def __init__(self,Cluster=1):
FileName = '/Users/rca/hadley/eddy_stress/bruce/MasatoWBindices.txt'
y = read_table(FileName)
y = array(y).transpose()
year = arange(1958,2002)
self.YearStart = year[0]
self.YearStop = year[-1]
self.index = y[Cluster-1]
def create_df(columns, grp, myrank, ranks):
''' create a dataframe, given file, group and list of datasets
arguments:
columns: datasets to be read as columns in a dataframe
grp: group name to be read
fname: file name of the file to read
myrank: process's rank
ranks: total number of MPI ranks in the job
output: a data frame per rank consisting of columns
'''
return pd.DataFrame(read_table.read_table(columns, grp, myrank, ranks))
def test_read_table():
data = [
["a1", "b1 author1 Search 21", "Attach1", "d1"],
["a2", "b2 author2 Search 22", "Attach2", "d2"],
["a3", "b3 author3 Search 23", "Attach3", "d3"],
["a4", "b4 author4 Search 24", "Attach4", "d4"],
]
columns = ["No", "Title", "Attach", "Published"]
input_table = pd.DataFrame(data, columns=columns, index=range(4))
with tempfile.NamedTemporaryFile(mode='w+t') as fp_sample_html:
input_table.to_html(fp_sample_html)
fp_sample_html.seek(0)
result = read_table.read_table(fp_sample_html)
assert isinstance(result, pd.DataFrame)
assert 'subject' in result.columns
assert 'author' in result.columns
assert 'count' in result.columns
assert 'Attach' in result.columns
assert 'Published' in result.columns
def main_fake_rate_measurement(prefix, output_name, etaregion="", procname="ttbar6"):
# Parse the input arguments
try:
ntuple_version = sys.argv[1]
tag = sys.argv[2]
except:
usage()
if "2016" in ntuple_version: lumi = 35.9
if "2017" in ntuple_version: lumi = 41.3
if "2018" in ntuple_version: lumi = 59.74
basedir = "plots/{}/{}/lin/".format(ntuple_version, tag)
# Denominator : fake from data (i.e. data - prompt)
yields_ddfake = rt.read_table(basedir + prefix + "Prompt__lepFakeCand2PtFineVarBin"+etaregion+".txt")
yields_ddfake["ddfake"] = []
for datacount, bkgcount in zip(yields_ddfake["data"], yields_ddfake["Total"]):
yields_ddfake["ddfake"].append(datacount - bkgcount)
# print yields_ddfake["ddfake"]
# Numerator : fake from data (i.e. data - prompt)
yields_ddfake_tight = rt.read_table(basedir + prefix + "TightPrompt__lepFakeCand2PtFineVarBin"+etaregion+".txt")
yields_ddfake_tight["ddfake"] = []
for datacount, bkgcount in zip(yields_ddfake_tight["data"], yields_ddfake_tight["Total"]):
yields_ddfake_tight["ddfake"].append(datacount - bkgcount)
# print yields_ddfake_tight["ddfake"]
fr_data = []
for den, num in zip(yields_ddfake["ddfake"], yields_ddfake_tight["ddfake"]):
if den.val != 0:
fr = num / den
fr_data.append(fr)
else:
fr_data.append(E(0, 0))
fr_data.pop(0) # first one is underflow bin
fr_data.pop(0) # second one is underflow bin
fr_data.pop(-1) # last one is overflow bin
print(fr_data)
# Denominator: Fake directly from ttbar MC
yields_ttbar = rt.read_table(basedir + prefix + "Fake__lepFakeCand2PtFineVarBin"+etaregion+".txt")
# print yields_ttbar[procname]
# Numerator: fake from data (i.e. data - prompt)
yields_ttbar_tight = rt.read_table(basedir + prefix + "TightFake__lepFakeCand2PtFineVarBin"+etaregion+".txt")
# print yields_ttbar_tight[procname]
fr_mc = []
for den, num in zip(yields_ttbar[procname], yields_ttbar_tight[procname]):
if den.val != 0:
fr = num / den
fr_mc.append(fr)
else:
fr_mc.append(E(0, 0))
print(fr_mc)
fr_mc.pop(0) # first one is underflow bin
fr_mc.pop(0) # second one is underflow bin
fr_mc.pop(-1) # last one is overflow bin
# bin boundaries
# bounds = [0., 10., 15., 20., 30., 150.]
# bounds = [0., 10., 20., 70.]
bounds = [0., 10., 20., 30., 50., 70.]
h_fr_data = r.TH1F("FR","",len(bounds)-1,array('d',bounds))
h_fr_mc = r.TH1F("FR","",len(bounds)-1,array('d',bounds))
for idx, fr in enumerate(fr_data):
h_fr_data.SetBinContent(idx+2, fr.val)
h_fr_data.SetBinError(idx+2, fr.err)
for idx, fr in enumerate(fr_mc):
h_fr_mc.SetBinContent(idx+2, fr.val)
h_fr_mc.SetBinError(idx+2, fr.err)
# Options
alloptions= {
"ratio_range":[0.0,2.0],
"nbins": 180,
"autobin": False,
"legend_scalex": 0.8,
"legend_scaley": 0.8,
"output_name": basedir + "/"+output_name+".pdf",
"bkg_sort_method": "unsorted",
"no_ratio": False,
"print_yield": True,
"yield_prec": 3,
"draw_points": True,
"hist_line_none": True,
"show_bkg_errors": True,
"lumi_value" : lumi,
# "yaxis_range": [0., 1],
}
p.plot_hist(
sigs = [],
bgs = [h_fr_mc.Clone()],
data = h_fr_data.Clone(),
syst = None,
colors=[2001],
legend_labels=["MC t#bar{t}"],
options=alloptions)
return h_fr_mc.Clone(), h_fr_data.Clone()
def __init__(self):
FileName = '/Users/rca/hadley/eddy_stress/bruce/WaveActivityIndex.txt'
year,index = read_table(FileName)
self.YearStart = int(year[0])
self.YearStop = int(year[-1])
self.index = index
