def ReadData(path_to_file, sname, selection=""):
# Make data object
dataobj = Data()
# Get the data
indata = root2array(filenames = path_to_file,
treename = "tree",
branches = dataobj.t_varnames+dataobj.w_varnames,
selection = selection)
# Add an extra field for the weights
emptydata = []
for i in range(len(m_weightnames)):
emptydata.append(np.zeros(len(indata),dtype=float))
indata = append_fields(base = indata,
names = m_weightnames,
data = emptydata,
usemask = False,
dtypes=float)
# Loop and calculate the weights
weight_tool = WeightTool()
for i in range(len(indata)):
if sname == m_sname_corsika or sname == m_sname_corsikaLE:
indata[i][m_weightnames[0]] = weight_tool.getWeight(indata[i],sname)
indata[i][m_weightnames[1]] = 0
indata[i][m_weightnames[2]] = 0
elif sname == m_sname_data:
indata[i][m_weightnames[0]] = 1
indata[i][m_weightnames[1]] = 0
indata[i][m_weightnames[2]] = 0
else:
indata[i][m_weightnames[0]] = weight_tool.getWeight(indata[i],m_sname_E2)
indata[i][m_weightnames[1]] = weight_tool.getWeight(indata[i],m_sname_Conv)
indata[i][m_weightnames[2]] = weight_tool.getWeight(indata[i],m_sname_Prompt)
# Convert to record array
#indata = rec2array(indata,fields=dataobj.t_varnames + ['w'])
indata = rec2array(indata)
# Remove nan if exists
indata = indata[~np.isnan(indata).any(axis=1)]
# Get Entries
nEntries = len(indata)
# Set the targets
# 1 -- signal
# 0 -- background
if sname == m_sname_E2:
targets = np.ones(nEntries,dtype=int)
else:
targets = np.zeros(nEntries,dtype=int)
# Set properties of data object
dataobj.setData(indata)
dataobj.setTargets(targets)
dataobj.setName(sname)
#print "---------------------------------------"
#print dataobj.data
#print dataobj.targets
#print ""
return dataobj
dt_nugen = root2array(filenames = f_nugen,
branches=variables + weightvars,
treename = "tree",
selection = sel)
dt_corsika = root2array(filenames = f_corsika,
branches=variables + weightvars,
treename = "tree",
selection = sel+"&&primPDG >= 1000260530")
#-----------------------------------------#
# Calculate the weights
#-----------------------------------------#
wt = WeightTool()
w_nugen = np.zeros(len(dt_nugen),dtype=float)
for i in range(len(dt_nugen)):
w_nugen[i] = wt.getE2(dt_nugen[i])
w_corsika = np.zeros(len(dt_corsika),dtype=float)
for i in range(len(dt_corsika)):
w_corsika[i] = wt.getCorsika(dt_corsika[i])
#w_nugen = w_nugen.reshape((len(w_nugen),1))
#w_nugen = pd.DataFrame(w_nugen,columns=['w'])
#-----------------------------------------#
# Merge data
#-----------------------------------------#
def ReadData(path_to_file, sname, selection=""):
# Make data object
dataobj = Data()
# Get the data
indata = root2array(filenames=path_to_file,
treename="tree",
branches=dataobj.t_varnames + dataobj.w_varnames,
selection=selection)
# Add an extra field for the weights
emptydata = []
for i in range(len(m_weightnames)):
emptydata.append(np.zeros(len(indata), dtype=float))
indata = append_fields(base=indata,
names=m_weightnames,
data=emptydata,
usemask=False,
dtypes=float)
# Loop and calculate the weights
weight_tool = WeightTool()
for i in range(len(indata)):
if sname == m_sname_corsika or sname == m_sname_corsikaLE:
indata[i][m_weightnames[0]] = weight_tool.getWeight(
indata[i], sname)
indata[i][m_weightnames[1]] = 0
indata[i][m_weightnames[2]] = 0
elif sname == m_sname_data:
indata[i][m_weightnames[0]] = 1
indata[i][m_weightnames[1]] = 0
indata[i][m_weightnames[2]] = 0
else:
indata[i][m_weightnames[0]] = weight_tool.getWeight(
indata[i], m_sname_E2)
indata[i][m_weightnames[1]] = weight_tool.getWeight(
indata[i], m_sname_Conv)
indata[i][m_weightnames[2]] = weight_tool.getWeight(
indata[i], m_sname_Prompt)
# Convert to record array
#indata = rec2array(indata,fields=dataobj.t_varnames + ['w'])
indata = rec2array(indata)
# Remove nan if exists
indata = indata[~np.isnan(indata).any(axis=1)]
# Get Entries
nEntries = len(indata)
# Set the targets
# 1 -- signal
# 0 -- background
if sname == m_sname_E2:
targets = np.ones(nEntries, dtype=int)
else:
targets = np.zeros(nEntries, dtype=int)
# Set properties of data object
dataobj.setData(indata)
dataobj.setTargets(targets)
dataobj.setName(sname)
#print "---------------------------------------"
#print dataobj.data
#print dataobj.targets
#print ""
return dataobj
