath + '/' + selection_name,
'avgmu')
def plot(self,
dirnames,
pdfoutputs,
pdftitles,
runLabel='',
doPDF=True,
legends=None):
legends = [
'Both Approved', 'Ringer Rejected', 'Ringer Approved',
'Both Rejected'
] if legends is None else legends
SetAtlasStyle()
beamer_plots = {}
global tobject_collector
basepath = self.getProperty("Basepath")
etBins = self.getProperty("EtBinningValues")
etaBins = self.getProperty("EtaBinningValues")
sg = self.getStoreGateSvc()
for idx, feat in enumerate(self.__quadrantFeatures):
dirname = os.getcwd() + '/' + dirnames[idx]
mkdir_p(dirname)
# hold quadrant name
quadrant_name = feat.name_a() + '_Vs_' + feat.name_b()
# For beamer...
if not quadrant_name in beamer_plots.keys():
beamer_plots[quadrant_name] = {}
beamer_plots[quadrant_name]['integrated'] = {}
### Plot binning plots
if (len(etBins) * len(etaBins)) > 1:
for etBinIdx, etaBinIdx in progressbar(
product(range(len(etBins) - 1),
range(len(etaBins) - 1)),
(len(etBins) - 1) * (len(etaBins) - 1),
prefix="Plotting... ",
logger=self._logger):
# hold binning name
binning_name = ('et%d_eta%d') % (etBinIdx, etaBinIdx)
# for beamer...
if not binning_name in beamer_plots[quadrant_name].keys():
beamer_plots[quadrant_name][binning_name] = {}
### loop over standard quantities
for key in standardQuantitiesNBins.keys():
outname = dirname + '/' + quadrant_name.replace(
'_Vs_', '_') + '_' + key + '_' + binning_name
out = PlotQuantities(sg,
basepath + '/' + quadrant_name +
'/' + binning_name,
key,
outname,
legends,
etBins=etBins,
etaBins=etaBins,
etidx=etBinIdx,
etaidx=etaBinIdx,
xlabel=electronQuantities[key],
divide='b',
runLabel=runLabel)
beamer_plots[quadrant_name][binning_name][key] = out
#del tobject_collector[:]
### loop over info quantities
for key in basicInfoQuantities.keys():
outname = dirname + '/' + quadrant_name.replace(
'_Vs_', '_') + '_' + key + '_' + binning_name
out = PlotQuantities(sg,
basepath + '/' + quadrant_name +
'/' + binning_name,
key,
outname,
legends,
etBins=etBins,
etaBins=etaBins,
etidx=etBinIdx,
etaidx=etaBinIdx,
xlabel=basicInfoQuantities[key],
divide='b',
runLabel=runLabel)
beamer_plots[quadrant_name][binning_name][key] = out
#del tobject_collector[:]
beamer_plots[quadrant_name][binning_name]['statistics'] = GetStatistics(sg, basepath+'/'+quadrant_name+'/'+binning_name, \
'avgmu',etidx=etBinIdx,etaidx=etaBinIdx,
etBins=etBins, etaBins=etaBins)
#### Plot integrated histograms
### loop over standard quantities
for key in standardQuantitiesNBins.keys():
outname = dirname + '/' + quadrant_name.replace(
'_Vs_', '_') + '_' + key
out = PlotQuantities(sg,
basepath + '/' + quadrant_name,
key,
outname,
legends,
xlabel=electronQuantities[key],
divide='b',
runLabel=runLabel,
addbinlines=True,
etBins=etBins,
etaBins=etaBins)
beamer_plots[quadrant_name]['integrated'][key] = out
tobject_collector = []
gc.collect()
### loop over info quantities
for key in basicInfoQuantities.keys():
outname = dirname + '/' + quadrant_name.replace(
'_Vs_', '_') + '_' + key + '_' + binning_name
out = PlotQuantities(sg,
basepath + '/' + quadrant_name,
key,
outname,
legends,
xlabel=basicInfoQuantities[key],
divide='b',
runLabel=runLabel,
addbinlines=True,
etBins=etBins,
etaBins=etaBins)
beamer_plots[quadrant_name]['integrated'][key] = out
tobject_collector = []
gc.collect()
beamer_plots[quadrant_name]['integrated'][
'statistics'] = GetStatistics(sg,
basepath + '/' + quadrant_name,
'avgmu',
etBins=etBins,
etaBins=etaBins)
if doPDF:
### Make Latex str et/eta labels
etbins_str = []
etabins_str = []
for etBinIdx in range(len(etBins) - 1):
etbin = (etBins[etBinIdx], etBins[etBinIdx + 1])
if etbin[1] > 100:
etbins_str.append(r'$E_{T}\text{[GeV]} > %d$' % etbin[0])
else:
etbins_str.append(r'$%d < E_{T} \text{[Gev]}<%d$' % etbin)
for etaBinIdx in range(len(etaBins) - 1):
etabin = (etaBins[etaBinIdx], etaBins[etaBinIdx + 1])
etabins_str.append(r'$%.2f<\eta<%.2f$' % etabin)
for slideIdx, feat in enumerate(self.__quadrantFeatures):
with BeamerTexReportTemplate1(theme='Berlin',
_toPDF=True,
title=pdftitles[slideIdx],
outputFile=pdfoutputs[slideIdx],
font='structurebold'):
# hold quadrant name
quadrant_name = feat.name_a() + '_Vs_' + feat.name_b()
section_name = feat.name_a() + ' Vs ' + feat.name_b()
#with BeamerSection( name = 'x' ):
with BeamerSection(name='Integrated Quantities'):
# prepare files for basic quantities
figures = []
for key in ['et', 'eta', 'phi', 'avgmu', 'nvtx']:
figures.append(
beamer_plots[quadrant_name]['integrated'][key])
BeamerMultiFigureSlide(
title='Basic Quantities',
paths=figures,
nDivWidth=3 # x
,
nDivHeight=2 # y
,
texts=None,
fortran=False,
usedHeight=0.6,
usedWidth=0.9)
# prepare files for calo standard quantities
figures = []
for key in [
'eratio', 'rhad', 'reta', 'rphi', 'f1', 'f3',
'wtots1', 'weta2'
]:
figures.append(
beamer_plots[quadrant_name]['integrated'][key])
BeamerMultiFigureSlide(
title='Standard Calo Quantities',
paths=figures,
nDivWidth=4 # x
,
nDivHeight=2 # y
,
texts=None,
fortran=False,
usedHeight=0.6,
usedWidth=0.9)
# prepare files for calo standard quantities
figures = []
for key in [
'd0significance', 'trackd0pvunbiased',
'deltaPhiRescaled2', 'eProbabilityHT',
'TRT_PID', 'deltaEta1', 'DeltaPOverP'
]:
figures.append(
beamer_plots[quadrant_name]['integrated'][key])
BeamerMultiFigureSlide(
title='Standard Track Quantities',
paths=figures,
nDivWidth=4 # x
,
nDivHeight=2 # y
,
texts=None,
fortran=False,
usedHeight=0.6,
usedWidth=0.9)
section = ['Basic Quantity'] * 2
section.extend(['Standard Calo Quantity'] * 8)
section.extend(['Standard Track Quantity'] * 7)
section.extend([
'Likelihood Discriminant', 'Ringer Neural Discriminant'
])
for idx, key in enumerate([
'avgmu',
'nvtx',
'eratio',
'rhad',
'reta',
'rphi',
'f1',
'f3',
'wtots1',
'weta2',
'd0significance',
'trackd0pvunbiased',
'deltaPhiRescaled2',
'eProbabilityHT',
'TRT_PID',
'deltaEta1',
'DeltaPOverP',
#'lhOutput','nnOutput'
]):
with BeamerSection(name=key.replace('_', '\_')):
figures = []
binning_name_list = []
for etBinIdx, etaBinIdx in product(
range(len(etBins) - 1),
range(len(etaBins) - 1)):
binning_name_list.append(
('et%d_eta%d') % (etBinIdx, etaBinIdx))
while len(binning_name_list) > 0:
figures = []
if len(binning_name_list) > 9:
for _ in range(9):
binning_name = binning_name_list.pop(0)
figures.append(
beamer_plots[quadrant_name]
[binning_name][key])
else:
for _ in range(len(binning_name_list)):
binning_name = binning_name_list.pop(0)
figures.append(
beamer_plots[quadrant_name]
[binning_name][key])
BeamerMultiFigureSlide(
title=section[idx] + ' (' +
key.replace('_', '\_') + ')',
paths=figures,
nDivWidth=4 # x
,
nDivHeight=3 # y
,
texts=None,
fortran=False,
usedHeight=0.7,
usedWidth=0.8)
with BeamerSection(name='Statistics'):
### Prepare tables
lines1 = []
lines1 += [HLine(_contextManaged=False)]
lines1 += [HLine(_contextManaged=False)]
#lines1 += [ TableLine( columns = ['kinematic region'] + reduce(lambda x,y: x+y,[ [r'\multicol{4}{*}{'+s+'}','','',''] for s in etbins_str]), \
lines1 += [ TableLine( columns = ['kinematic region'] + reduce(lambda x,y: x+y,[ [s,'','',''] for s in etbins_str]), \
_contextManaged = False ) ]
lines1 += [HLine(_contextManaged=False)]
lines1 += [ TableLine( columns = ['Det. Region'] + reduce(lambda x,y: x+y,[[r'$Q_{ij}$',r'$\rho{ij}$',r'$\kappa_{P}$',r'$dis_{ij}$'] \
#lines1 += [ TableLine( columns = ['Det. Region'] + reduce(lambda x,y: x+y,[['a','b','c','d'] \
for _ in etbins_str]), _contextManaged = False ) ]
lines1 += [HLine(_contextManaged=False)]
for etaBinIdx in range(len(etaBins) - 1):
str_values = []
for etBinIdx in range(len(etBins) - 1):
binning_name = ('et%d_eta%d') % (etBinIdx,
etaBinIdx)
stats = beamer_plots[quadrant_name][
binning_name]['statistics']
str_values += [
'%1.2f' % stats['Qij'],
'%1.2f' % stats['Pij'],
'%1.2f' % stats['Kp'],
'%1.2f' % stats['dis_ij']
]
lines1 += [
TableLine(columns=[etabins_str[etaBinIdx]] +
str_values,
_contextManaged=False)
]
lines1 += [HLine(_contextManaged=False)]
lines1 += [HLine(_contextManaged=False)]
with BeamerSlide(title="The General Statistics"):
with Table(
caption='The statistics pair wise values.'
) as table:
with ResizeBox(size=0.9) as rb:
with Tabular(columns='|l|' + 'cccc|' *
len(etbins_str)) as tabular:
tabular = tabular
for line in lines1:
if isinstance(line, TableLine):
tabular += line
else:
TableLine(line, rounding=None)