def runReco(inf):
#Set the channel, load in the models and normalization factors
if '3l' in inf:
channel = '3l'
ptDict = ptDictHiggsTop3lS
topModel = load_model(
"/data_ceph/afwebb/higgs_diff/topMatching/models/keras_model_top3l.h5"
)
topNormFactors = np.load(
"/data_ceph/afwebb/higgs_diff/topMatching/models/top3l_normFactors.npy",
allow_pickle=True)
model3lF = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop3lF.h5"
)
normFactors3lF = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop3lF_normFactors.npy",
allow_pickle=True)
model3lS = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop3lS.h5"
)
normFactors3lS = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop3lS_normFactors.npy",
allow_pickle=True)
elif '2lSS' in inf:
channel = '2lSS'
ptDict = ptDictHiggsTop2lSS
topModel = load_model(
"/data_ceph/afwebb/higgs_diff/topMatching/models/keras_model_top2lSS.h5"
)
topNormFactors = np.load(
"/data_ceph/afwebb/higgs_diff/topMatching/models/top2lSS_normFactors.npy",
allow_pickle=True)
model2lSS = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop2lSS.h5"
)
normFactors2lSS = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop2lSS_normFactors.npy",
allow_pickle=True)
else:
print(f'Channel {channel} is invalid. Should be 2lSS or 3l')
return
#Open the root file
f = TFile.Open(inf)
nom = f.Get('nominal')
if hasattr(nom, "recoHiggsPt_2lSS") or hasattr(nom, "recoHiggsPt_3lS"):
print(f'{inf} already has score')
return
#initialize output dicts
events = []
higgsRecoScores = []
topRecoScores = []
if channel == '3l':
events3lF = []
eventsDecay = []
higgsRecoScoresF = []
#Loop over all entries
nEntries = nom.GetEntries()
for idx in range(nEntries):
if idx % 10000 == 0:
print(str(idx) + '/' + str(nEntries))
#Get the events
nom.GetEntry(idx)
#Find the best top combination, top reco score
topRes = findBestTopKeras(nom, channel, topModel, topNormFactors)
if not topRes:
topIdx0, topIdx1 = 0, 0
topScore = np.float32(-10)
else:
topIdx0, topIdx1 = topRes['bestComb']
topScore = topRes['topScore']
topRecoScores.append(topScore) # add the top reco score
#Find the higgs decay products, higgs reco score for 3lF model
if channel == '3l':
res3lF = findBestHiggsTop(nom, '3lF', model3lF, normFactors3lF,
topIdx0, topIdx1, topScore)
#if not res3lF: continue
higgsTopScoreF = res3lF['higgsTopScore']
lepIdx = res3lF['bestComb'][0]
events3lF.append(
ptDictHiggsTop3lF(nom, lepIdx, higgsTopScoreF, topIdx0,
topIdx1, topScore))
higgsRecoScoresF.append(higgsTopScoreF)
#Find the higgs decay products, higgs reco score for 3lS, 2lSS (same final state)
if channel == '3l':
res = findBestHiggsTop(nom, '3lS', model3lS, normFactors3lS,
topIdx0, topIdx1, topScore)
else:
res = findBestHiggsTop(nom, '2lSS', model2lSS, normFactors2lSS,
topIdx0, topIdx1, topScore)
if not res:
higgsTopScore = np.float32(-10)
lepIdx, jetIdx0, jetIdx1 = 1, 0, 0
else:
higgsTopScore = res['higgsTopScore']
lepIdx, jetIdx0, jetIdx1 = res['bestComb']
#add the pt prediction dictionary
events.append(
ptDict(nom, jetIdx0, jetIdx1, lepIdx, higgsTopScore, topIdx0,
topIdx1, topScore))
higgsRecoScores.append(higgsTopScore)
#add decay mode dicts
if channel == '3l':
eventsDecay.append(
decayDict(nom, higgsTopScoreF, higgsTopScore, topIdx0, topIdx1,
topScore))
if channel == '3l':
return events, events3lF, eventsDecay, higgsRecoScores, higgsRecoScoresF, topRecoScores
else:
return events, higgsRecoScores, topRecoScores
def runReco(inf):
#load in the top model - not picklable, can't do outside the function
topModel = load_model(
"/data_ceph/afwebb/higgs_diff/topMatching/models/keras_model_top3l.h5")
topNormFactors = np.load(
"/data_ceph/afwebb/higgs_diff/topMatching/models/top3l_normFactors.npy"
)
topMaxVals = topNormFactors[0]
topMinVals = topNormFactors[1]
topDiff = topMaxVals - topMinVals
model3lF = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop3lF.h5"
)
normFactors3lF = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop3lF_normFactors.npy"
)
maxVals3lF, minVals3lF = normFactors3lF
diff3lF = maxVals3lF - minVals3lF
model3lS = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop3lS.h5"
)
normFactors3lS = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop3lS_normFactors.npy"
)
maxVals3lS, minVals3lS = normFactors3lS
diff3lS = maxVals3lS - minVals3lS
f = TFile.Open(inf)
nom = f.Get('nominal')
#initialize output dicts
events = []
#Loop over all entries
nEntries = nom.GetEntries()
for idx in range(nEntries):
if idx % 10000 == 0:
print(str(idx) + '/' + str(nEntries))
nom.GetEntry(idx)
#Perform top matching. Get top candidates, topScore
topRes = findBestTopKeras(nom, '3l', topModel, topNormFactors)
if not topRes: continue
topIdx0, topIdx1 = topRes['bestComb']
topScore = topRes['topScore']
#Perform higgs matching. Get 3lF, 3lS scores
res3lF = findBestHiggsTop(nom, '3lF', model3lF, normFactors3lF,
topIdx0, topIdx1, topScore)
res3lS = findBestHiggsTop(nom, '3lS', model3lS, normFactors3lS,
topIdx0, topIdx1, topScore)
if not res3lF or not res3lS: continue
#identify which lepton came from the Higgs
lepIdx = -1
if nom.lep_Parent_0 == 25:
isF = True
else:
isF = False
if nom.lep_Parent_1 == 25: lepIdx = 1
if nom.lep_Parent_2 == 25: lepIdx = 2
if lepIdx == -1: continue
if isF:
events.append(
decayDict(nom, res3lF['higgsTopScore'],
res3lS['higgsTopScore'], topIdx0, topIdx1, topScore,
0)) #Correct combination
else:
events.append(
decayDict(nom, res3lF['higgsTopScore'],
res3lS['higgsTopScore'], topIdx0, topIdx1, topScore,
1)) #Incorrect combination - swaps 2 and 1
dfFlat = pd.DataFrame.from_dict(events)
dfFlat = shuffle(dfFlat)
outF = '/'.join(inf.split("/")[-2:]).replace('.root', '.csv')
dfFlat.to_csv('csvFiles/' + outF, index=False)
nom.GetEntry(idx)
if '3l' in channel:
if channel == '3lF' and nom.lep_Parent_0 != 25: continue
if channel == '3lS' and nom.lep_Parent_0 == 25: continue
topRes = findBestTopKeras(nom, '3l', topModel, topNormFactors)
else:
topRes = findBestTopKeras(nom, '2lSS', topModel, topNormFactors)
if not topRes:
continue
topIdx0, topIdx1 = topRes['bestComb']
topScore = topRes['topScore']
#Get dict of all possible jet combinations
higgsRes = findBestHiggsTop(nom, channel, higgsModel, higgsNormFactors,
topIdx0, topIdx1, topScore)
if not higgsRes: continue
higgsMatches = higgsRes['bestComb']
truthPair = higgsRes['truthComb']
if channel == '3lF' and len(truthPair) != 1:
continue
elif channel != '3lF' and len(truthPair) != 3:
continue
nEvents += 1
if higgsMatches == truthPair:
nCorrect += 1
if higgsMatches[0] == truthPair[0]:
lepCorrect += 1
if channel != '3lF':
def runReco(inf):
#Set the channel, load in the top model
if '3l' in inf:
channel = '3l'
is3l = True
ptDict = ptDictHiggsTop3lS
topModel = load_model(
"/data_ceph/afwebb/higgs_diff/topMatching/models/keras_model_top3l.h5"
)
topNormFactors = np.load(
"/data_ceph/afwebb/higgs_diff/topMatching/models/top3l_normFactors.npy"
)
model3lF = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop3lF.h5"
)
normFactors3lF = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop3lF_normFactors.npy"
)
model3lS = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop3lS.h5"
)
normFactors3lS = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop3lS_normFactors.npy"
)
elif '2lSS' in inf:
channel = '2lSS'
ptDict = ptDictHiggsTop2lSS
is3l = False
topModel = load_model(
"/data_ceph/afwebb/higgs_diff/topMatching/models/keras_model_top2lSS.h5"
)
topNormFactors = np.load(
"/data_ceph/afwebb/higgs_diff/topMatching/models/top2lSS_normFactors.npy"
)
model2lSS = load_model(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/keras_model_higgsTop2lSS.h5"
)
normFactors2lSS = np.load(
"/data_ceph/afwebb/higgs_diff/higgsMatching/models/higgsTop2lSS_normFactors.npy"
)
else:
print(f'Channel {channel} is invalid. Should be 2lSS or 3l')
exit()
f = TFile.Open(inf)
nom = f.Get('nominal')
#initialize output dicts
events = []
events3lF = []
#Loop over all entries
nEntries = nom.GetEntries()
for idx in range(nEntries):
if idx % 10000 == 0:
print(str(idx) + '/' + str(nEntries))
nom.GetEntry(idx)
#Get the Higgs Pt
for i, pdgId in enumerate(nom.m_truth_pdgId):
if pdgId == 25:
higgs_pt = nom.m_truth_pt[i]
break
if not higgs_pt:
continue
topRes = findBestTopKeras(nom, channel, topModel, topNormFactors)
if not topRes: continue
topIdx0, topIdx1 = topRes['bestComb']
topScore = topRes['topScore']
isF = False
if is3l and nom.lep_Parent_0 == 25:
isF = True
if isF:
res3lF = findBestHiggsTop(nom, '3lF', model3lF, normFactors3lF,
topIdx0, topIdx1, topScore)
if not res3lF: continue
higgsTopScore = res3lF['higgsTopScore']
lepIdx = res3lF['bestComb'][0]
events3lF.append(
ptDictHiggsTop3lF(nom, lepIdx, higgsTopScore, topIdx0, topIdx1,
topScore, higgs_pt))
else:
if is3l:
res = findBestHiggsTop(nom, '3lS', model3lS, normFactors3lS,
topIdx0, topIdx1, topScore)
else:
res = findBestHiggsTop(nom, '2lSS', model2lSS, normFactors2lSS,
topIdx0, topIdx1, topScore)
if not res: continue
higgsTopScore = res['higgsTopScore']
lepIdx, jetIdx0, jetIdx1 = res['bestComb']
events.append(
ptDict(nom, jetIdx0, jetIdx1, lepIdx, higgsTopScore, topIdx0,
topIdx1, topScore, higgs_pt))
dfFlat = pd.DataFrame.from_dict(events)
dfFlat = shuffle(dfFlat)
outF = '/'.join(inf.split("/")[-2:]).replace('.root', '.csv')
if channel == '2lSS':
dfFlat.to_csv('inputFiles/higgsTop2lSS/' + outF, index=False)
elif channel == '3l':
dfFlat.to_csv('inputFiles/higgsTop3lS/' + outF, index=False)
df3lF = pd.DataFrame.from_dict(events3lF)
df3lF = shuffle(df3lF)
df3lF.to_csv('inputFiles/higgsTop3lF/' + outF, index=False)