def process_folder(in_root_folder):
for root, dirs, files in os.walk(in_root_folder):
for text_file in files:
(name, ext) = os.path.splitext(text_file)
if not ext in ['.xml', '.xhtml']:
continue
source_name = os.path.join(root, text_file)
print >>sys.stderr, 'INFO: processing file %s' % source_name
process_file(source_name, name)
plot.scatter(GLOBAL_WORDS_STAT['word_counts'], GLOBAL_WORDS_STAT['dominant_counts'])
plot.xlim(20000)
plot.title('Word count - dominant lexemes number correlation')
plot.savefig('./dominant_word_count_correlation.png')
plot.clf()
plot.scatter(GLOBAL_SENTENCES_STAT['sentence_counts'], GLOBAL_SENTENCES_STAT['dominant_counts'])
plot.xlim(2000)
plot.title('Sentence count - dominant lexemes number correlation')
plot.savefig('./dominant_sentence_count_correlation.png')
plot.clf()
plotting.make_histogram('./crirical_freq_error.png', \
'Critical frequency error histogram', \
GLOBAL_CRITICAL_FREQUENCY_ERROR_STAT, \
in_normed = False)
print 'Critical frequency error mean: ', numpy.mean(GLOBAL_CRITICAL_FREQUENCY_ERROR_STAT)
print 'Critical frequency error variance: ', numpy.std(GLOBAL_CRITICAL_FREQUENCY_ERROR_STAT)
stack = make_stack(var, cuts.name, MCGroups, dataGroup,
openedFiles, s, "iso", lumis, cuts.isoCutsMC,
cuts.isoCutsData, "", cuts.name)
stacks[var.name + s + "iso"] = stack
else:
for st in syst_type:
stack = make_stack(var, cuts.name, MCGroups, dataGroup,
openedFiles, s + st, "iso", lumis,
cuts.isoCutsMC, cuts.isoCutsData, "",
cuts.name)
stacks[var.name + s + st + "iso"] = stack
#Anti-iso region
for s in systematics:
if s == "Nominal":
make_histogram(var, dataGroup, cuts.name, openedFiles, lumis, s,
"antiiso", cuts.antiIsoCutsData)
stack = make_stack(var, cuts.name + s, MCGroups, dataGroup,
openedFiles, s, "antiiso", lumis,
cuts.antiIsoCutsMC, cuts.antiIsoCutsData, "",
cuts.name)
stacks[var.name + s + "antiiso"] = stack
#print "cuts",cuts.isoCutsData
tdrstyle.tdrstyle()
cst = TCanvas("Histogram", "Jet Systematics in final selection", 10, 10,
1000, 1000)
lumibox = lumi_textbox(lumi_iso["mu"])
histos = []
stacks = {}
#Iso region
for s in systematics:
if s == "Nominal":
stack = make_stack(var, cuts.name, MCGroups, dataGroup, openedFiles, s, "iso", lumis, cuts.isoCutsMC, cuts.isoCutsData, "", cuts.name)
stacks[var.name+s+"iso"] = stack
else:
for st in syst_type:
stack = make_stack(var, cuts.name, MCGroups, dataGroup, openedFiles, s+st, "iso", lumis, cuts.isoCutsMC, cuts.isoCutsData, "", cuts.name)
stacks[var.name+s+st+"iso"] = stack
#Anti-iso region
for s in systematics:
if s == "Nominal":
make_histogram(var, dataGroup, cuts.name, openedFiles, lumis, s, "antiiso", cuts.antiIsoCutsData)
stack = make_stack(var, cuts.name+s, MCGroups, dataGroup, openedFiles, s, "antiiso", lumis, cuts.antiIsoCutsMC, cuts.antiIsoCutsData, "", cuts.name)
stacks[var.name+s+"antiiso"] = stack
#print "cuts",cuts.isoCutsData
tdrstyle.tdrstyle()
cst = TCanvas("Histogram","Jet Systematics in final selection",10,10,1000,1000)
lumibox = lumi_textbox(lumi_iso["mu"])
histos = []
hData=dataGroup.getHistogram(var, "Nominal", "iso"+cuts.name)
#hQCDShapeOrig = dataGroup.getHistogram(var, "Nominal", "antiiso")
hData.Draw("e1")
